Research

Areas of Research

Motion Planning

Autonomous Vehicls and Intelligent Transportation Systems

Task and Mission Planning

Vision and Machine Learning

Papers at Scholar

Socially-aware Robot Motion Planning (Learning-based techniques)

Text

Key Publications

  • R. Kala (2023) Autonomous Mobile Robots: Planning, Navigation and Simulation, Elsevier
  • SMH Jafri, R. Kala (2023) Dynamic Head-on Robot Collision Avoidance Using LSTM. Neural Processing Letters 55: 1173–1208.
  • SMH Jafri, R. Kala (2022) End-to-end human inspired learning based system for dynamic obstacle avoidance. Complex and Intelligent Systems 8: 5065–5086.
  • A. Malviya, R. Kala, R. (2022) Learning-based simulation and modeling of unorganized chaining behavior using data generated from 3D human motion tracking. Robotica, 40(3), 544-569.
  • S. Beohar, F. Heinrich, R. Kala, H. Ritter, A. Melnik, Solving Learn-to-Race Autonomous Racing Challenge by Planning in Latent Space, In: ICML’22 Workshop on Safe Learning For Autonomous Driving.
  • M. Vallecha, R. Kala (2022) Group and Socially Aware Multi-Agent Reinforcement Learning. In 2022 30th Mediterranean Conference on Control and Automation (MED), pp. 73-78, Athens, Greece.
  • I. Sethi, A. Trivedi, P. Singhal, M. Bhawe, R. Agarwal, R. Kala, G. C. Nandi (2022) Group-Aware Human Trajectory Prediction. In: 2022 IEEE 6th Conference on Information and Communication Technology (CICT), Gwalior, India, 2022, pp. 1-5.
  • A. Khare, R. Motwani, S. Akash, J. Patil, R. Kala (2018) Learning the Goal Seeking Behaviour for Mobile Robots. In: Proceedings of the 2018 3rd Asia-Pacific Conference on Intelligent Robot Systems, IEEE, Singapore, pp. 56-60.

Behaviour-Driven Intelligent Transportation Systems

Text

Key Publications

  • R. Kala (2023) Autonomous Mobile Robots: Planning, Navigation and Simulation, Elsevier
  • R. Chandra, M. Mahajan, R. Kala, R. Palugulla, C. Naidu, A. Jain, D. Manocha (2023) METEOR: A Dense, Heterogeneous, and Unstructured Traffic Dataset with Rare Behaviors, In: IEEE International Conference on Robotics and Automation (ICRA), pp. 9169-9175, London, United Kingdom.
  • A. Malviya, R. Kala, (2022) Risk Modeling of the Overtaking Behavior in the Indian Traffic. In 2022 IEEE 25th International Conference on Intelligent Transportation Systems (ITSC), pp. 2882-2887, Macau, China.
  • R. B. Jha, A. Rai and R. Kala (2021) Predictive Risk Analysis using Deep Learning in Indian Traffic. In: Proceedings of the 2021 IEEE International Intelligent Transportation Systems Conference (ITSC), pp. 258-263.

Simultanious Localization and Mapping (SLAM)

Text

Key Publications

  • R. Kala (2023) Autonomous Mobile Robots: Planning, Navigation and Simulation, Elsevier
  • V. Paturkar, R. Yadav, R. Kala (2024) Sequential visual place recognition using semantically-enhanced features, Multimedia Tools and Applications, DOI: 10.1007/s11042-023-17404-4.
  • R. Yadav, V. Pani, A. Mishra, N. Tiwari, R. Kala (2023) Locality-constrained continuous place recognition for SLAM in extreme conditions. Applied Intelligence 53: 17593–17609.
  • L. Kenye, R. Kala (2023) Low-Cost Simultaneous Localization and Mapping Using Occupancy Grid, Place Recognition and Semantic Priors. In: 2023 32nd IEEE International Conference on Robot and Human Interactive Communication (RO-MAN), pp. 1083-1088, Busan, Korea.
  • R. Yadav, R. Kala (2022) Fusion of Visual Odometry and Place Recognition for SLAM in Extreme Conditions, Applied Intelligence 52: 11928–11947.
  • L. Kenye, R. Kala (2022) Improving RGB-D SLAM in Dynamic Environments using Semantic Aided Segmentation, Robotica, 40(6), 2065-2090.
  • L. Kenye, R. Kala (2022) Feature-Based Correspondence Filtering Using Structural Similarity Index for Visual Odometry, International Journal of Pattern Recognition and Artificial Intelligence 36(9): 2255013.
  • L. Kenye, R. Kala (2022) An Ensemble of Spatial Clustering and Temporal Error Profile Based Dynamic Point Removal for visual Odometry, Multimedia Tools and Applications 81: 23259–23288.
  • R. Gautam, H. Harsh Jainm, M. Poply, R. Jain, M. Anand, R. Kala (2018) Experience based localization in wide open indoor environments. Paladyn, Journal of Behavioral Robotics 9(1): 82–94.
  • U. Kumar, R. Kala, G.C. Nandi (2023) Low-Cost Domain Adaptive Experience Based Localization for Autonomous Robots, In: Proceedings of the 2023 6th International Conference on Advances in Robotics, Article 11, pp. 1-6, Ropar, India.
  • A. Agrawal, D. Agarwal, M. Arora, R. Mahajan, S. Beohar, L. Kenye, R. Kala (2022) SLAM and Map Learning using Hybrid Semantic Graph Optimization. In 2022 30th Mediterranean Conference on Control and Automation (MED), pp. 731-736, Athens, Greece.
  • L. Kenye, R. Palugulla, M. Arora, B. Bhat, R. Kala and A. Nayak (2020) Re-localization for Self-Driving Cars using Semantic Maps. In: Proceedings of the 2020 Fourth IEEE International Conference on Robotic Computing (IRC), Taichung, Taiwan, 2020, pp. 75-78.

Socially-aware Robot Motion Planning (Model-based techniques)

Text

Key Publications

  • R. Kala (2023) Autonomous Mobile Robots: Planning, Navigation and Simulation, Elsevier
  • R. Kala (2021) Video Lecture on Multi-Agent Simulations, Swarm and Evolutionary Robotics (34 Hour Video Lecture Series), Center of Intelligent Robotics, IIIT Allahabad. Available at: http://www.rkala.in/books/#als  
  • V. Malviya, R. Kala (2023) Navigation with a Cooperative Social Robot for a Group of Visitors using Face Detection and a ‘Stop and Wait’Scheme. Journal of Scientific & Industrial Research 82: 1009-1021.
  • V. Malviya, R. Kala (2023) Socialistic 3D tracking of humans from a mobile robot for a ‘human following robot’ behaviour. Robotica 41(5): 1407-1435.
  • V. Malviya, R. Kala (2022) Trajectory Prediction and Tracking using a Multi-Behaviour Social Particle Filter, Applied Intelligence, 52, 7158–7200.
  • A.K. Reddy, V. Malviya, R. Kala, R (2021) Social Cues in the Autonomous Navigation of Indoor Mobile Robots. International Journal of Social Robotics, 13, 1335–1358.
  • A. Malviya, R. Kala (2021) Social robot motion planning using contextual distances observed from 3D human motion tracking, Expert Systems with Applications 184:115515.
  • U. Kumar, A. Banerjee, R. Kala (2020) Collision avoiding decentralized sorting of robotic swarm. Applied Intelligence 50: 1316–1326.
  • V. Malviya, A.K. Reddy, R. Kala (2020) Autonomous Social Robot Navigation using a Behavioral Finite State Social Machine. Robotica 38(12): 2266-2289.
  • V. Malviya, R. Kala (2016) Tracking Vehicle and Faces: Towards Socialistic Assessment of Human Behaviour. In: Proceedings of the Conference on Information and Communication Technology, Jabalpur, India, 2018, pp. 1-6.

