外观
论文arXiv 2610.1775015 天前
通过动态人体运动生成学习用于全身移动辅助的机器人策略
原文链接：Learning Robot Policies for Whole-Body Mobility Assistance via Dynamic Human Motion Generation（arXiv 2610.17750 · 发布日期：2026-10-13）
Learning Robot Policies for Whole-Body Mobility Assistance via Dynamic Human Motion Generation
提出基于动态人体运动生成的仿真框架，学习全身移动辅助策略，并在仿真STS、L&T及初步真实STS迁移中验证。
核心要点
- 全身移动辅助的人机数据采集成本高且安全敏感，仿真训练更具吸引力。
- 训练带对抗运动先验的人体策略，使其响应机器人动作生成真实受助者运动。
- 用人类自适应脚本控制器采集演示，训练3D Diffusion Policy输出移动操作臂全身动作。
- 策略在仿真中完成STS和L&T，STS经少量真实数据微调后初步实现Sim-to-Real迁移。
验证范围与局限：验证主要在仿真中的STS和L&T任务，真实世界仅报告STS经少量数据微调后的初步迁移。
英文摘要 (Abstract)
Robotic assistance for human mobility could benefit care recipients and reduce caregiver burden during physically demanding tasks such as Sit-to-Stand (STS) and Lift-and-Transfer (L&T). Learning robot policies for these whole-body assistive tasks is challenging: real-world data collection for human-robot interaction is costly and safety-critical, making simulation an attractive alternative. Prior work, however, typically treats the human as static or minimally responsive and thus fails to capture the cooperative nature of mobility assistance. We present a simulation-based framework for learning whole-body assistive robot policies. At its core is a human policy trained with an adversarial motion prior that produces realistic care-recipient motion in response to the robot's actions. A human-adaptive scripted controller interacts with this policy to collect diverse robot demonstrations at scale. From these demonstrations, we train 3D diffusion policies that map segmented human point clouds and robot joint positions to whole-body actions for a mobile manipulator, without relying on privileged human state at deployment. The resulting robot policies successfully perform both STS and L&T assistance in simulation. Preliminary experiments further demonstrate sim-to-real transfer for STS after fine-tuning on a small amount of real-world data. Videos are available on our project page: https://rchi-lab.github.io/human-gen-mobility-assistance/
作者：S Ban, Shohei Nagai, Qingyang Song, Hanxi Wan, Eric Zhao, Thomas Wang, Zackory Erickson
来源
本页事实对应的公开页面，以原文为准。