Postgraduate Course: Robot Learning and Sensorimotor Control (INFR11186)
|School||School of Informatics
||College||College of Science and Engineering
|Credit level (Normal year taken)||SCQF Level 11 (Postgraduate)
||Availability||Available to all students
|Summary||This course is designed as a follow up to the introductory course on Robotics: Science and Systems and will gear students towards advanced topics in robot control, learning and planning from an optimisation perspective. Control of complex, compliant, multi degree of freedom (DOF) sensorimotor systems like humanoid robots or autonomous vehicles have been pushing the limits of traditional planning and control methods.
This course aims at introducing an optimisation approach to the challenges and will take the students through various aspects involved in motor planning, control, estimation, prediction and learning with an emphasis on the computational perspective. We will learn about optimisation and learning tools and methodologies particularly geared towards problems of online real-time predictive planning for robot control.
Issues and possible approaches for planning under uncertainty and redundancy, sensorimotor transformations and stochastic optimal control will be discussed. This will be put in context through exposure to topics in underactuated systems, legged locomotion and human motor control, and the use of computational methods in understanding biological sensorimotor mechanisms.
1. Optimal Control Approaches - Dynamic Programming, LQR, Trajectory Optimization: Direct and Shooting Methods (iLQR, DDP)
2. Adaptive Learning and Control - Predictive Control - Underactuation - Multi-contact modelling and optimization - Constrained Operational Space Control - Hierarchical QP and Stack of task formulation
3. Interaction and Robust Control - Stochastic Optimal Control - LQG - Cartesian Impedance Control - Passivity Methods - Lyapunov Stability - LQR-Trees and Sum-of-Squares Programming
4. Movement Primitives - Rhythmic vs Point to Point Movements - Dynamical Systems and DMPs - Path Integral Methods - Learning by Demonstration
5. Understanding Human Sensorimotor Control - Force Field and Adaptation - Optimal control theory for Explaining Sensorimotor Behaviour - Impedance Control - Human(oid) Locomotion and Stability.
Entry Requirements (not applicable to Visiting Students)
||Other requirements|| This course is open to all Informatics students including those on joint degrees. For external students where this course is not listed in your DPT, please seek special permission from the course organiser (lecturer).
Some prior exposure to robotics basics (such as Robotics: Science and Systems) and/or machine learning basics is recommended. A mathematical background is assumed. Programming will be required in an environment such as MATLAB.
Information for Visiting Students
|High Demand Course?
Course Delivery Information
|Not being delivered|
On completion of this course, the student will be able to:
- Demonstrate knowledge of key areas of robot dynamics control and kinematic planning.
- Analyze and evaluate conceptual and empirical problems in adaptive control and robot learning.
- Analyze and implement a subset of established learning algorithms in dynamics learning and stochastic optimal control.
- Demonstrate understanding of issues related to optimality in human motor control; develop ability to frame human motor control problems in an optimization framework.
|Donald E. Kirk, Optimal Control Theory: An Introduction|
Robert F. Stengel, Optimal Control and Estimation
Mark W. Spong, Seth Hutchinson and M. Vidyasagar, Robot Modeling and Control
Sciliano, Khatib (ed.) Springer Handbook of Robotics
|Graduate Attributes and Skills
|Course organiser||Dr Michael Mistry
Tel: (0131 6)50 2937
|Course secretary||Ms Lindsay Seal
Tel: (0131 6)50 2701