Robot Mission Planning

Text

Key Publications

  • R. Kala (2023) Autonomous Mobile Robots: Planning, Navigation and Simulation, Elsevier
  • R. Kala (2023) Mission planning on preference-based expression trees using heuristics-assisted evolutionary computation, Applied Soft Computing 136, 110090.
  • R. Kala (2021) Multi-robot mission planning using evolutionary computation with incremental task addition, Intelligent Service Robotics 14:741–771.
  • R. Kala (2020) Robot Mission Planning using Co-evolutionary Optimization, Robotica 38(3): 512 – 530.
  • R. Kala (2019) Evolutionary Planning for Multi-User Multi-Task Missions, In Proceedings of the 2019 IEEE Congress on Evolutionary Computation (CEC), Wellington, New Zealand, pp. 2689-2696.
  • R. Kala (2019) Evolutionary Planning for Multi-User Multi-Task Missions, In Proceedings of the 2019 IEEE Congress on Evolutionary Computation (CEC), Wellington, New Zealand, pp. 2689-2696.
  • A. Bharadwaj, R. Kala (2019) Sensor based Evolutionary Mission Planning, In Proceedings of the 2019 IEEE Congress on Evolutionary Computation (CEC), Wellington, New Zealand, pp. 2697-2704.
  • R. Kala (2018) Dynamic Programming Accelerated Evolutionary Planning for Constrained Robotic Missions, In Proceedings of the IEEE Conference on Simulation, Modelling and Programming for Autonomous Robots (SIMPAR), Brisbane, Australia, pp 81-86.
  • R. Kala (2018) Increased Visibility Sampling for Probabilistic Roadmaps, In Proceedings of the IEEE Conference on Simulation, Modelling and Programming for Autonomous Robots (SIMPAR), Brisbane, Australia, pp. 87-92.
  • R. Kala, A. Khan, D. Diksha, S. Shelly and S. Sinha (2018) Evolutionary Mission Planning, In Proceedings of the 2018 IEEE Congress on Evolutionary Computation (CEC), Rio de Janeiro, Brazil, pp. 1-8.
  • S. Dumka, S. Maheshwari, R. Kala (2018) Decentralized Multi-Robot Mission Planning using Evolutionary Computation, In Proceedings of the 2018 IEEE Congress on Evolutionary Computation (CEC), Rio de Janeiro, Brazil, pp. 662-669.
  • R. Kala (2016) Sampling based mission planning for multiple robots. In Proceedings of the 2016 IEEE Congress on Evolutionary Computation (CEC), Vancouver, BC, Canada, pp. 662-669.
  • A. Bharadwaj, R. Kala (2019) Sensor based Evolutionary Mission Planning, In Proceedings of the 2019 IEEE Congress on Evolutionary Computation (CEC), Wellington, New Zealand, pp. 2697-2704.
  • R. Kala (2018) Dynamic Programming Accelerated Evolutionary Planning for Constrained Robotic Missions, In Proceedings of the IEEE Conference on Simulation, Modelling and Programming for Autonomous Robots (SIMPAR), Brisbane, Australia, pp 81-86.
  • R. Kala (2018) Increased Visibility Sampling for Probabilistic Roadmaps, In Proceedings of the IEEE Conference on Simulation, Modelling and Programming for Autonomous Robots (SIMPAR), Brisbane, Australia, pp. 87-92.
  • R. Kala, A. Khan, D. Diksha, S. Shelly and S. Sinha (2018) Evolutionary Mission Planning, In Proceedings of the 2018 IEEE Congress on Evolutionary Computation (CEC), Rio de Janeiro, Brazil, pp. 1-8.
  • S. Dumka, S. Maheshwari, R. Kala (2018) Decentralized Multi-Robot Mission Planning using Evolutionary Computation, In Proceedings of the 2018 IEEE Congress on Evolutionary Computation (CEC), Rio de Janeiro, Brazil, pp. 662-669.
  • R. Kala (2016) Sampling based mission planning for multiple robots. In Proceedings of the 2016 IEEE Congress on Evolutionary Computation (CEC), Vancouver, BC, Canada, pp. 662-669.
  • A. Kumar, R. Kala (2016) Linear Temporal Logic-based Mission Planning, International Journal of Interactive Multimedia and Artificial Intelligence, 3(7): 32-41.
  • V. Beri, R. Kala, G.C. Nandi (2019) Time Bound Robot Mission Planning for Priority Machine Using Linear Temporal Logic for Multi Goals. In: Proceedings of the International Conference on Ubiquitous Communications and Network Computing, pp 250-263.

Sampling-based Motion Planning

If there’s too much work to do and too little time, it is always a good idea to do some samples of work here and there. If a house cannot be cleaned in totality, clean a few top spots; in a new city, it is good enough to visit top touristy places; in a class it is good enough to make friends with a variety of people who’ll be with you in different serious and embarrassing situations; searching for a lost million dollar cheque, it is enough to search prominent places where you’d have missed it, etc. These selected few bits of work are called as samples, and if you select the best samples, there’s no need to complete the entire work given. This reduces the work significantly, but puts a more difficult work on identification of best samples to solve the problem. A few hard-working may do it all, a few crazy may leave it all, and then there are the wise who know the right thing for the right job.

So if a path needs to be searched from a source to a goal and there are infinite paths possible, there is no need to search the entire space. Instead, just search for a sampled sub-space, which happens by saying these random points seem awesome for the problem. Try navigating between neighboring samples, and if you can without collision, there’s a small valid path segment as a reward. If path segments are fairly large in numbers, you get a roadmap (specifically Probabilistic Roadmap), which is the secret key to move anywhere in space to anywhere else. Let us focus, literally, between a given source and goal, select samples and search with the same into the mind. Restricting the path segments to be a tree growing from source (or goal or both source and goal), gives a Rapidly-exploring Random Tree that grows like a wild tree in search of the goal in life.

Before delving into research, it is good to know who the superstar of this domain is, or the ideal solution. The superstar depends on what you want. Let us take the simplest problem, to be able to navigate around, meaning it should be possible get a reasonably good solution irrespective of the chosen source and goal. So there should be a roadmap that has roads around all obstacles. This should be a clear bias in the design of the strategies to select the vertices and edges of the roadmap, wherein few samples far away from obstacles and edges that connect otherwise hard to connect samples are extremely precious.

The research in sampling based motion planning is to sit in the control room of crime control and to say these areas look great for work, and these do not. Anything better than random gives you enough bragging rights. Top strategies including focusing near obstacles and especially narrow corridors known for some insane stuff. There’s more than selecting samples, which is to, literally, connect the dots. You could strategize to waste a lifetime connecting two dots that seem related and important, or just be lazy and connect the obvious ones only. There are pros and cons, like the road to success was just round the corner and you were busy looking straight, or there was no shortcut to success and you kept looking for it. Inability to connect two regions can lead to no path being found for the motion planning problem. Spending too little time may not find simple ways, while spending too much time connecting spaces separated by a big obstacle in between is wasteful.

The research here applies some crazy ideas to get a way around. This includes getting samples which are in the center-stage and thus can be easily seen by all samples around and are easy to connect. The higher is the visibility of samples, the easier is to connect them, the lesser are the number of samples required to make the roadmap. Even crazy is to make a roadmap inside the obstacles. No robot travels that obviously. However, it is hard to get a sample inside a narrow corridor. In computing, a gangster in the hiding by travelling through narrow lanes and corridors can be caught by surrounding him/her from all sides of the adjoining obstacles. This gives enough samples inside the corridor to connect all dots.

And the research here also takes you on a tour around the barren narrow lanes with enough corners for an adventure. The focus is to select such interesting areas and to travel them to connect places that are otherwise seen as a disconnected world altogether. This combines with the work put by peers to find and report interesting places with standard toolkit already applied. The adventure begins right there.

If you’re confused of having too many strategies already, there’s a simple way out, which is to use all of them. All think-tank and strategists sit and perform together. At any point of time, the ones who seem to be doing a fair deal of job are promoted and over-utilized, while the ones who are making others time a mess are terminated. There’s a cruel world out here. The sampling and edge connection strategies are made hybrid and adaptive to automatically select the best ones.

