Courses

Robots are capable of doing every wonderful and challenging task you want them to do, provided that the robots are made capable of masterminding the missions that you desire. Planning deals with the intelligence of making smart moves to even vague and dumb task definitions, rather than the other way round. Motion planning is the problem of enabling the robots run for you or run from you, without causing injury to anyone/anything movable or immovable. Even humans stumble when walking for which a common and recent example is texting and walking in characteristic scenarios. Nevertheless, asking the humans to teach the art of navigation to robots is the challenge taken in the course. Luckily we have standard tools for teaching and cheating, which is what the course is about. And if you succeed, those scary science fiction robots may just get real, a small but valid possibility!  

In this course, we study how the robots can move from one place to the other, without colliding, while making quality navigation plans in computationally less time. Attempt is to make the robot avoid small to big obstacles, structured and unstructured obstacles, static and dynamic obstacles, and complex mazes to wide open spaces; while triumphantly reaching the goal. Quicker calculations imply faster robots with more capability to handle sudden or dynamic changes in the environment. A variety of methods would be discussed including those coming from the domains of artificial intelligence, soft computing and from the general walking, running and quarrelling principles of the students.  

Ever wondered by nearly impromptu making decisions you end up being so awesome? How the sight of a question paper can invalidate all pre-decided cheating chains and dynamically make new ones without easy communication? What gives the capability to see a new dangerous assignment and stand tall united within no time? And what gives the capability to the institution to foresee any such attempts and tactically drop surprises which are hard to combat? In this beautiful journey we see how innocent, small and week looking lives otherwise end up giving a display of the most majestic nature, whether in your favor or against you is a matter of discretion. Taking an inspiration, we see the mechanisms to simulate and engineer the artificial systems of the future that will do something amazing, while still be so simple to look, to develop and (to some extent) to cost.

The course takes a deeper looks into all micro and macro beings around, all cool looking natural mechanisms and everything that you’d been doing so far, to assess the fundamental working mechanisms behind these and thereafter to see if the same can be injected into artificial systems and robots for some amazing capabilities. The course talks about the intelligent paradigms of search and evolutionary behaviors of animals (and animal-like humans), exhibition of characteristics behaviors that you love or hate, and creation of a simulation setup to get a full view of the amazing world of chaos all around, and the mechanisms to make robots exhibit the same characteristics.

One of the most desired capabilities of robots is to fetch a can of beer from the refrigerator and to serve that to you, when you’d not be in a position to do so. This course is towards the same technology and hence worthy of reading. The course discusses the math and science of this noble task, so that one can program robotic manipulators to work, while ensuring no spillage, no destruction, no getting stuck, and an accurate and efficient service.

The course talks about the basics of robotics in general and the robotic manipulators in specific, explaining all the key components which enables the manipulators to carry operations. One could transform the pose of one joint of the manipulator to the other, finally giving the ability to know the location of the hand or the end-effector with respect to the base; further creating a mechanism to compute the pose of every joint to get the hand or the end-effector at the desired location. The velocities can be transformed between joints to get the velocity of the end-effector or the inverse. The relations can be used to compute a smooth trajectory for the end-effector and joints of the manipulator to achieve the desired task. Once these basic blocks are known, one could make a dynamics model of the manipulator and further devise control strategies for the manipulator. The ability to control the manipulator makes the basic foundation block to program the robot to carry interesting operations, or to use a simulation setup to test the correctness of the program. Finally the technology leads to an automation setup and automation models for the factory floor.

Many kids join us to fulfil their childhood dream of making a robot that looks exactly the same as any science fiction movie, and therefore, to advertise we have to run a course that promises exactly the same thing. Being an IT institute, we primarily look at the software side of it, and making education affordable, focus on the simulation aspects.

The course on Foundations of Robotics – II (that closely resembles the course on humanoid robotics) takes you through a journey covering all software components that power modern robots. Even though the students often get lost in this journey, we make sure that the human fate is never witnessed by the robots by focused on Simultaneous Localization and Mapping concepts, through which robots always get a map and their location. The students often re-visit the rationality of their decision of choosing this elective, however, the course ensures that the robots make the best decisions always for navigation through a mixture of planning techniques and execution through controls. Because we deal with students, we know the meaning of every gesture that the students make during the class, and teach the students how to impart the same skill set into robots. To add some fun, the course also does window shopping of different robots, sensors and cool gadgets.

In a world where machines are learning the entire curriculum of all top universities and corporate combined, it would be imperative that robotics and autonomous systems is within their curriculum. We are an amazing university where humans are making machines learn, and machines are helping humans learn. In parallel, we taught machines to learn robotics and autonomous systems decision making, particularly navigation, and we taught humans the algorithmics for the same. They both failed with ammusing answers in the examination copies for the students and amusing behaviors of the robots who grauduated from the machine learning university. So we thought that teaching students how robotics and autonomous systems (fail to) learn would make an interesting course.

The course gives a background of machine learning as the chief tool to operate robots, and literally goes deeper with time featuring a coverage of deep learning and recurrent models. By this time the students get some rewards as marks in their account, so we teach them reinforcement learning to help them in their decision making. We then shift gears to cover robotics and autonomous systems, deciphering all the algorithmics that lets robots know their position, their map, helps them make navigation and manipulation decisions, and control themselves in pursuit of the same. We understand why this is too complicated and unnecissary to learn in a world where the robots are learning themselves, and discuss the supervised learning and reinforcement learning frameworks for robots that learn for themselves.

Mesmerized by the storm of increase of intelligence in the machines and the storm of decrease of intelligence in the humans, the institute decided to start a flagship course that teaches the students everything about intelligent machines in a single course, and this course was born. Studied by students from different academic coursework backgrounds, with different projects in the past, and with different requirements – this mandatory course is the modern day equivalent of unity in diversity. The course sometimes covers topics that all but one already know, and sometimes leaves topics that none know.

