Description

• Overview. This course will study the algorithmic aspects of AI-based systems that sense and interact with the physical world. This field is broadly characterised as autonomous systems and also called physical/embodied AI/ AI-based robotics. The course will have both practical and theoretical components. The practical component will build on theory and will require thorough experimentation and analysis by the students.
• Core 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: COL333 / COL774 / COL3333/ COL7333/ COL7341/ AIL7025/ AIL7024. Permitted: ****AIL7022 / APL745 / APL744 / APL747 / ELL409.
• Note: Students who have undertaken COL864 (Sem 1 2025-26) are requested not to register for COL7378/778. They would have already done the advanced version of this course with a significant overlap. They will gain more by doing other courses instead.

Logistics

Announcements

• The rubric for the midterm can be found here
• Information related to mid-term examination appears below.
• No class on Monday 16.02.2026.
• Assignment 2 is available. Please see the assignment section. It will be discussed in the class on 05.02.2026.
• Extra class is scheduled for Saturday (17.01.2026) at 2:00pm in SIT001 (SIT Building ground floor).
• Assignment 1 is released. Please see the assignment section.
• First class will be held on Monday 05.01.2026.
• We will be using Piazza for all course related discussions, assignment clarifications and announcements. The link appears above.

Topics

The tentative list of topics appears below.

• Course Organisation/Introduction
• Agent Representation