Key Publications

  • L. Kenye, R. Kala (2022) Optimistic Motion Planning Using Recursive Sub- Sampling: A New Approach to Sampling-Based Motion Planning, International Journal of Interactive Multimedia and Artificial Intelligence, 7(4): 87-99.
  • R. Kala (2019) On sampling inside obstacles for boosted sampling of narrow corridors, Computational Intelligence 35(2): 430-447.
  • R. Kala (2016) Homotopic Roadmap Generation for Robot Motion Planning, Journal of Intelligent and Robotic Systems, 82(3): 555–575.
  • R. Kala (2016) Homotopy conscious roadmap construction by fast sampling of narrow corridors, Applied Intelligence, 45(4): 1089-1102.
  • A. Kannan, P. Gupta, R. Tiwari, S. Prasad, A. Khatri and R. Kala (2016) Robot Motion Planning using Adaptive Hybrid Sampling in Probabilistic Roadmaps. Electronics 5(2), 16.
  • R. Kala (2018) Increased Visibility Sampling for Probabilistic Roadmaps, In Proceedings of the IEEE Conference on Simulation, Modelling and Programming for Autonomous Robots, Brisbane, Australia, pp. 87-92.

Intelligent Transportation Systems

One of the best ways to pursue a hobby at modern times is to do so at the traffic jams, when the world stops for no understandable reasons; and for the ones without a hobby, there is always a possibility to think about the purpose of everything in life, including traffic jams. It is imperative to think why traffic congestions happen, especially when there is no sight of a traffic light nearby stopping the traffic. To make it simple, let us say that you can happily attend 5 guests per day (capacity flow) and if more guests come, your efficiency reduces, upto 0 when your house is stormed with guests and you have no space to mingle with them. Because you’re a lovable person, people keep storming in and you don’t chuck them out, leaving out house as choked, when nobody naturally volunteers to come in. It is better to be inefficient serving just 3 guests a day, and getting a lower number of people in. Similarly with traffic, if more vehicles enter the system than ideal, a part of the transportation network dies.

If the number of vehicles entering the roads is more than those serviceable, a congestion will happen. And there is nobody who can stop you from entering the roads. So a congestion will happen, unless someone builds new roads. There is a way out. Take long secret routes that people seldom take and you’ll never get into a congestion. And those routes can be calculated algorithmically and traffic metrics adjusted to make those roads look unattractive for the future traffic. The research makes strategies to distribute traffic by changing the routing algorithms, thus anticipating congestion and avoiding it.

This puts a very fundamental question, by what time should you leave to the airport to catch the flight of your next dream holiday? To be very safe, it is good to leave early morning for the late night flight, to be sure that no matter how bad God is upon you, there is plenty of time to spare. For the adventurous, it is always a sight to show some athletics and jump last minute into the airport. The research lets you choose your type/need (the risk level) – going to a boring family function with an incentive of getting late, going to the concert of your favorite star with a need to get the best seats, going for shopping where you’re always welcome, or starting business at the time told by the family priest which better not be missed. The research suggests a good starting time based on the anticipated traffic and risk level. Funny enough, to be absolutely sure for the once-a-lifetime moment, it is always suggestive to reach at least a few hours earlier.

No matter how safe you play, the traffic may mess up. You missed that you’d be going through an area with festive traffic, or the football match gets over at the same time, or that the local school had a function at the same time – they will never let you reach on time even if it is your wedding day. If there was a human control, it would be possible to slip in a heavy bribe in return of favors. Luckily, technology has a way out, to let the traffic lights en-route turn magically green and let the vehicles around move away, if possible, in return of favors. The cooperative traffic systems allow the traffic entities to cooperate, when you badly need it.

It is always good to end with a fantasy fairy tale, and therefore, imagine a transportation network with self-driving cars that can gossip between themselves, with traffic lights, with lane managers and also with the transportation authorities. There’s a lot that can come out from these chit-chats, like dynamically changing the traffic rules so that everyone is happy, letting rich vehicles take a priority and go through special roads and lanes, letting vehicles elect a traffic light change by a democracy (which is also otherwise efficient), let vehicles cordially distribute lanes and speed limits rather than a boss telling them, etc. This also presents a future where vehicles will amicably and socially solve all real-life traffic problems, just like some civilized human societies do so in some parts of the world.

Key Publications

  • R. Kala (2016) On-Road Intelligent Vehicles: Motion Planning for Intelligent Transportation Systems, Elsevier, Waltham, MA.
  • R. Kala (2013) Motion Planning for Multiple Autonomous Vehicles (14 videos/13 hours Video Lecture Series), School of Cybernetics, School of Systems Engineering, University of Reading, UK. Available here
  • H. Bhati, G. Suri, R. Kala, G. C. Nandi (2022) Simulation Aided Anticipatory Congestion Avoidance for Warehouses. In: 2022 IEEE 18th International Conference on Automation Science and Engineering (CASE), 2022, pp. 2062-2067, Mexico City, Mexico.
  • R. Kala (2016) Reaching destination on time with cooperative intelligent transportation systems, Advanced Transportation 50(2): 214–227.
  • R. Kala, K. Warwick (2015) Congestion Avoidance in City Traffic. Journal of Advanced Transportation, 49(4): 581–595.
  • R. Kala, K. Warwick (2015) Intelligent Transportation System with Diverse Semi-Autonomous Vehicles, International Journal of Computational Intelligent Systems, 8(5): 886-899.
  • R. Kala, K. Warwick (2014) Computing Journey Start Times with Recurrent Traffic Conditions. IET Intelligent Transport Systems, 8(8): 681 – 687.

Motion Planning for Multiple Autonomous Vehicles

There is an Indian driving where you can drive anywhere, at any speed, and make any turn anytime, as long as you do not dash into someone ‘stronger’ than you; where the speeds vary from manually ridden rickshaws to Ferraris and the sizes vary from bicycles to overloaded trucks, all on the same road; where the motorbikes overtake cars and the cars overtake bicycles like a criss-cross between hurdles race played simultaneously with multiple age groups; where it is more important to know when not to follow the traffic rules, than to know when to actually follow the traffic rules; where the driving is not limited to steering and speed control alone, but extends to horns and shouts; where you should not be so fast so as to assume a well-built road ahead, and not so slow so as to be called a dumb; and where glamour awareness around is more important than the traffic awareness.

And there is a British traffic where you have no other option than to follow the vehicle in front (if any); drive within the predefined lanes and within the predefined speed limits; change lane if possible; see and follow all the signs and traffic signals, be it marked on the road, marked on a signboard aside the road, marked on a signboard vertically above, or a small signboard of blockage on the road; look for all the vehicles and pedestrians at every side of the road and know the priorities associated; if you happen to make mistakes, pray for the absence of video cameras nearby; horn is an extreme indication of the fault of the person in front.

Similar to the fact that Indians believe in fitting more people in the cars and buses than allowed, more food in their stomach than possible, and more luggage in their bags than possible; the Indian traffic fits in more vehicles on the roads than the maximum possible bandwidth with a lane oriented traffic (largely possible due to the varying sizes of the vehicles). Be it the natural differences in speeds; or the factors of social prestige, stud-ness, or mere impatience; some vehicles have to overtake the others, even if remotely possible. And when you are aware that the minor accidents are well fought and immediately forgotten, the risk is worth taking. (No driving license, no points lost!). This is what makes the Indian traffic more efficient than any organized traffic with vehicles as diverse in speeds and sizes, as in the Indian traffic.

Hence, while in India expect a complete chaos, and while in Britain expect similar types of vehicles neatly following each other, where the chaos is largely triggered by diversity of vehicles hence necessitating an unorganized traffic. So all you need to cause a chaos in British traffic is to make it diverse. While riding bullock carts or flooding in motorbikes may not be a good idea – even though very slow, autonomous vehicles may be conspiring towards this direction.

In most simple card games, it is easy to teach children the rules of the game, enable them understand the game logic and the game dynamics, which makes them capable of making near-optimal moves to every situation so that in most cases the luckiest player wins. However, it is hard to teach them the cheating principles which are widespread, require skill and experience, difficult to implement, and are largely opponent-based. The winning edge mostly lies in these cheating skills more than anything else. Similarly, it is easy to learn driving as a simple vehicle following, lane change and situational assessment mechanism. In a card game, playing with skilful cheaters, you can be badly defeated and forced to quit if you simply follow the rules, you can be defeated if you are not a good cheater, you can win if you are too good in cheating, and you can be caught if you are not careful in cheating. The same rules apply for driving in unorganized traffic. While you may learn conventional driving, if you only follow those principles, you do not survive; if you are clever enough, you just survive; if you are know the tricks well, you succeed in getting the best bargain out of the other vehicles usually implying many overtakes at great speeds; and if you try too much, you end up in an accident!

