Learning and Autonomous Control

The team Learning and Autonomous Control (LAC) focuses on robot control methods spanning the whole range from high-level cognitive approaches including adaptation and learning to low-level motion control. We develop novel algorithms, methods, and solutions in the following areas of robotics:

  1. robot learning - reinforcement learning and deep learning for teaching robots interactively, from human demonstrations and also for continual improvement of the robot’s performance;
  2. robot navigation - motion planning in dynamic environments, social interaction with other agents and real-time computational aspects of model predictive control;
  3. multi-robot control - real-time coordination, dynamic vehicle routing and task assignment, multi-agent learning and security and privacy aspects of multi-robot systems.

We apply our novel methods to industrial robotics, agro-food and retail robotics, mobile manipulation, autonomous driving, aerial vehicles, and intelligent transportation.

 

Professors

Teaching

  • RO47002: Machine Learning for Robotics
  • RO4705: Planning and Decision Making
  • ME41025: Robotics Practicals
  • ME47035: Robot Motion Planning and Control
  • SC42050: Knowledge-Based Control Systems
  • CS4230: Machine Learning 2 (module on reinforcement learning)