TeamHOI: Learning a Unified Policy for Cooperative Human-Object Interactions with Any Team Size
Fuente:
arXiv
Saved in:
| Main Authors: | , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866911498712907776 |
|---|---|
| author | Lionar, Stefan Lee, Gim Hee |
| author_facet | Lionar, Stefan Lee, Gim Hee |
| contents | Physics-based humanoid control has achieved remarkable progress in enabling realistic and high-performing single-agent behaviors, yet extending these capabilities to cooperative human-object interaction (HOI) remains challenging. We present TeamHOI, a framework that enables a single decentralized policy to handle cooperative HOIs across any number of cooperating agents. Each agent operates using local observations while attending to other teammates through a Transformer-based policy network with teammate tokens, allowing scalable coordination across variable team sizes. To enforce motion realism while addressing the scarcity of cooperative HOI data, we further introduce a masked Adversarial Motion Prior (AMP) strategy that uses single-human reference motions while masking object-interacting body parts during training. The masked regions are then guided through task rewards to produce diverse and physically plausible cooperative behaviors. We evaluate TeamHOI on a challenging cooperative carrying task involving two to eight humanoid agents and varied object geometries. Finally, to promote stable carrying, we design a team-size- and shape-agnostic formation reward. TeamHOI achieves high success rates and demonstrates coherent cooperation across diverse configurations with a single policy. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2603_07988 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | TeamHOI: Learning a Unified Policy for Cooperative Human-Object Interactions with Any Team Size Lionar, Stefan Lee, Gim Hee Computer Vision and Pattern Recognition Graphics Multiagent Systems Robotics Physics-based humanoid control has achieved remarkable progress in enabling realistic and high-performing single-agent behaviors, yet extending these capabilities to cooperative human-object interaction (HOI) remains challenging. We present TeamHOI, a framework that enables a single decentralized policy to handle cooperative HOIs across any number of cooperating agents. Each agent operates using local observations while attending to other teammates through a Transformer-based policy network with teammate tokens, allowing scalable coordination across variable team sizes. To enforce motion realism while addressing the scarcity of cooperative HOI data, we further introduce a masked Adversarial Motion Prior (AMP) strategy that uses single-human reference motions while masking object-interacting body parts during training. The masked regions are then guided through task rewards to produce diverse and physically plausible cooperative behaviors. We evaluate TeamHOI on a challenging cooperative carrying task involving two to eight humanoid agents and varied object geometries. Finally, to promote stable carrying, we design a team-size- and shape-agnostic formation reward. TeamHOI achieves high success rates and demonstrates coherent cooperation across diverse configurations with a single policy. |
| title | TeamHOI: Learning a Unified Policy for Cooperative Human-Object Interactions with Any Team Size |
| topic | Computer Vision and Pattern Recognition Graphics Multiagent Systems Robotics |
| url | https://arxiv.org/abs/2603.07988 |