Machine perception is the ability of an embodied device to perceive, comprehend, and reason about the surrounding environment. This course will introduce students to foundational principles of geometric and statistical learning approaches for machine perception. Topics include sensing techniques (vision, motion, audio, touch), probabilistic state estimation, localization and mapping, 3D reconstruction, object detection, and scene understanding algorithms. Students will implement, debug and test machine perception algorithms on different sensory data in Python through labs and hands-on programming assignments. Prerequisite: CS225. One of CS440, CS446, ECE484, or equivalent, is recommended.


  • Time: Tuesday/Thursday 11:00am - 12:15pm
  • Location: Room 0216 Siebel Center for Comp Sci
  • Office Hour: Shenlong: Siebel 3336 Thursday 4:00pm - 5:00pm; Albert: TBD
  • Discussion: Campuswire (Code: 1739)
  • Assignments Submission: Gradescope (Course Code: BBX6NE)
  • Online Lectures: This is an in-person class. We will not be offering online option/recording for this class. It is designed to be highly interactive and we strongly recommend that you attend in person in order to fully participate and benefit from the class.
  • Contact: Students should ask all course-related questions on Campuswire, where you will also find announcements. For external inquiries, personal matters, or in emergencies, you can post private message that is only available to the course instructors in Campusewire (email is likely to get starts with [CS498]).