AiRLIHockey: Highly Reactive Contact Control and Stochastic Optimal Shooting

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Jankowski, Julius, Marić, Ante, Calinon, Sylvain
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866909083591770112
author Jankowski, Julius
Marić, Ante
Calinon, Sylvain
author_facet Jankowski, Julius
Marić, Ante
Calinon, Sylvain
contents Air hockey is a highly reactive game which requires the player to quickly reason over stochastic puck and contact dynamics. We implement a hierarchical framework which combines stochastic optimal control for planning shooting angles and sampling-based model-predictive control for continuously generating constrained mallet trajectories. Our agent was deployed and evaluated in simulation and on a physical setup as part of the Robot Air-Hockey challenge competition at NeurIPS 2023.
format Preprint
id arxiv_https___arxiv_org_abs_2401_14964
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle AiRLIHockey: Highly Reactive Contact Control and Stochastic Optimal Shooting
Jankowski, Julius
Marić, Ante
Calinon, Sylvain
Robotics
Air hockey is a highly reactive game which requires the player to quickly reason over stochastic puck and contact dynamics. We implement a hierarchical framework which combines stochastic optimal control for planning shooting angles and sampling-based model-predictive control for continuously generating constrained mallet trajectories. Our agent was deployed and evaluated in simulation and on a physical setup as part of the Robot Air-Hockey challenge competition at NeurIPS 2023.
title AiRLIHockey: Highly Reactive Contact Control and Stochastic Optimal Shooting
topic Robotics
url https://arxiv.org/abs/2401.14964