跳到正文
研踪PaperTrail
← 研踪 PaperTrail

arXiv:2605.01427 · v2

SixthSense: Proprioception-Only Whole-Body Wrench Estimation for Humanoids

首次提交 2026-05-02 20:57
版本更新 2026-11-19 15:27
雷达观测 2026-11-20 19:58
arXiv ↗PDF ↗

摘要

Humanoid robots are entering the physical world at scale, yet are often criticized as oversized toys---good at dancing, but lacking the force-interaction capabilities for practical tasks. Reliable whole-body contact perception is difficult because floating-base dynamics make proprioceptive wrench recovery ambiguous, while model-based estimators require accurate dynamics and support-force inputs. We propose SixthSense, which uses conditional flow matching to model sparse spatiotemporal fields of link-wise contact gates and 6-D wrenches conditioned on proprioceptive and IMU histories. We train one estimator on pooled data from lying, standing, walking, and motion tracking. Across extensive simulation experiments, SixthSense outperforms learned and model-based baselines in overall contact estimation and remains robust to observation noise. We further establish a real-robot benchmark with our newly collected Unitree G1 dataset, where SixthSense achieves the strongest overall performance among learned estimators and requires approximately 50\,ms per inference. Controlled ambiguity experiments show that its samples recover multiple dynamically plausible contact modes with improved local physical consistency. We finally deploy SixthSense for collision detection and contact-triggered physical human--robot interaction.

AI 论文解读

基于摘要 · 非全文审阅

此版本尚未生成 AI 解读。解读由后台任务生成并按论文版本保存,登录后共享已有结果。

版本差异

本站首次收录为 v2,暂无更早版本可对照。

观测到的版本

相邻记录可能跳过中间版本;首次发现 v2 及以上也会标为版本更新。

v2 · 2026-11-19 15:27 · 最新观测版本

SixthSense: Proprioception-Only Whole-Body Wrench Estimation for Humanoids

Humanoid robots are entering the physical world at scale, yet are often criticized as oversized toys---good at dancing, but lacking the force-interaction capabilities for practical tasks. Reliable whole-body contact perception is difficult because floating-base dynamics make proprioceptive wrench recovery ambiguous, while model-based estimators require accurate dynamics and support-force inputs. We propose SixthSense, which uses conditional flow matching to model sparse spatiotemporal fields of link-wise contact gates and 6-D wrenches conditioned on proprioceptive and IMU histories. We train one estimator on pooled data from lying, standing, walking, and motion tracking. Across extensive simulation experiments, SixthSense outperforms learned and model-based baselines in overall contact estimation and remains robust to observation noise. We further establish a real-robot benchmark with our newly collected Unitree G1 dataset, where SixthSense achieves the strongest overall performance among learned estimators and requires approximately 50\,ms per inference. Controlled ambiguity experiments show that its samples recover multiple dynamically plausible contact modes with improved local physical consistency. We finally deploy SixthSense for collision detection and contact-triggered physical human--robot interaction.

查看此版本解读 →查看此版本原文 ↗