Hierarchical Planning and Control for Box Loco-Manipulation
dc.contributor.author | Xie, Zhaoming | en_US |
dc.contributor.author | Tseng, Jonathan | en_US |
dc.contributor.author | Starke, Sebastian | en_US |
dc.contributor.author | Panne, Michiel van de | en_US |
dc.contributor.author | Liu, C. Karen | en_US |
dc.contributor.editor | Wang, Huamin | en_US |
dc.contributor.editor | Ye, Yuting | en_US |
dc.contributor.editor | Victor Zordan | en_US |
dc.date.accessioned | 2023-10-16T12:32:50Z | |
dc.date.available | 2023-10-16T12:32:50Z | |
dc.date.issued | 2023 | |
dc.description.abstract | Humans perform everyday tasks using a combination of locomotion and manipulation skills. Building a system that can handle both skills is essential to creating virtual humans. We present a physically-simulated human capable of solving box rearrangement tasks, which requires a combination of both skills. We propose a hierarchical control architecture, where each level solves the task at a different level of abstraction, and the result is a physics-based simulated virtual human capable of rearranging boxes in a cluttered environment. The control architecture integrates a planner, diffusion models, and physics-based motion imitation of sparse motion clips using deep reinforcement learning. Boxes can vary in size, weight, shape, and placement height. Code and trained control policies are provided. | en_US |
dc.description.number | 3 | |
dc.description.sectionheaders | Physics-based Character Control | |
dc.description.seriesinformation | Proceedings of the ACM on Computer Graphics and Interactive Techniques | |
dc.description.volume | 6 | |
dc.identifier.doi | 10.1145/3606931 | |
dc.identifier.issn | 2577-6193 | |
dc.identifier.uri | https://doi.org/10.1145/3606931 | |
dc.identifier.uri | https://diglib.eg.org:443/handle/10.1145/3606931 | |
dc.publisher | ACM Association for Computing Machinery | en_US |
dc.subject | CCS Concepts: Computing methodologies -> Physical simulation; Reinforcement learning character animation, loco-manipulation" | |
dc.subject | Computing methodologies | |
dc.subject | Physical simulation | |
dc.subject | Reinforcement learning character animation | |
dc.subject | loco | |
dc.subject | manipulation" | |
dc.title | Hierarchical Planning and Control for Box Loco-Manipulation | en_US |