Skip to content

AI for Robotics

PDF icon Download in PDF

  • Lecturer: Stéphane Doncieux (stephane.doncieux@sorbonne-universite.fr)
  • Course code: UM5RBI34
  • Student workload: 16 h of lectures, 12 h of labs
  • Credits: 3 ECTS
  • Specialization tracks: ROBOT SI (elective) MeDH
  • Semester offered: S1 S2 S3 S4
  • Language of instruction: French English
  • Targeted audience: Eng. Sc. department Other :
  • Localization : PMC Campus Other :

Course Overview

This course unit introduces students to the issues involved in applying AI methods, particularly learning methods, to real robots. It presents different AI approaches to robotics, focusing on two complementary reinforcement-learning methods (with and without gradients) and on planning in robotics.

Mots-clés : Artificial intelligence, robotics, learning, motion planning

Prerequisites

Students should have previously acquired the following prerequisites to follow this course:

  • Machine learning, deep learning

Intended Learning Outcomes

By the end of this course, students will be able to:

  1. Situate the different artificial-intelligence approaches used in robotics;
  2. Understand the principles of evolutionary algorithms;
  3. Implement and apply evolutionary algorithms such as NSGA-II;
  4. Understand the principles of quality-diversity algorithms;
  5. Choose a deep reinforcement-learning algorithm suited to a given problem
  6. Implement and apply DQN and DDPG
  7. Implement and apply policy-gradient methods
  8. Identify a planning problem and choose a suitable algorithm
  9. Implement and apply motion-planning algorithms (RRT, RRT*)
  10. Understand the principles of alternative AI approaches for robotics

Indicative Teaching Sequence and Methods

Week C/TD/TP* Content Preparation Learn.\ outc.
S1 C  AI and robotics: introduction / Evolutionary robotics AAV1-4
S2 TP Evolutionary robotics AAV2-4
S3 C Deep RL and robotics AAV5
S4 TP Deep RL and robotics AAV6-7
S5 C Planning and robotics / introductory lecture 1 AAV8, AAV12
S6 TP Planning and robotics AAV9
S7 C Introductory lectures 2 and 3 AAV12
  • C/TD/TP respectively corresponds to lectures, tutorials and lab sessions.

Sequence of the unit

The course unit consists of three lecture/practical sessions and three introductory lectures.

Indicative Assessment of Intended Learning Outcomes (1st session)

Week Individ./group In-person/remote Type of exam Evaluated outcomes Scale %
S2 Individual In-person TP AAV2-4 20%
S4 Individual In-person TP AAV5-7 20%
S6 Individual In-person TP AAV8-11 20%
S15 Individual In-person Other AAV 1-12 40%

2nde session

Session Individ./group In-person/remote Type of exam Evaluated outcomes Scale %
2 Individual In-person Other AAV 1-12 100%

Bibliographic references

  • 1.     Russel, S. & Norvig, P. (2016). Artificial Intelligence: A modern approach.
    1. Vernon, D. (2014). Artificial cognitive systems: A primer.
    1. Floreano, D. & Mattiussi, C. (2008). Bio-inspired artificial intelligence
    1. LaValle, S. M. (2006) Planning algorithms http://planning.cs.uiuc.edu/

Logo SDI Date of generation of this unit description: 06/10/2026 Logo SDI