ContactMimic: Humanoid Object Interaction via Contact Control

ContactMimic: Humanoid Object Interaction via Contact Control

|Authors: Xinyao Li, Xialin He, Runpei Dong, Saurabh Gupta

|Venue: arXiv preprint | Year: 2026

|arXiv: 2607.08742v1

Abstract

Keypoint tracking alone is insufficient for object interaction tasks such as sitting on a chair, wiping a board, or pushing furniture, where the robot can reach the correct pose without making meaningful physical contact with the object. We present CONTACTMIMIC, a learning framework that tracks explicit partlevel binary contact commands alongside keypoint trajectories. CONTACTMIMIC is made possible through the use of contact-following rewards and a trajectory augmentation scheme aimed at breaking the correlations between keypoint trajectories and contact labels. The resulting policy successfully decouples contact behavior from keypoint geometry, and achieves precise physical contact as well as contact-controllability (produce or suppress contact during deployment as desired). Simulation experiments across 10 diverse human-object interaction motions confirm that CONTACTMIMIC exhibits contact controllability that enables it to complete manipulation tasks without task-specific rewards, while also outperforming keypoint-only trackers on contact-relevant tasks. Ablations confirm the necessity of the proposed trajectory augmentation scheme and sim2real deployment validates contact controllability in the real world across 5 different motions. Video results are available on https://lixinyao11.github.io/contactmimic-page/.

Key Contributions

• Keypoint tracking alone is insufficient for object interaction tasks such as sitting on a chair, …
• We present CONTACTMIMIC, a learning framework that tracks explicit partlevel binary contact comma…
• CONTACTMIMIC is made possible through the use of contact-following rewards and a trajectory augme…
• The resulting policy successfully decouples contact behavior from keypoint geometry, and achieves…
• Simulation experiments across 10 diverse human-object interaction motions confirm that CONTACTMIM…

Topics

• manipulation
• reinforcement-learning
• control

Code & Data

No code repository linked in paper metadata.

BibTeX

@article{Li2026_260708742v1,
  title     = {ContactMimic: Humanoid Object Interaction via Contact Control},
  author    = {Xinyao Li and Xialin He and Runpei Dong and Saurabh Gupta},
  year      = {2026},
  eprint    = {2607.08742v1},
  archivePrefix = {arXiv},
  primaryClass  = {cs.RO},
  url       = {https://arxiv.org/abs/2607.08742v1}
}