Learning Feasible Transitions for Efficient Contact Planning
Rikhat, Akizhanov Victor, Dhedin Majid, Khadiv Ivan, Laptev
Rikhat, Akizhanov
Victor, Dhedin
Majid, Khadiv
Ivan, Laptev
Supervisor
Department
Computer Vision
Embargo End Date
Type
Conference proceeding
Date
2025
License
Language
English
Collections
Research Projects
Organizational Units
Journal Issue
Abstract
In this paper, we propose an efficient contact planner for quadrupedal robots to navigate in extremely constrained environments such as stepping stones. The main difficulty in this setting stems from the mixed nature of the problem, namely discrete search over the steppable patches and continuous trajectory optimization. To speed up the discrete search, we study the properties of the transitions from one contact mode to another. In particular, we propose to learn a dynamic feasibility classifier and a target adjustment network. The former predicts if a contact transition between two contact modes is dynamically feasible. The latter is trained to compensate for misalignment in reaching a desired set of contact locations, due to imperfections of the low-level control. We integrate these learned networks in a Monte Carlo Tree Search (MCTS) contact planner. Our simulation results demonstrate that training these networks with offline data significantly speeds up the online search process and improves its accuracy.
Citation
R. Akizhanov, V. Dhédin, M. Khadiv, and I. Laptev, “Learning Feasible Transitions for Efficient Contact Planning,” in Proc. 7th Annu. Learning for Dynamics and Control Conf. (L4DC), Ann Arbor, MI, USA, Jun. 4–6, 2025, Proc. Mach. Learn. Res., vol. 283, pp. 431–442. ML Research Press, 2025.
Source
Proceedings of Machine Learning Research
Conference
7th Annual Learning for Dynamics and Control Conference, L4DC 2025
Keywords
Contact Planning, Deep Learning, Legged Robot, Motion Planning, Deep Learning, Optimization, Partial Discharges, Robot Programming, Contact Modes, Contact Planning, Legged Robots, Motion-planning, Property, Quadrupedal Robot, Speed Up, Stepping-stones, Trajectory Optimization, Motion Planning
Subjects
Source
7th Annual Learning for Dynamics and Control Conference, L4DC 2025
Publisher
ML Research Press