CS7001: Robot Perception and Learning
| Instructor | Nived Chebrolu |
| Credits | 8 (6 for Theory, 2 for Lab) |
| Lecture Timings | Wed/Fri, Slot 6: 9:30 – 11:00 AM |
| Lecture Venue | CC-101 |
| Lab Timings | TBA |
| Lab Venue | Software Lab 3 (SL3) in CC Building |
| TAs | Adarsh, Arjun, Arun, Bhavik, Jaison, Priya, Ved, Saurbh, Shakthi, Shivam, Sriventakeshawar. |
| Instructor/TA Office Hours | TBA |
Announcements
[Jul 26th, 2026] Course website is live. Welcome!
[Jul 27th 2026] First lecture session will be on 29th July (Wed) in CC-101 at 9.30 AM.
[Jul 27th 2026] First lab session will be held on 3rd Aug (Mon) in SL3 at 8:15 AM.
[Aug 4th 2026] Lab sessions for robot assembly and testing will be held on 5th Aug (Wed) and 7th Aug (Fri) in SL3 at 5:00 PM. All students are expected to attend both the sessions.
Overview
Description
This course introduces the foundations of robot perception and learning, covering how robots sense, interpret, and reason about the world around them. Topics span probabilistic state estimation methods, localization and mapping for mobile robots, planning and exploration, and robot learning techniques using data and simulation tools. The course will place an emphasis on hands-on implementation both in simulation as well on robot hardware.
Prerequisites
There are no strict pre-requisites enforced. Students should be comfortable with the following:
Probability and Linear Algebra
Programming in Python
Basic Machine Learning concepts are helpful but not strictly required.
Who Can Take This Course
This is a graduate-level course open to all M.Tech/M.S. and PhD students. B.Tech students in their third and fourth year are also eligible to enroll in the course.
Course Schedule
Note: The schedule is tentative and will be updated over the course.
| Week | Date | Topic | Slides | References |
| 1 | Jul 29 | Introduction and Course Overview | intro, probability primer | Thrun et al. “Probabilistic Robotics”, Chapter 2.1 & 2.2 |
| 1 | Jul 31 | Recursive State Estimation | bayes filter, notebook | Thrun et al. “Probabilistic Robotics”, Chapter 2.3 |
| 2 | Aug 5 | Robot Locomotion | robot locomotion, notebook | – |
| 2 | Aug 7 | Probablisitic Motion Models | motion models, notebook | Thrun et al. “Probabilistic Robotics”, Chapter 5 |
| 3 | Aug 12 | Probabilistic Sensor Models | sensor models,notebook | Thrun et al. “Probabilistic Robotics”, Chapter 6 |
| 3 | Aug 14 | Kalman Filters and Extended Kalman Filters (EKF) | EKF | Thrun et al. “Probabilistic Robotics”, Chapter 3 & 7 |
| 4 | Aug 19 | Localization using Extended Kalman Filters | EKF localization, notebook | Thrun et al. “Probabilistic Robotics”, Chapter 3 & 7 |
| 4 | Aug 21 | Particle Filters and Monte-Carlo Localization | Particle Filter | Thrun et al. “Probabilistic Robotics”, Chapter 3 & 8.3 |
| 5 | Aug 26 | Holday (Id) | – | – |
| 5 | Aug 28 | Mapping with Known Poses | Occupancy grid mapping, notebook | Thrun et al. “Probabilistic Robotics”, Chapter 4.2, 9.1, 9.2 |
| 6 | Sep 2 | Simultaneous Localization and Mapping (SLAM), EKF SLAM | EKF SLAM | Thrun et al. “Probabilistic Robotics”, Chapter 10 |
| 6 | Sep 4 | Particle Filter SLAM | Particle Filter based SLAM | Thrun et al. “Probabilistic Robotics”, Chapter 13 |
| 7 | Sep 9 | Least-Squares/Graph SLAM I | – | – |
| 7 | Sep 11 | Least-Squares/Graph SLAM II | – | – |
| 8 | Sep 12–20 | Mid-semester Exam | – | – |
| 9 | Sep 23 | SLAM Frontends | – | – |
| 9 | Sep 25 | Map Representations and Modern SLAM pipelines | – | – |
| 10 | Sep 30 | Motion Planning I | – | – |
| 10 | Oct 2 | Holiday (Gandhi Jayanti) | – | – |
| 11 | Oct 7 | Motion Planning II | – | – |
| 11 | Oct 9 | Planning under Uncertainty | – | – |
| 12 | Oct 14 | Exploration and Informative Path Planning II | – | – |