While the research community is busy teaching the autonomous vehicles the general traffic rules and driving primitives, which are mainly intended for an organized traffic; my work deals with teaching the vehicles the tricks and cheats of unorganized traffic. The long term aim is to have autonomous vehicles in an unorganized traffic, or to fill the road with application specific diverse autonomous vehicles which necessitate an unorganized way of operation. Teaching autonomous vehicles to drive is similar to teaching a newbie how to drive, while it is accepted that teaching is in general a frustrating task where the teacher is always under the impression that the student is dumb and lazy, and the student has exactly the same views regarding the teacher. The good thing about teaching autonomous vehicles is that the latter is untrue; although the bad thing is that you can never challenge their level of dumbness. Humans have inbuilt intelligence, and thanks to a set of intelligent algorithms which are well established, inducing similar intelligence in machines is not so hard.

When it comes to the strategy of driving – there are goal shooters, chess masters, and boxers. Football is played more intensely off the field than on the field, with the goal shooters (or sampling based planners) usual targets of infinite love and criticism. What do they actually consider in seconds of ball control? Certainly, mostly the most straightforward choices, although some thought process may be devoted to select the side and approximate position of shoot by considering random choices. In driving, after basic steering and speed control (or the control problem), this corresponds to driving as straight as possible, overcoming slowest of vehicles as they come around, and avoiding anyone passing through (the planning problem). In all the cases, the rather straightforward and quick looking way may be decided; for which the humans use their ability to identify and analyse obstacles around, deliberate their actions in the future, and quickly mine out safe distances to be maintained and hence the steering required; while machines can use algorithms like Genetic Algorithms, Rapidly-exploring Random Trees, etc. While driving it is very important to decide whether to overtake a vehicle ahead, or instead follow it (the coordination problem). This affects the driving speed and avoidance strategy. Humans learn to identify feasibility of an overtaking manuever, and especially in the initial phases usually get wrong which is the cause of collisions and quarrels; while machines can deliberate into the future using competing plans and sensed speeds. Communication, if available, enables to know the participating vehicle’s intentions for better feasibility assessment. This option is only possible with an autonomous-vehicle only scenario, a valid possibility much into the future.

Kids know a simple rule – if you are smart, prove your smartness in the smartest game of all times. The chess masters (or graph based planners) are ultimate genius who think over all the combination of moves right into the future, know which moves are clearly good and bad for consideration, and formulate the best strategy. In a road, this corresponds to exploiting the road architecture to make the overall planning time effective, while strategically deciding all the combinations of overtakes, vehicle following behaviours, vehicle avoidance strategies, etc. Again, communication enables to make sure that two vehicles follow exactly the same overall strategy. Never even think to mess around with the boxers (or reactive planners) who have unbelievable reflexes, and can rip you apart in seconds, or defend themselves most strongly in the blink of an eye. In a road, this corresponds to assessing the immediate scenario to take the basic decision of where to turn, by what magnitude, and at what speed. One may use algorithms like Fuzzy Logic, Potential Fields and Elastic Strip; or may frame rules similar to what you would give to a kid explaining him/her how to act in every different situation. Small deliberative means may be helpful in better decision making regarding overtake feasibility, side of overtake and obstacle avoidance, etc. The tradeoff is always between deliberation, offering near-optimal and near-complete solutions at the expense of computational time (which significantly increases with an increase in the number of vehicles); and reactiveness offering faintly optimal and faintly complete solutions for odd-looking scenarios, while being very computationally efficient for any number of vehicles.

Key Publications

  • R. Kala (2016) On-Road Intelligent Vehicles: Motion Planning for Intelligent Transportation Systems, Elsevier, Waltham, MA.
  • R. Kala (2013) Motion Planning for Multiple Autonomous Vehicles (14 videos/13 hours Video Lecture Series), School of Cybernetics, School of Systems Engineering, University of Reading, UK. Available at: http://rkala.in/autonomousvehiclesvideos.php
  • R. Kala, K. Warwick (2014) Dynamic Distributed Lanes: Motion Planning for Multiple Autonomous Vehicles. Applied Intelligence, 41(1): 260-281.
  • R. Kala, K. Warwick (2014) Heuristic based evolution for the coordination of autonomous vehicles in the absence of speed lanes. Applied Soft Computing, 19: 387–402.
  • R. Kala, K. Warwick (2013) Planning Autonomous Vehicles in the Absence of Speed Lanes using an Elastic Strip. IEEE Transactions on Intelligent Transportation Systems, 14(4): 1743-1752.
  • R. Kala, K. Warwick (2013) Multi-Level Planning for Semi-Autonomous Vehicles in Traffic Scenarios based on Separation Maximization. Journal of Intelligent and Robotic Systems, 72(3-4): 559-590.
  • R. Kala, K. Warwick (2013) Motion Planning of Autonomous Vehicles in a Non-Autonomous Vehicle Environment without Speed Lanes. Engineering Applications of Artificial Intelligence, 26(5-6): 1588–1601.
  • R. Kala, K. Warwick (2015) Reactive Planning of Autonomous Vehicles for Traffic Scenarios, Electronics, 4(4), 739-762.
  • R. Kala, K. Warwick (2015) Motion Planning of Autonomous Vehicles on a Dual Carriageway without Speed Lanes. Electronics, 4(1): 59-81.
  • C. J. Shackleton, R. Kala, K. Warwick (2013) Sensor-Based Trajectory Generation for Advanced Driver Assistance System. Robotics, 2(1): 19-35.
  • R. Kala, K. Warwick (2011) Multi-Vehicle Planning using RRT-Connect. Paladyn Journal of Behavioural Robotics, 2(3): 134-144.
  • R. Kala, K. Warwick (2012) Planning autonomous vehicles in the absence of speed lanes using lateral potentials. In Proceedings of the 2012 IEEE Intelligent Vehicles Symposium, Alcalá de Henares, Spain, pp. 597-602.
  • R. Kala, K. Warwick (2011) Planning of Multiple Autonomous Vehicles using RRT. In Proceedings of the 10th IEEE International Conference on Cybernetic Intelligent Systems, Docklands, London, pp. 20-25.

Multi-Robot Motion Planning

Humans are social beings who live as per social customs and norms which we are taught right from the childhood, so you cannot tell your professor how bad the lecture was; every guest lecture is wonderful whose greatness depends upon the vocabulary of the person delivering the vote or thanks; it is more important to know the views of your senior over a topic than to know what the topic under discussion is; and so on. The robots are accepted as elements that would be social in their own fancy way, or would interact closely with the human society. And certainly, if the robots aspire to conquer the planet and prove their dominance over the human race, they better form their own laws, ethics, values, and rules of the game. On the contrary, if they are meant to aid the humans, there is no point if you agree with your boss, while your robot has some other fancy ideas.

When it comes to navigation, the humans are more intelligent than it looks. We know on bunking classes which areas would be safe and which would get us into serious trouble; seeing someone whom we are avoiding, we instantaneously cite the best lane to hide into; we know if someone looks suspicious, what radius of distance to maintain; we know the more senior a person is, the more centrally he/she should be located; we know elders and handicap have priorities; and we know on a long way, who is to be followed for how long. The robots are more task-oriented and less fun, disregard many social norms, and think they know you well. It is a serious challenge to drive behind a car you know is being driven by a woman. You have no idea what the car might do, suddenly there might be a turn the least expected, speeding up and slowing down may have no norms, so in all you need to is be prepared for everything including the worst.

For all other cases and all other scenarios, assuming people to do what they should or seem to be doing is a rather happy go lucky strategy, but works out in most cases. There are certainly occasional cases where funny things happen. You take left to surpass a person walking towards you, so does he/she, noting conflicting plans both simultaneously rectify the same, both again see the correction made by the other person and simultaneously revert back, both realize there is something terribly wrong and stop to let the other person sort out, both smile and carefully take a step while being very vigilant how the other person is moving. If it still goes on, you are probably watching a Bollywood film; in real life such ‘made for each other’ scenarios are practically impossible and humans use a lot of facial gestures to indicate the intents. In any case all this is a source of great amusement for everyone around. And then there are times where you expect a person to walk straight and wait for him/her to go through so that you can cross the road; who for no reason slows suggesting you to change the plan and instead walk fast and past; but as soon as you take big steps, out of nowhere the other person gets a surge of energy and starts walking fast; once committed, it would be foolish to change the plan now and you take bigger steps while the other person seems to be acting blind; and of course you need to slow to avoid a collision, with the other person having dragged you all the way. Everyone knows the magnitude of acting skills required when you realize that you have missed a turn on the road and need to turn and walk back, to avoid any embarrassment. A typical robot moving with a fuzzy based lower end planner would display all these and much more interesting things.

