Foundations of Robotics
Cornell University, Fall 2025
Instructors: Tapomayukh Bhattacharjee, Preston Culbertson
Lecture: TR 10:10-11:25AM, Office Hours: See Ed
Credits: Fall 2025 - 4 credits - Letter grades only.
Week 1 Announcement
First lecture on August 26th!
Robotics is interdisciplinary and draws inspiration from many different fields towards solving a variety of tasks in real-world environments using physical systems. This course is a challenging introduction to basic computational concepts used broadly in robotics. By the end of this course, students should have a fundamental understanding of how the different sub-fields of robotics such as kinematics, state estimation, motion planning, and controls come together to develop intelligent behaviors in physical robotic systems. The mathematical basis of each area will be emphasized, and concepts will be motivated using common robotics applications. Students will be evaluated using a mixture of theoretical and programming exercises throughout the semester.
This course is offered in two versions; one for undergraduate students, and one for CS graduate students. While both versions cover similar material, the graduate version includes additional deliverables, including additional problems in some assignments. If you are a graduate student, you need to enroll in the graduate version of the course. For any questions, please contact Prof. Bhattacharjee.
Tapomayukh (Tapo) Bhattacharjee
he/him
tapomayukh@cornell.edu
Tapo wants to enable robots to assist people with mobility limitations with activities of daily living. He believes that efficient and safe physical and social interactions between robots and their immediate environments is the key. His work spans the fields of human-robot interaction, haptic perception, and robot manipulation.
Preston Culbertson
he/they
pculbertson@cornell.edu
Preston develops methods for physically robust robot learning, motivated in particular by problems in dexterous manipulation and tool use. His work combines ideas from optimization, control theory, and machine learning to design systems that remain reliable when models, sensors, or hardware are imperfect. The goal is to create robots that can explicitly manage uncertainty, adapt, and improvise when deployed in messy real-world settings.