辅助护理中接触丰富型人机交互的物理一致性基准
A Physics-Consistent Benchmark for Contact-Rich Human-Robot Interaction in Assistive Care
浏览论文内容
中文总结 AI 辅助
该研究提出用于机器人辅助洗澡的接触丰富型人机交互物理一致性基准，经实验发现仅任务完成不代表有效接触，需对辅助机器人策略做物理感知筛选。
中文摘要 AI 辅助
传统任务级评估仅关注机器人策略是否完成指定动作，但会遗漏仅在与人类物理接触时才会出现的故障，这一局限在接触丰富型辅助任务中尤为关键，此类任务的有效评估需要具备物理响应能力的人类、超越任务成功的交互质量评估，以及无漏洞的观察者评分协议。我们提出一种接触丰富型人机交互的物理一致性基准，以机器人辅助洗澡为实例实现。该基准结合了可变形、被动响应的人类模型、感知物理的评分指标（除任务级成功外），以及冻结的仅视觉/仅评分者评估协议。为确立物理有效性，我们针对Franka阻抗控制器对医疗护理人体模型施加的力-压痕测量值，对区域级模拟响应进行校准。在采用冻结T1-T7协议、每种方法各140次运行的情况下，LLM增强型状态机（State Machine）的任务成功率达72.9%，但经正确区域和力安全筛选后降至56.4%；VoxPoser产生的接触更轻柔、更稳定，但仅完成27.9%的试验；零样本pi0.5的任务成功率仅为0.7%，无正确区域或安全门控成功案例。这些结果表明，仅任务完成不意味着物理上有效的接触，需在部署接触丰富型辅助机器人策略前进行物理感知筛选。
英文摘要
Conventional task-level evaluation asks whether a robot policy completes a specified action, but can miss failures that emerge only during physical human contact. This limitation is critical in contact-rich assistive tasks, where meaningful evaluation requires a physically responsive human, interaction-quality assessment beyond task success, and a leak-free observer-scorer protocol. We introduce a physics-consistent benchmark for contact-rich human-robot interaction, instantiated in robot-assisted bathing. The benchmark combines a deformable, passively responding human, physics-aware scores alongside task-level success, and a frozen vision-only / scorer-only evaluation protocol. To establish physical validity, region-wise simulated responses are calibrated against force-indentation measurements from Franka impedance pushes on a medical-care manikin. Under a frozen T1-T7 protocol with 140 runs per method, an LLM-augmented state machine (State Machine) achieves 72.9% task success but drops to 56.4% after correct-region and force-safety screening; VoxPoser produces lighter and more stable contact but completes only 27.9% of trials; and zero-shot pi0.5 achieves 0.7% task success with no correct-region or safety-gated successes. These results show that task completion alone does not imply physically valid contact and motivate physics-aware screening before deployment of contact-rich assistive robot policies.
发表机构
- School of Mechanical and Robotics Engineering, Tongji University（同济大学机械与机器人工程学院）
- Centre for Advanced Robotics Technology Innovation, Nanyang Technological University（南洋理工大学先进机器人技术创新中心）
- College of Electronic and Information Engineering, Tongji University（同济大学电子与信息工程学院）
机构由 AI 辅助整理，请以论文原文为准。