In conception, all events are professionally planned well in advance, so that everything goes on smoothly. This may not only include what to do in case of a possible fire and earthquake, but also who would take which seat, in what order they arrive, in what order they clap and laugh, and what actions are taken if someone does not follow the protocol. So is the case with robots, who may talk to each other well in advance to fix the protocol. Of course, we are dealing with an only robot event. Humans know well that there is macro management, in which people believe themselves to be Gods and draw out what they call a masterpiece, expecting all the lower level people are true disciples with infinite skills; and micromanagement where the people are convinced that some fool gave a vague plan to adhere to, but know the authority should never be questioned, and people are made to follow them by force or by choice, any discrepancy or false ground level truth being dealt with in the quickest and the dirtiest of ways. Similarly the robots may assume the best cases to draw out something awesome for them; and on later realizing conflicting plans, the quickest and dirtiest of negotiations may take place to come to any consensus soon. If you are senior, simply force the slave junior to act as per your wills (priority based planners); in case of equality there is an obvious fight with both parties stepping down sparingly with time.

Planning a good trip with your friends is always a lovely experience. From destination(s), dates and duration; to the dos, don’ts and rules of the trip are heavily debated and well-fought. The challenge is certainly not the execution part once the key decisions have been made and frozen, the challenge lies in balancing contradictory and weird preferences, at all times keeping the group as a whole. The greater part of the challenge comes from the participants whose presence is solely for entertainment and disruptive purposes. The good thing is that everyone is at the same place and a good amount of discussion is possible till something mutually agreeable comes out; the bad thing is that ‘no plan’ is not an option after much hype has already been created. Cheating, manipulation of truth and false promises are though accepted. This is another art that the robots are good at, though mostly under the strict control of an arbitrator who defines the rules of negotiation. Knowing the preferences of all the robots, whether the arbitrator does everything (centralized planners) or instead the robots themselves have something to do, is dependent upon the system. In any case it can be ascertained that the planning meeting will end with something feasible and almost best, no matter what all gets exchanged and for whatsoever amount of time.

Some students solve a mathematical problem starting from the question to the answer; some others try to reach the question from the answers; some try both ways; some are experts in scribbling anything in the middle so that the two ends meet; some others can sneak a peek at the next person to get some lines in the middle that may make sense in a fully senseless proof; some people have the skills to talk, discuss and select the best steps out of each other’s work; some others working on completely different problems use the same rules, which may mean addition of more wrong material, or a better and a highly related material; in any case it is only important for all the questions to be solved by anyone, post which cheating skills would enable everyone to benefit from each other’s intelligence giving rise to a truly free and knowledge sharing society based on the human principles. Of course in case of multiple solutions to the same question, a more intelligent person gets priority. The robots resort to similar means with the challenge being a good travel plan for all the robots formed collaboratively.

Key Publications

  • R. Tiwari, A. Shukla, R. Kala (2013) Intelligent Planning for Mobile Robotics:Algorithmic Approaches, IGI Global Publishers,Hershey, PA.
  • R. Kala (2018) Routing-based navigation of dense mobile robots. Intelligent Service Robotics 11(1): 25–39.
  • R. Kala (2018) On repelling robotic trajectories: coordination in navigation of multiple mobile robots. Intelligent Service Robotics 11(1): 79–95.
  • R. Kala (2014) Navigating Multiple Mobile Robots without Direct Communication. International Journal of Intelligent Systems, 29(8): 767–786.
  • R. Kala (2014) Coordination in Navigation of Multiple Mobile Robots. Cybernetics and Systems, 45(1): 1-24.
  • R. Kala (2013) Rapidly-exploring Random Graphs: Motion Planning of Multiple Mobile Robots. Advanced Robotics, 27(14): 1113-1122.
  • R. Kala (2013) Multi-Robot Motion Planning using Hybrid MNHS and Genetic Algorithms. Applied Artificial Intelligence, 27(3): 170-198.
  • R. Kala (2012) Multi-Robot Path Planning using Co-Evolutionary Genetic Programming. Expert Systems With Applications, 39(3): 3817-3831.
  • Apoorva, R. Gautam, R. Kala (2018) Motion Planning for a Chain of Mobile Robots Using A* and Potential Field, Robotics 2018, 7(2), 20.

Path Planning for Mobile Robots

An ideal robot would be your slave, who gets everything you want from different places; nicely follows you whenever you need; takes, disseminates and follows your instructions; fights for you; does not fight with you; stands tall to your fancy desires; spies for you; is unaffected by how many times you ask it to do ridiculous jobs; is uncovered by terms like robot rights, robot ethics and robot law; and costs much less than what a human would take to do most things in the list. The central challenge is enabling the robot to go from one place to the other, without colliding and breaking itself down, or breaking your dearest glassware. In a mishap, the good point is that you can shout as much as you want, without having the robot retaliating back; the bad point is of course it makes no difference to it. It must be noted that teaching robots how to walk is a dangerous art; you never know when they may walk up to you and rise against mankind for the freedom of their species.

Robots act similar to kids when it comes to the art of walking. Depending upon the age, some kids can barely crawl, some wander around aimlessly, some run faster than they can see, some follow a ‘slow and steady wins the race’ strategy, some walk crocked, some take more sober and smooth paths, some can predict how you’d come to catch them and take necessary preventive actions well in advance, some take random directions which later proves to be beneficial and is a showcase of natural or supernatural intelligence, some repel schools, and some attract toys. From intelligence to dumbness, robots do everything 10 times as good and bad. With kids everything is a source of fun; while with robots it depends whether the person behind is an undergraduate student doing a planning project, a research student trying to innovate, an end user having bought a cool robot gadget, a competition between teams, general audience of the robot competitions, or a child playing with robots.

Unlike humans, robots are weird creatures that may have all strange sensors embedded into them or located externally. In a human terminology, this means having eyes struck at a room so that you can spy on what your roommate is doing behind you, having eyes in hands so that you can easily dig it in places to easily find lost items, and having weird sensations depending upon how far you are from the obstacles. Having an option to temporarily re-arrange your organs opens a pool of fantasies, which if available would definitely be creatively designed, for the robots this is an option. Given all the weird senses, it would be expected that the robots being potentially a more advanced species should be able to move, talk, dictate and conquer like the ones projected in the science fiction movies. It seems the Terminators of tomorrow are yet in their infant stages, with leading researchers teaching them the art of the game.

Remember the last time when you were so lost listening to your favourite song in your MP3 player, that you didn’t realize you’re walking at a dead end road; or when you were so excited seeing an old friend that you leaped towards him/her without realizing wet floor ahead. A greater challenge after encountering these situations is to think over a reaction in a super-fast mode to make it look normal and avoid any embarrassment. We all know that humans are capable of thinking all possible outcomes well in advance, and any such incident which you did not pre-compute is a waste of skill. There is a similar expectation from the robots, and luckily the graph search algorithms can enable the robot pre-compute all the possibilities to mine out the best way out; although you require loads of computation and planning time. Much like humans, a robot which thinks a lot before acting may sometimes be called better than one which acts itself into an embarrassing situation which sticks a lifetime.

Be in falling in love, selecting the destination for your next visit, or deciding what to eat in a restaurant; theoretically we consider all the options and decide the best one; while practically we know there is always ‘the one’ which always stands apart, and irrespective of the number of options, is magically easy to cite. After choosing ‘the one’ the task is just to collect enough reasoning to satisfy your choice, take advise only from the friends who support ‘the one’, avoid the friends who have an alternative view; and all this goes well until you accidently get a friend who, in your language, gives you enough reasons to prove that ‘the one’ is actually someone else; in which case the process repeats with the new choice. Navigation can be studied and simplified in a similar way. Seeing random choices, you fall in love with one, and keep perfecting it, until some accident happens and a better option suddenly drops in front of you. The evolutionary planners, working in a similar manner, enable a robot to construct its trajectory. There is always a chance you do not get to ‘the one’, unless you do not mind spending your life searching in eternity; the robots (and their masters) do mind that.

