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.
Related Publications
- R. Tiwari, A. Shukla, R. Kala (2013) Intelligent Planning for Mobile Robotics:Algorithmic Approaches, IGI Global Publishers,Hershey, PA.
- R. Kala (2010) Video Lecture of Soft Computing (39 Hour Video Lecture Series), Soft Computing and Expert System Laboratory, IIITM Gwalior, India. Available at: http://rkala.in/softcomputingvideos.php
- R. Kala (2018) Routing-based navigation of dense mobile robots. Intelligent Service Robotics 11(1): 25–39. (Download Paper)
- R. Kala (2018) On repelling robotic trajectories: coordination in navigation of multiple mobile robots. Intelligent Service Robotics 11(1): 79–95. (Download Paper)
- R. Kala (2014) Navigating Multiple Mobile Robots without Direct Communication. International Journal of Intelligent Systems, 29(8): 767–786. (Download Paper)
- R. Kala (2014) Coordination in Navigation of Multiple Mobile Robots. Cybernetics and Systems, 45(1): 1-24. (Download Paper)
- R. Kala (2013) Rapidly-exploring Random Graphs: Motion Planning of Multiple Mobile Robots. Advanced Robotics, 27(14): 1113-1122. (Download Paper)
- R. Kala (2013) Multi-Robot Motion Planning using Hybrid MNHS and Genetic Algorithms. Applied Artificial Intelligence, 27(3): 170-198. (Download Paper)
- R. Kala (2012) Multi-Robot Path Planning using Co-Evolutionary Genetic Programming. Expert Systems With Applications, 39(3): 3817-3831. (Download Paper)
- Apoorva, R. Gautam, R. Kala (2018) Motion Planning for a Chain of Mobile Robots Using A* and Potential Field, Robotics 2018, 7(2), 20. (Download Paper)
