Description

• This course will study Embodied AI or intelligent AI systems that interact with the physical world. This is a sub-area of AI that deals with the algorithmic aspects of intelligent robotics and more generally autonomous systems.
• The course will be arranged around topics: planning, state estimation and learning that are central to an intelligent agent. Additionally, we will examine how the agent can make intelligent decisions given imperfect or uncertain knowledge about the world.
• Note that we will focus on the core algorithmic and AI aspects. The detailed physical interaction and control will largely be abstracted away for algorithmic treatment.
• Pre-requisites: Introduction to Artificial Intelligence (COL333-671) or Introduction to Machine Learning (COL774 or equivalent). Programming proficiency and knowledge of probabilistic models, basic deep learning, basic search algorithms, logic and probability will be an advantage.
• The course will set the context with the foundational material on fundamentals of embodied AI systems and then introduce recent work. The course has a research orientation and will require self-exploration on selected topics building off knowledge from earlier courses.

Logistics

Announcements

• Namasivayam K (CSE PhD student) will be the head TA for the course.
• First class will be held on Tuesday 01.08.2023.
• The minor examination will be conducted on Thursday, September 14th, 2023. The instructions are given below.
• Viva for A1 will be conducted on Wednesday (20.09.2023). Please see piazza (https://piazza.com/class/llxmli726sx4jv/post/13) for more details.
• Please see the major examination instructions here.
• The Major exam solution and rubrics are available here

Topics

The class material will be covered on the white/black board. Slides and reference papers for some of the topics will also be provided. Slides/papers will be uploaded below (typically after the class). The list is tentative and can be slightly modified as we progress.

Assignments