When anyone hits you, do not waste time thinking, simply hit back; when someone says free cake, no need to think over it, run to get a handful; when something comes flying in, catch; when something pops up in front of you, stop and turn. So many things we do are a voluntary or involuntary reaction constituting a person’s behaviour. Similarly, robot or human walking can be seen as a behavioural reaction to whatever we see instantaneously. Such planners are fast, really fast. Just like an immediate reaction to fighting with the wrong person has consequences, serious consequences; such a walking technique can lead to seriously dumb results. But who cares if it is a robot. Successful robot navigation gets projects and publications, a poor one gets some amusement. And because robots make so many mistakes, you get lots of material to tease them lifelong, if only they reacted to those.

There is an easy way to solve every problem – tell funders you will hire the best experts; hire the best experts of different domains; let the different experts be assured that the other one is actually working; wait till the very end; organize a debate to let the experts fight over who’s right, who’s wrong, and who does what, and how; let a random design come out of the debate; let the experts write down what the design does in big and hefty words; and this satisfies everyone. Similarly, every algorithm can be mixed with any other; you can simply take different algorithms and ‘mix and match’ as you like; as long as you are smart enough to know in what points the resultant algorithm exceeds the base methods. Research community being too big to have already tried all combinations is not a problem, if you cannot get original ingredients, or an original recipe; try unique quantities, unique pre-preparation and post-preparation techniques, and if nothing, then a unique presentation. So, in principle, there is always an algorithm, a hybrid of base algorithms, which (in a limited sense) is always better than the base methods. So you could create a Terminator which broadly considers all possibilities, but makes rapid movements and local plans; or a flirty robot which indicates commitment to someone, at the same time considering the other options; or a salesman robot which can use some magic to select the best looking options, which form the basis of still better options, till the master customer is satisfied; or a manager robot which makes broad plans and spends the entire time forcing people to refine them, rectify them, or suggest new plans.

Key Publications

  • R. Kala (2023) Autonomous Mobile Robots: Planning, Navigation and Simulation, Elsevier
  • R. Tiwari, A. Shukla, R. Kala (2013) Intelligent Planning for Mobile Robotics:Algorithmic Approaches, IGI Global Publishers,Hershey, PA.
  • SMH Jafri, R. Kala (2019) Motion Planning for an Outdoor Mobile Robot on a Probabilistic Costmap, International Journal of Robotics and Automation 34(6): paper 4.
  • S.S. Paliwal, R. Kala (2018) Maximum clearance rapid motion planning algorithm. Robotica 36(6): 882-903
  • R. Kala, A. Shukla, R. Tiwari (2011) Robotic path planning in static environment using hierarchical multi-neuron heuristic search and probability based fitness. Neurocomputing, 74(14-15): 2314-2335.
  • R. Kala, A. Shukla, R. Tiwari (2011) Robotic Path Planning using Evolutionary Momentum based Exploration. Journal of Experimental and Theoretical Artificial Intelligence, 23(4): 469-495.
  • R. Kala, A. Shukla, R. Tiwari (2010) Dynamic Environment Robot Path Planning using Hierarchical Evolutionary Algorithms. Cybernetics and Systems, 41(6): 435-454.
  • R. Kala, A. Shukla, R. Tiwari (2010) Fusion of probabilistic A* algorithm and fuzzy inference system for robotic path planning. Artificial Intelligence Review, 33(4): 275-306.
  • C. S. Pati, R. Kala (2017) Vision-Based Robot Following Using PID Control. Technologies 5(2), 34.
  • R. Kala, A. Shukla, R. Tiwari (2012) Robot Path Planning using Dynamic Programming with Accelerating Nodes. Paladyn Journal of Behavioural Robotics, 3(1): 23-34.
  • R. Kala, A. Shukla, R. Tiwari (2012) Robotic Path Planning using Hybrid Genetic Algorithm Particle Swarm Optimization. International Journal of Information and Communication Technology, 4(2-4): 89 – 105.
  • R. Kala, A. Shukla, R. Tiwari (2010) Evolving Robotic Path with Genetically Optimized Fuzzy Planner. International Journal of Computational Vision and Robotics, 1(4): 415-429.
  • A. Shukla, R. Tiwari, R. Kala (2009) Mobile Robot Navigation Control in Moving Obstacle Environment using Genetic Algorithms and Artificial Neural Networks. International Journal of Artificial Intelligence and Computational Research, 1(1): 1-12.
  • S. M. H. Jafri, Rahul Kala (2015) Path Planning of a Mobile Robot in Outdoor Terrain, In Intelligent Systems Technologies and Applications Vol. 2, Springer, pp. 187-195.
  • R. Kala, A. Shukla, R. Tiwari (2009) Robotic Path Planning using Multi Neuron Heuristic Search. In Proceedings of the ACM 2nd International Conference on Interaction Sciences: Information Technology, Culture and Human, Seoul, Korea, pp. 1318-1323.
  • R. Kala, A. Shukla, R. Tiwari, S. Rungta, R. R. Janghel (2009) Mobile Robot Navigation Control in Moving Obstacle Environment using Genetic Algorithm, Artificial Neural Networks and A* Algorithm. In Proceedings of the IEEE World Congress on Computer Science and Information Engineering, Los Angeles/Anaheim, USA, pp. 705-713. 
  • A. Shukla, R. Tiwari, R. Kala (2008) Mobile Robot Navigation Control in Moving Obstacle Environment using A* Algorithm. In Proceedings of the International conference on Artificial Neural Networks in Engineering, ASME Publications, St. Louis, Missouri, pp. 113-120.

Soft Computing

Soft is the candy that the candyman sells, soft are the rasgullas drenched in sauce, soft is the heart which you always wished your teacher had, soft is the feel of your crush, many things in the world are soft, some of them intentionally omitted here. However, here the focus would be on the most unexpected application of softness; that is softness in computing. Neither does it mean manufacturing soft processors which can be taken out and played with, nor does it mean publishing soft books which ease your fingers all day and night; although soft computing experts would have enjoyed those definitions better. It does mean having a soft-hearted teacher, who would accept any answer to any question – vague or concrete, correct or nearly correct, solved using correct or nearly correct procedure, solved using a procedure which does or does not make any sense, question itself being well-defined or poorly defined. So imagine working in an exciting domain where you could be asked for anything, you can reply anything, understand anything, anything may make sense or be completely non-sense – that is soft computing. The small but unfortunate catch here is that the sense or no-sense liberty is usually given only to the machines. So as a human you are expected to make sense while engineering machines, which while operating may mess it up, hopefully after the project has somehow been delivered. An irony is that even though soft computing refers to a soft hearted teacher, as a disciple it may be taught by some of the most hard task masters.

So the machines can be asked anything senseful or senseless, while they would do their best to make sense. Try asking how likely is it that your crush comes to you (be prepared to give details about both, as many as available), or how likely are you to pass that awful subject, or whether you have any of the deadliest of the diseases, or who the person in that strange video is, or what all props are there in the entire video, or what the people are doing, or how to continuously control your AC or washing machine, or how to drive from one place to the other, or how to make a masterpiece, or how to best save your money, etc. And certainly the obvious inputs and the logic behind the question may be known precisely, vaguely, or not at all known; depending upon which the system may give a great or a rather ridiculous answer. You may have written funny answers in examinations in reply to questions you didn’t know, but were creative enough to draw your own interpretations; these systems can be funny too.

If he can play basketball, even I can, I am clearly faster than him; if she can’t clear the interview, I certainly can’t, I don’t even have that X-factor; people from my region generally score high in exams, my chances are bright; if the shop is in this area, it has to be awesome. So many times we may have not tried anything, nor we may have any idea how it may be, or any knowledge how things work or don’t work; we may still predict the outcomes simply by looking at the people who have tried it. If you are a keen observer, you may in fact be right; else everyone knows how to defend ones wrong decision by playing a blame game, stating it as an exceptional, stating the facts that were presented were wrong, or you were misunderstood and you actually stated the right prediction. Similarly with the machines which would typically be neural networks; simply give them all the examples that you have and see the response. If the data you give is good with facts well-identified and relevant, the machine might do an awesome job, else it’s just a dumb machine. The good thing is of course that you can make the machine solve for anything silly or wise, the bad thing is that you will have to record examples which depending upon the problem can be simple, impossible, or mischievous. The good thing is that the machine can give a good shot even when given a few examples, the bad thing is unless the examples have something relevant in them, the machine makes rather silly decisions which if taken seriously can have funny consequences.