Like many other courses at this institute, a good part of the course is on neural networks and machine learning with the difference that for some post-graduate students this is the first such offering. The course slowly dissects the commonly seen intelligent systems, takes the technology outside for examination, notes the basic constituents, and teaches the generics. Because machine learning is a hype, the course covers different applications, problems, and some tools. The leftover time goes into evolutionary computation and fuzzy logic. To make the instructor look intellectual, the complexity is added by discussions on different hybrid systems involving multiple techniques at once. The laboratory part is easy to solve given a wide array of libraries available. The course looks into some machine learning data sets, regression and classification problems, and some computer vision problems to gets a hands-on and let students brag about what their codes do in front of non-IT friends and family.

Intelligence is the most precious gift which most of the humans have, and most of them make good use of it, though may not always be at the right time. Humans are so intelligent that we go forth with teaching this skill to other people and even our beloved machines. In this course I try to make the students intelligent, so that they may make the lame looking machines intelligent and do some awesome stuff. Thinking about thinking is a weird thing to do, which however lays the foundation of making machines intelligent by incorporating the same thinking fundamentals. And attributed to their enormous storage capacity and speed to process information, both much higher than the practically what the humans exhibit, especially students; the machines are winning over the humans by a long way. However the dumbness showed by machines to the easiest of things is also in no comparison to the dumbness of humans, even students.

Today the machines can compute all possibilities of everything good and bad against every action and reaction over time, to tell you smart moves, smart enough to flatter people. The machines could interpret the vague, false and incomplete narrations of your friends to present you the truth. The machines could act logically stop you from making decisions, which you may take in a flow and later regret. And what not, it is a pool of possibilities. So the machine package sounds far better than any living companion, only till it comes to a context unseen, unheard, not thought of, unimaginable and a surprise when the acts of your machine package would be mere entertaining rather than helping.

Data is like your wardrobe, you want the selected clothes as fast as possible, should occupy the least magnitude of space, should take the least of efforts to add stuff and organize, and should look beautiful at the same time. Naturally the requirements are too hard to keep, especially when you’re a heartthrob and people love gifting you now and then. The course preaches the way to understand your problems and get your stuff organized, the digital version. The course discusses fancy looking structures to organize your stuff; while the stuff may be ugly, the organization is beautiful and efficient.

This is largely a programming course and takes aboard the students in a challenging journey of increasing complexity as the course proceeds. Starting from the primitive uses of arrays and linked lists, and using the same primitives to implement basic data structures, the course carries forward to programming and using trees and graphs. The course presents a blend of programming primitive operations of data structures, and using the data structures for unbelievable problems creatively crafted by the instructors.

To a community that believes computer software powered by algorithms are the one-stop solution to all world problems, this is the celebritic course whose GPAs are believed to increase your LPAs as per modern myths. Here we convince ourselves that that we can solve all hard real-life problmes using the tool-set that the course brings, and that the solutions would be scalable when the world’s population is simultaniously onboarded. If you have a (not-so-personal) problem in life, try treating it with one of the finest choicest of liquours crewed for ages and served in this course. If it can’t, we offer a license to take one of the many advanced theoretical and application oriented courses.

The course teaches you how to divide your cheating material among friends and collaborate to conquer the exams, and the complexity of the solution to reap benefits within the examination period. We study how to allocate study material into pockets by hashing the topic name, so that the time from reading the question to getting the chits is minimized. While the instructor struggles to make the class dynamic, we teach you how to program using dynamic programming, and be greedy in your approaches to life ‘coz there are limited top grades. We model the batch as a graph to search the shortest path of a cheat from a source to a destination, and see how to make networks such that the total time for the whole batch to copy an assignment is minimized and flow across the network is maximized. We also teach how to compare two assignments to help you add enough non-sensical information to minimize automated match.

This course teaches you the skills to make great software (front end) to solve all problems in the world, and teaches you to code using stunning looking re-usable designs so that someone can proxy for you by working over the same codes when you’re enjoying vacations at exotic locations. Looking at the failure to custom design my office after repetitive attempts, I choose to get students’ hands dirty with the programming aspects on the code. The language is carefully chosen using most enthralling name as a metric, which came down to JAVA.

My part of the course gives the most unreal problems, mostly simulating stuff I wish I could do in real life, and asks the students to actually learn how to program them. The course involves understanding the different object oriented flavors of Object Oriented Methodologies and tasting them in JAVA. The first half of the course starts with lousy command line applications, primarily dealing with injecting inheritances and interfaces to all modules of a boring simulation exercise. After an intermission, we deal with what bugs most programmers, exceptions, and add a GUI flavor to give the course a better visual appeal. For the lazy programmers, the course covers the collection frameworks. To impress ‘the one’ in a tech world, the course also covers multi-threading and animations.

Think it is cool to visit new places and talk to the locals in their local dialects, thus knowing a large kitty of languages? We do the same thing here, except that the people are computer screens and therefore the languages are programming in nature. We give you the power to surprize your computer with a new language that your computer understands. This course on window shopping of programming languages also teases you to understand which stement makes which impact inside your computer brain’s and how your computer understands you. We let you chose your language while dating your computer, a language that takes the least time to express your intentions with no or little mis-understanding of thoughts, while also takes the least time to execute the intentions, for once and always.

The course discusses different kinds of programming languages and their need. We follow the love story of how a variable binds to a storage location successfully giving birth to a value of a specific datatype if the couple are scope-compatible. We see how these values could together express themselves as expressions and assignments, with a control mechanism inside one or many sub-programs of life. We look into how to concurrently solve problems, hoping, unlike students, all units are functional and logic-based.