研究人与人、人与机器人协作搬东西时的触觉沟通，发现人类协作更流畅。
Haptic Communication in Human-Human and Human-Robot Co-Manipulation
- 用低成本惯性传感器追踪共同搬运物体的运动轨迹，比较人与人、人与机器人的协作差异。
- 人-人协作在流畅性和准确性上显著优于人-机器人协作，客观数据和主观反馈一致。
- 揭示了机器人需具备类人触觉交互能力，以提升物理任务中的协作表现。
当两人共同搬运物体时，必须通过运动计划进行沟通。这种协作部分通过被搬运物体自身的运动实现，我们称之为“触觉通信”。本研究记录了人类二人组在一人主导动作而另一人未知计划的情况下共同搬运物体的过程，随后同一批参与者与机器人协作完成相同任务。通过低成本惯性测量单元（IMU）追踪共享物体的运动轨迹，可直接对比人类-人类与人类-机器人协作的表现。研究还通过研究内及研究后问卷收集参与者反馈，结果表明人类协作在流畅性上显著更优；对IMU数据的分析也验证了不同条件下的运动特征存在客观差异。主客观指标的差异表明，未来应研究如何让机器人具备发送和接收类人触觉信号的能力，从而提升其在物理任务中的协作性能。
原文摘要 · Abstract (English)
When a human dyad jointly manipulates an object, they must communicate about their intended motion plans. Some of that collaboration is achieved through the motion of the manipulated object itself, which we call "haptic communication." In this work, we captured the motion of human-human dyads moving an object together with one participant leading a motion plan about which the follower is uninformed. We then captured the same human participants manipulating the same object with a robot collaborator. By tracking the motion of the shared object using a low-cost IMU, we can directly compare human-human shared manipulation to the motion of those same participants interacting with the robot. Intra-study and post-study questionnaires provided participant feedback on the collaborations, indicating that the human-human collaborations are significantly more fluent, and analysis of the IMU data indicates that it captures objective differences in the motion profiles of the conditions. The differences in objective and subjective measures of accuracy and fluency between the human-human and human-robot trials motivate future research into improving robot assistants for physical tasks by enabling them to send and receive anthropomorphic haptic signals.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。