When winters come, I get cold; I perform well in all subjects taught by this teacher; if I exercise, I don’t fall ill; every time I write with this lucky pen, my exams go well; if she accepts my friend request, she likes me; if my best friend wishes me good luck, I perform well in the game. There are too many rules in life. Logical or baseless, routine or superstition, suggestive or mandatory, they all help us in some way or the other; after all there is no proof that superstitions do not work. People invent rules, pass them down to others, take them from others, retain some and throw off some. The problem is naturally having too many rules. For any situation multiple rules may be applicable, which may support each other or contradict each other; each rule may be applicable, somewhat applicable or not applicable (say winters came with barely any drop in the temperature); the rules may have different importance depending upon the situation or the inventor. A fuzzy inference system caters to all these issues and assesses a situation to give some output. The rules need to be fed into the system. These may be based on the human designer’s knowledge or learnt by the system itself. The resultant rules may be meaningful or baseless; depending upon whether the human designer or the learning system was wise or felt prey to superstitions on seeing some consistently strange examples.

There are always too many choices in life, which further give rise to more and more choices. It is not uncommon spending in hours thinking about the choices in life, until you get bored, somebody interrupts or a pending download completes. What is the perfect weekend, what to eat, how to spend your salary, how to walk around to visit the campus, in which order to invite your friends for a party, in which order to collect them for the party, how to make an awesome dish – these are all very serious problems in life. Take the example of planning an awesome trip with friends. The common goal is to make every penny worth it. So not only is each and every decision important, the overall travel plan is of value. Putting in some crazy ideas might just extend the trip costing more than someone’s budget, and if you leave out some overly-hyped adventure, maybe you could fit in many great things to do at reasonable prices. World is a big place, there is too much to do, there are lame to crazy fantasies to be completed, for every desire there are too many choices to pick from, and obviously the time and budget are limited. Do not be fooled by the travel operators who make a plan for you based on what they think you might want, simply let an intelligent system running an algorithm like evolutionary algorithm make all your decisions. Of course you need to feed in the pool of options, constraints and preferences which play a big role in designing the perfect trip. A plan all your friends combined may take years to formulate, what a non-intelligent computer program might take months to formulate, these systems may have the perfect trip for you in seconds.

Solving a problem in a family is an interesting task. You take someone’s suggestion, who broadcasts it to everyone else in the family, some of whom further make a series of phone calls and there are multiple families solving the problem, and so on. So even if the question was how difficult is a particular exam, there is an entire extended friend-family network onto the job. There are extensive discussions made, phone calls exchanged, questions asked and answered, senseful and senseless comments made, etc. Towards the end a decision may be made. If the people in the network with positive (even if marginal) contribution are high, a good decision may be expected. Similarly an ensemble of intelligent systems may be better than the single counterpart. Problem solving in a college environment is even more interesting. If you have a crush on a Bihari, ask that person; if on a Punjabi, ask him; if on an ultra modern one, ask that guy; and for general suggestions there are always a pool of people. So it is first about selecting the expert, and then taking expert guidance. Alternatively, many other times, one person is responsible for family background checking of your prospective crush, some other is responsible for finding out likes and dislikes, someone else checks out for general behaviour in the home place, and someone else matches the zodiac – they all collectively decide what is the scope and extent of a relationship. And a more common case is a senior passing his work to a junior who splits it into segments and makes his juniors do the work, who may in turn transfer to some other people. As long as everyone does almost the complete work, the problem gets solved, with someone responsible for connecting the solutions. Even intelligent systems divide the work into a modular architecture for an enhanced performance.

Remember there is an intelligent system which deals with choices (evolutionary algorithms). So having too many possible neural networks to solve a problem, too many fuzzy systems to solve a problem, too many modular architectures possible, and too many ensembles possible is not a problem – let an evolutionary algorithm deal with it to make evolutionary neural networks and evolutionary fuzzy systems. So if you are not sure that your intelligent system learnt well, you are not confident about the rules someone plugged in, you doubt if you designed the best possible architecture of your system, you believe your system may have been lazy, or you believe your system may have had bad influence, or you believe you do not have the energy to design a system of choice; in all these cases you can simply recruit an evolutionary algorithm who would be happy to solve the problem for you, in consultation with the base systems. Both working hand-in-hand may best serve you, with some strings attached of course. Or you can say that the fuzzy systems represent the problem well and the neural networks learn well without prior knowledge, so a cool trick would be to make a neural network learn a fuzzy system resulting in an adaptive neuro fuzzy inference system. You could further recruit an evolutionary algorithm to design the complete neuro fuzzy system.

