SixthSense: Task-Agnostic Proprioception-Only Whole-Body Wrench Estimation for Humanoids
Xingzhou Chen, Xiayan Xu, Yan Ning, Jiyu Yu, Yizheng Zhang, Siyi Qian, Lingzhu Xiang, Jiahao Chen, Yuquan Wang, Haodong Zhang, Ling Shi

TL;DR
SixthSense is a novel proprioception-only method for humanoid robots that accurately estimates contact events and wrenches without relying on external sensors, enhancing force-interaction capabilities.
Contribution
It introduces a task-agnostic, proprioception-based approach using conditional flow matching to infer contact information, overcoming limitations of existing analytical methods.
Findings
Achieved high accuracy in contact detection across various humanoid behaviors.
Enabled reliable force estimation solely from proprioception and IMU data.
Demonstrated effectiveness in collision detection and human-robot interaction scenarios.
Abstract
Humanoid robots are entering our physical world at scale, yet as oversized toys--good at singing and dancing, but short on force-interaction capabilities for practical tasks. Bridging this gap necessitates prioritizing reliable contact perception as a fundamental requirement. Estimating external wrenches in humanoids is complicated by floating-base dynamics and indeterminate contact locations. Existing analytical frameworks require idealistic assumptions and hard-to-obtain measurements, which are often unavailable in practice. To bridge this gap, we propose SixthSense, a task-agnostic approach that infers whole-body contact timing, location, and wrenches from proprioception and IMU data alone. To capture the multi-modal dynamics between unstructured contact inputs and the uncertain motion outputs, we employ conditional flow matching to tokenize proprioceptive histories and estimate a…
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