| 12 | Oct 16 | Exploration and Informative Path Planning II | – | – |
| 13 | Oct 21 | Introduction to robot learning, Learning from Demonstrations I | – | – |
| 13 | Oct 23 | Learning from Demonstrations II | – | – |
| 14 | Oct 28 | Reinforcement Learning for Robotics - II | – | – |
| 14 | Oct 30 | Reinforcement Learning for Robotics - II | – | – |
| 15 | Nov 4 | Recent developments in Robot Perception and Learning | – | – |
| 15 | Nov 6 | Course Wrap-up | – | – |
Grading
| Component | Weight |
| Mid-semester Exam | 15% |
| End-semester Exam | 15% |
| Assignments (4) | 40% |
| Labs (4) | 20% |
| Attendance/Quizzes | 10% |
Assignments will primarily be programming exercises where you will be asked to implement algorithms and test them in a simulation environment. There will also be analytical questions alongside the programming parts.
Labs will be done in groups of two and involve demonstrating the algorithms working on actual robot hardware.
Assignment and lab evaluations will include a viva component.
Mid-semester and End-semester exams will involve both programming and theory questions. Exams are closed-book; access to any material or the internet will not be allowed.
Academic Honesty
Students are expected to adhere to the highest standards of integrity and academic honesty. Violations will be dealt with strictly, in accordance with the institute's procedures and disciplinary actions for academic malpractice.
Assignments: All assignments must be completed individually. Students are free to discuss course material with peers, but must not discuss the contents of assignments with anyone other than the instructor or TAs. Sharing code is not permitted, even for portions that are perceived to be peripheral to the core logic (e.g., file handling, plotting, data loading). Consulting solutions to the given or related assignments on the internet is also not allowed.
Labs: Labs are done in groups. Collaboration within the group is encouraged. However, groups must not share code or solutions with other groups, and must not consult solutions to related exercises on the internet.
Examinations: All examinations are closed-book. Consulting any external material or another person during an exam will be treated as cheating.
Permitted use of external resources: Students may consult internet resources to understand a concept, a command, or a data structure (e.g., documentation, lecture notes, Wikipedia, textbooks). Library code or snippets for operations unrelated to the core logic of an assignment such as data I/O or visualization are acceptable. Using AI tools for such peripheral portions is also permissible, but discouraged. Every external resource consulted, for whatever reason, must be cited in a file named resources.txt included with the submission. If AI tools were used, each query must be reported verbatim along with a link to the session. Failure to disclose any resource or AI usage will itself be considered a violation.
If in doubt about what constitutes legitimate collaboration, ask the instructor before submitting.
References
The course does not follow a single textbook. Relevant reading will be posted alongside each lecture. The following are useful references:
S. Thrun, W. Burgard, and D. Fox, Probabilistic Robotics, MIT Press, 2005.
R. Siegwart, I. R. Nourbakhsh, and D. Scaramuzza, Introduction to Autonomous Mobile Robots, 2nd Edition, MIT Press, 2011.
L. Carlone, A. Kim, T. Barfoot, D. Cremers, and F. Dellaert, SLAM Handbook: From Localization and Mapping to Spatial Intelligence, Cambridge University Press, 2025.
P. Corke, Robotics, Vision and Control, 3rd Edition, Springer, 2023.
R. S. Sutton and A. G. Barto, Reinforcement Learning: An Introduction, 2nd Edition, MIT Press, 2018.