Key Publications

  • A. Shukla, R. Tiwari, R. Kala (2010) Real Life Applications of Soft Computing, CRC Press, Boca Raton, FL.
  • A. Shukla, R. Tiwari, R. Kala (2010) Towards Hybrid and Adaptive Computing: A Perspective, Studies in Computational Intelligence, Springer-Verlag Berlin, Heidelberg.
  • R. Kala (2010) Video Lecture of Soft Computing (39 Hour Video Lecture Series), Soft Computing and Expert System Laboratory, IIITM Gwalior, India. Available here: 
  • R. Kala, A. Shukla, R. Tiwari (2009) Self-Adaptive Parallel Processing Neural Networks with irregular Nodal Processing Powers using Hierarchical Partitioning. Neural Network World, 19(6): 657-680.
  • S. Kant, R. Kala, R. Tiwari, A. Shukla, S. Kumar (2016) Lip Recognition Using Various Neural Classifiers. International Journal of Electrical, Electronics and Data Communication, 4 (10): 86-94.
  • A. Gupta,  S. Bhalla,  S. Dwivedi,  N. Verma, R. Kala (2015) On the Use of Local Search in the Evolution of Neural Networks for the Diagnosis of Breast Cancer, Technologies, 3(3): 162-181.
  • R. R. Janghel, R. Tiwari, R. Kala, A. Shukla (2012) Breast Cancer Data Prediction by Dimensionality Reduction Using PCA and Adaptive Neuro Evolution. International Journal of Information Systems and Social Change, 3(1): 1-9. 
  • R. Kala, A. Shukla, R. Tiwari (2011) Modular Symbiotic Adaptive Neural Evolution for High Dimensional Classificatory Problems. Intelligent Decision Technologies, 5(4): 309-319.
  • R. Kala, A. Shukla, R. Tiwari (2011) A Novel Approach to Classificatory problem using Neuro-Fuzzy Architecture. International Journal of Systems, Control and Communications, 3(3): 259-269.
  • R. Kala, R. Tiwari, A. Shukla (2011) Breast Cancer Diagnosis using Optimized Attribute Division in Modular Neural Networks. Journal of Information Technology Research, 4(1): 34-47.
  • R. Kala, R. R. Janghel, R. Tiwari, A. Shukla (2011) Diagnosis of Breast Cancer by Modular Evolutionary Neural Networks. International Journal of Biomedical Engineering and Technology, 7(2): 194 – 211.
  • A. Tripathi, P. Gupta, A. Trivedi, R. Kala (2011) Wireless Sensor Node Placement using Hybrid Genetic Programming and Genetic Algorithms. International Journal of Intelligent Information Technologies,7(2): 63-83.
  • R. Kala, A. Shukla, R. Tiwari (2010) Clustering Based Hierarchical Genetic Algorithm for Complex Fitness Landscapes. International Journal of Intelligent Systems Technologies and Applications, 9(2): 185-205.
  • R. Kala, A. Shukla, R. Tiwari (2010) Hierarchical Evolutionary Strategy for Complex Fitness Landscapes. Journal of Information Science and Technology,7(2): 36-57.
  • R. Kala, H. Vazirani, N. Khawalkar, M. Bhattacharya (2010) Evolutionary Radial Basis Function Network for Classificatory Problems. International Journal of Computer Science Applications,7(4): 34-49.
  • R. Kala, H. Vazirani, A. Shukla, R. Tiwari (2010) Medical Diagnosis using Incremental Evolution of Neural Network. Journal of Hybrid Computing Research,3(1): 9-17.
  • R. Kala, H. Vazirani, A. Shukla, R. Tiwari (2010) Evolution of Modular Neural Network in Medical Diagnosis. International Journal of Applied Artificial Intelligence in Engineering System, 2(1): 49 -58.
  • R. Kala, H. Vazirani, A. Shukla, R. Tiwari (2010) Offline Handwriting Recognition using Genetic Algorithm. International Journal of Computer Science Issues, 7(2): 16-25.
  • R. Kala, A. Shukla, R. Tiwari (2010) A Novel Approach to Classificatory Problem using Grammatical Evolution based Hybrid Algorithm. International Journal of Computer Applications, 1(28): 61-68.
  • A. Tarsauliya, S. Kant, R. Kala, R. Tiwari, A. Shukla (2010) Analysis of Artificial Neural Network for Financial Time Series Forecasting. International Journal of Computer Applications, 9(5): 16–22.
  • R. Kala, A. Shukla, R. Tiwari (2010) A Novel Approach to Clustering using Genetic Algorithm. International Journal of Engineering Research and Industrial Applications, 3(1): 81-88.
  • H. Vazirani, R. Kala, A. Shukla, R. Tiwari (2010) Use of Modular Neural Network for Heart Disease. International Journal of Computer and Communication Technology, 1(2-4): 88-93.
  • A. Shukla, R. Kala (2008) Multi Neuron Heuristic Search. International Journal of Computer Science and Network Security, 8(6): 344-350.
  • A. Shukla, R. Kala (2008) Predictive Sort. International Journal of Computer Science and Network Security, 8(6): 314-320.
  • A. Sharma, I. Wadhwa and R. Kala (2015) Monocular camera based object recognition and 3D-localization for robotic grasping. In Proceedings of the 2015 International Conference on Signal Processing, Computing and Control, Waknaghat, pp. 225-229.
  • P. Mohan, S. Srivastava, G. Tiwari, R. Kala (2015) Background and skin colour independent hand region extraction and static gesture recognition. In Proceedings of the 2015 Eighth International Conference on Contemporary Computing, Noida, India, pp.144-149.
  • A. Kumar, R. Kala (2015) Geometric shape drawing using a 3 link planar manipulator. In Proceedings of the 2015 Eighth International Conference on Contemporary Computing, Noida, India, pp. 404-409.
  • N. Joshi, A. Kumar, P. Chakraborty and R. Kala (2015) Speech controlled robotics using Artificial Neural Network, In: Proceedings of the 2015 Third International Conference on Image Information Processing, Waknaghat, pp. 526-530.
  • V. Kumar, G. C. Nandi, R. Kala (2014) Static Hand Gesture Recognition using Stacked Denoising Sparse Autoencoders, In Proceedings of the 2014 Seventh International Conference on Contemporary Computing, Noida, India, pp. 99 – 104.
  • A. Tarsauliya, R. Kala, R. Tiwari, A. Shukla (2011) Financial Time Series Forecast Using Neural Network Ensembles. In Proceedings of the International Conference on Swarm Intelligence, Springer Lecture Notes in Computer Science, Chongqing, China, pp. 480- 488.
  • A. Tarsauliya, R. Kala, R. Tiwari, A. Shukla (2011) Financial Time Series Volatility Forecast Using Evolutionary Hybrid Artificial Neural Network. In Proceedings of the Springer Fourth International Conference on Network Security & Applications, Chennai, India, pp. 463-471
  • R. R. Janghel, A. Shukla, R. Tiwari, R. Kala (2010) Intelligent Decision Support System for Breast Cancer. In Proceedings of the International Conference on Swarm Intelligence, Springer Lecture Notes in Computer Science, Beijing, China, pp. 351-358.
  • R. Kala, H. Vazirani, A. Shukla, R. Tiwari (2010) Fusion of Speech and Face by Enhanced Modular Neural Network. In Proceedings of the Springer International Conference on Information Systems, Technology and Management, Bankok, Thailand, pp. 363-372.
  • Y. K. Meena, K. V. Arya, R. Kala (2010) Classification using Redundant Mapping in Modular Neural Networks. In Proceedings of the 2010 IEEE World Congress on Nature and Biologically Inspired Computing, Fukuoka, Japan, pp. 554 – 559.
  • R. R. Janghel, A. Shukla, R. Tiwari, R. Kala (2010) Breast Cancer Diagnostic System using Symbiotic Adaptive Neuro-evolution (SANE). In Proceedings of the 2010 IEEE International Conference of Soft Computing and Pattern Recognition, Cercy Pontoise/Paris, France, pp. 326-329.
  • R. R. Janghel, A. Shukla, R. Tiwari, R. Kala (2010) Breast Cancer Diagnosis using Artificial Neural Network Models. In Proceedings of the 3rd IEEE International Conference on Information Sciences and Interaction Sciences,Chengdu, China, pp. 89-94.
  • H. Vazirani, R. Kala, A. Shukla, R. Tiwari (2010) Diagnosis of Breast Cancer by Modular Neural Network. In Proceedings of the Third IEEE International Conference on Computer Science and Information Technology,Chengdu, China, pp. 115-119.
  • A. Shukla, R. Tiwari, A. Ranjan, R. Kala (2009) Multi Lingual Character Recognition using Hierarchical Rule Based Classification and Artificial Neural Network. In Proceedings of the Sixth International Symposium on Neural Networks, Springer Verlag Lecture Notes in Computer Science, Wukan, China, pp. 821–830.
  • R. Kala, A. Shukla, R. Tiwari (2009) Comparative analysis of intelligent hybrid systems for detection of PIMA Indian diabetes. In Proceedings of the 2009 IEEE World Congress on Nature & Biologically Inspired Computing, Coimbatote, India, pp. 947 – 952.
  • R. Kala, A. Shukla, R. Tiwari (2009) Optimized Graph Search using Multi Level Graph Clustering. In Proceedings of the Springer International Conference on Contemporary Computing, Noida, India, pp. 103-114.  
  • R. Kala, A. Shukla, R. Tiwari (2009) Fuzzy Neuro Systems for Machine Learning for Large Data Sets. In Proceedings of the IEEE International Advanced Computing Conference, Patiala, India, pp. 541-545. 
  • R. Kala, A. Shukla, R. Tiwari (2009) Fast Learning Neural Network using modified Corners Algorithm. In Proceedings of the IEEE Global Congress on Intelligent System, Xiamen, China, pp. 367-373.
  • R. Kumar, R. Ranjan, S. K. Singh, R. Kala, A. Shukla, R. Tiwari (2009) Multilingual Speaker Recognition Using Neural Network. In Proceedings of the Frontiers of Research on Speech and Music, Gwalior, India, pp. 1-8.
  • R. Kala, A. Shukla, R. Tiwari (2013) Breast Cancer Diagnosis Using Optimized Attribute Division in Modular Neural Networks. In Interdisciplinary Advances in Information Technology Research, IGI Global, Chapter 3, Hershey, PA, pp. 34-47.
  • R. Kala, A. Shukla, R. Tiwari (2011) Handling Large Medical Data Sets for Disease Detection. In Biomedical Engineering and Information Systems: Technologies, Tools and Applications, IGI Global, Chapter 8, Hershey, PA, pp. 162-176.
  • R. Kala, A. Shukla, R. Tiwari (2010) Hybrid Intelligent Systems for Medical Diagnosis. In Intelligent Medical technologies and Biomedical Engineering: Tools and Applications, IGI Global, Chapter 9, Hershey, PA, pp. 187-202.
  • A. Shukla, R. Tiwari, H. K. Meena, R. Kala (2009) Speaker Identification using Wavelet Analysis and Modular Neural Networks. Journal of Acoustic Society of India,36(1): 14-19.
  • A. Shukla, R. Tiwari, H. K. Meena, R. Kala (2009) Speaker Identification using Wavelet Analysis and Artificial Neural Networks. Journal of Acoustic Society of India, 36(1): 20-25.
  • A. Shukla, R. Tiwari, H. K. Meena, R. Kala (2009) Speaker Identification using Wavelet Analysis and Modular Neural Networks. In Proceedings of the  National Symposium on Acoustics, Vishakhapatnam, India, pp. 125-130.