Planning in Robotics

Login to KOS for course enrollment Display time-table
Code Completion Credits Range
Garant předmětu:
Pavel Surynek
Pavel Surynek
Pavel Surynek
Department of Applied Mathematics

The course covers theoretical aspects of planning in robotics from an abstract level known from classical planning to motion planning directly executable on robotic hardware. Abstract symbolic planning and robotics are linked together in this subject, so we will show how to create symbolic plans and refine them through geometric motion planning to the level of control of robotic hardware. The focus will be on (but not limited to) algorithms for creating classical plans by forward state search, planning with time and resources, planning under uncertainty, probabilistic planning. The course will smoothly continue with specific robotic aspects of planning, i.e. motion planning and reflecting the true plan execution in contrast to the ideal abstract plan, geometric representations of working and configuration spaces, combinatorial and probabilistic methods for pathfinding in configuration spaces, location and mapping techniques, motion planning with differential constraints. Planning and coordinating multiple robots will be important aspect that we will focus on. The course is focused on algorithmic techniques for generating plans, not on execution of plans by robots. It is therefore recommended to further verify the theoretical knowledge in practice in some of the robotic simulators or on real robots in the faculty laboratory.

Syllabus of lectures:
Syllabus of tutorials:

1. Classical planning, forward search planning algorithms, heuristics

2. Neo-classical planning and space planning, nondeterministic planning models

3. Extension of classical planning with resources and time, planning under uncertainty, probabilistic planning

4. Motion planning, working and configuration spaces and their exact and bitmap representations

5. Path / trajectory finding in configuration spaces - feasible and optimal, kinematics

6. Useful techniques from 3D computer graphics and computational geometry, collision detection

7. Localization and mapping, feedback planning

8. Planning with differential constraints and robot dynamics

9. Methods for motion planning in holonomic and non-holonomic cases

10. Control theory in robotics

11. Motion planning in multi-robot case, conflict-based search and connection with decision problems in logic theories

12. Techniques in specific application domains: autonomous transportation, automated warehouses, collaborative robotics

Study Objective:

The aim is to provide graduates with a comprehensive overview of planning in robotics with an emphasis on a deep understanding of important principles. We expect that the graduates will be able to contribute to the development of the field within their own research. We assume that the course will contribute to the education of future leaders in planning and robotics.

Study materials:

[1] M. LaValle, S.: Planning Algorithms. Cambridge University Press, 2006.

[2] Ghallab, M, Nau, D., Traverso, P.: Automated Planning and Acting. Cambridge University Press, 2016.

[3] Choset, H., Lynch, K. M., Hutchinson, S., Kantor, G., Burgard, W., Kavraki, L. E., Thrun, S.: Principles of Robot Motion: Theory, Algorithms, and Implementations. MIT Press, 2005.

Time-table for winter semester 2023/2024:
Time-table is not available yet
Time-table for summer semester 2023/2024:
Time-table is not available yet
The course is a part of the following study plans:
Data valid to 2024-04-11
Aktualizace výše uvedených informací naleznete na adrese https://bilakniha.cvut.cz/en/predmet6219506.html