Saved in:
Bibliographic Details
Main Authors: Wang, Jiayi, Kim, Sanghyun, Lembono, Teguh Santoso, Du, Wenqian, Shim, Jaehyun, Samadi, Saeid, Wang, Ke, Ivan, Vladimir, Calinon, Sylvain, Vijayakumar, Sethu, Tonneau, Steve
Format: Preprint
Published: 2023
Subjects:
Online Access:https://arxiv.org/abs/2306.04732
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866917642125705216
author Wang, Jiayi
Kim, Sanghyun
Lembono, Teguh Santoso
Du, Wenqian
Shim, Jaehyun
Samadi, Saeid
Wang, Ke
Ivan, Vladimir
Calinon, Sylvain
Vijayakumar, Sethu
Tonneau, Steve
author_facet Wang, Jiayi
Kim, Sanghyun
Lembono, Teguh Santoso
Du, Wenqian
Shim, Jaehyun
Samadi, Saeid
Wang, Ke
Ivan, Vladimir
Calinon, Sylvain
Vijayakumar, Sethu
Tonneau, Steve
contents Planning multi-contact motions in a receding horizon fashion requires a value function to guide the planning with respect to the future, e.g., building momentum to traverse large obstacles. Traditionally, the value function is approximated by computing trajectories in a prediction horizon (never executed) that foresees the future beyond the execution horizon. However, given the non-convex dynamics of multi-contact motions, this approach is computationally expensive. To enable online Receding Horizon Planning (RHP) of multi-contact motions, we find efficient approximations of the value function. Specifically, we propose a trajectory-based and a learning-based approach. In the former, namely RHP with Multiple Levels of Model Fidelity, we approximate the value function by computing the prediction horizon with a convex relaxed model. In the latter, namely Locally-Guided RHP, we learn an oracle to predict local objectives for locomotion tasks, and we use these local objectives to construct local value functions for guiding a short-horizon RHP. We evaluate both approaches in simulation by planning centroidal trajectories of a humanoid robot walking on moderate slopes, and on large slopes where the robot cannot maintain static balance. Our results show that locally-guided RHP achieves the best computation efficiency (95\%-98.6\% cycles converge online). This computation advantage enables us to demonstrate online receding horizon planning of our real-world humanoid robot Talos walking in dynamic environments that change on-the-fly.
format Preprint
id arxiv_https___arxiv_org_abs_2306_04732
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle Online Multi-Contact Receding Horizon Planning via Value Function Approximation
Wang, Jiayi
Kim, Sanghyun
Lembono, Teguh Santoso
Du, Wenqian
Shim, Jaehyun
Samadi, Saeid
Wang, Ke
Ivan, Vladimir
Calinon, Sylvain
Vijayakumar, Sethu
Tonneau, Steve
Robotics
Planning multi-contact motions in a receding horizon fashion requires a value function to guide the planning with respect to the future, e.g., building momentum to traverse large obstacles. Traditionally, the value function is approximated by computing trajectories in a prediction horizon (never executed) that foresees the future beyond the execution horizon. However, given the non-convex dynamics of multi-contact motions, this approach is computationally expensive. To enable online Receding Horizon Planning (RHP) of multi-contact motions, we find efficient approximations of the value function. Specifically, we propose a trajectory-based and a learning-based approach. In the former, namely RHP with Multiple Levels of Model Fidelity, we approximate the value function by computing the prediction horizon with a convex relaxed model. In the latter, namely Locally-Guided RHP, we learn an oracle to predict local objectives for locomotion tasks, and we use these local objectives to construct local value functions for guiding a short-horizon RHP. We evaluate both approaches in simulation by planning centroidal trajectories of a humanoid robot walking on moderate slopes, and on large slopes where the robot cannot maintain static balance. Our results show that locally-guided RHP achieves the best computation efficiency (95\%-98.6\% cycles converge online). This computation advantage enables us to demonstrate online receding horizon planning of our real-world humanoid robot Talos walking in dynamic environments that change on-the-fly.
title Online Multi-Contact Receding Horizon Planning via Value Function Approximation
topic Robotics
url https://arxiv.org/abs/2306.04732