SixthSense:面向人类oid的无任务依赖的本体感知-only全身 wrench 估计
SixthSense: Proprioception-Only Whole-Body Wrench Estimation for Humanoids
AI总结:
本文提出SixthSense,一种基于本体感知和IMU数据的无任务依赖方法,用于估计人类oid的全身接触时间和位置及外部wrench,解决浮动物理动力学和不确定接触位置的难题。
摘要:
人类oid机器人正在进入我们的物理世界,但它们更像是 oversized toys,擅长唱歌跳舞,但在实际任务中缺乏足够的力交互能力。填补这一差距需要将可靠的接触感知作为基本要求。在人类oid中估计外部wrench是复杂的,因为存在浮动物理动力学和不确定的接触位置。现有的分析框架需要理想化的假设和难以获得的测量,这些在实践中往往不可用。为了解决这一问题,我们提出了SixthSense,一种无任务依赖的方法,通过本体感知和IMU数据推断全身接触时间、位置和wrench。为了捕捉无结构接触输入与不确定运动输出之间的多模态动力学,我们采用条件流匹配来对本体感知历史进行分词,并估计一个时空稀疏的接触事件流。SixthSense作为一个即插即用的感知模块,适用于碰撞检测、物理人机交互和力反馈遥控等应用。在站立、行走和全身运动跟踪策略上的实验展示了在多样化行为中的前所未有的性能。
英文摘要:
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.
机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。