让机器人在受力时自动保持平衡，提升抓取能力。
FAME: Force-Adaptive RL for Expanding the Manipulation Envelope of a Full-Scale Humanoid
- 用强化学习让机器人根据手部受力和身体姿态动态调整平衡策略。
- 仿真中站立成功率达73.84%，远超基线的29.44%~51.40%。
- 无需腕部传感器，可直接部署到真实人形机器人上。
在双臂操作中，外部手部作用力会通过运动链传递并限制可行操作范围，维持平衡至关重要。我们提出FAME——一种基于力自适应强化学习的框架，其策略通过编码上肢关节配置与双手交互力的潜在上下文进行条件化。训练时，我们在每只手上施加球面采样的三维扰动力，并引入上肢姿态课程，使策略暴露于连续变化手臂构型下的操作扰动中。部署时，交互力由机器人动力学估计并输入相同编码器，实现无需腕部力/扭矩传感器的在线适应。在五个固定臂位、随机手力及底座高度下，FAME平均站立成功率提升至73.84%，优于仅使用课程训练的基线（51.40%）和基础策略（29.44%）。我们进一步将学习策略部署于全尺寸Unitree H12人形机器人，在不对称单臂负载和对称双臂负载等典型场景中验证了鲁棒性。代码与视频见https://fame10.github.io/Fame/
原文摘要 · Abstract (English)
Maintaining balance under external hand forces is critical for humanoid bimanual manipulation, where interaction forces propagate through the kinematic chain and constrain the feasible manipulation envelope. We propose \textbf{FAME}, a force-adaptive reinforcement learning framework that conditions a standing policy on a learned latent context encoding upper-body joint configuration and bimanual interaction forces. During training, we apply diverse, spherically sampled 3D forces on each hand to inject disturbances in simulation together with an upper-body pose curriculum, exposing the policy to manipulation-induced perturbations across continuously varying arm configurations. At deployment, interaction forces are estimated from the robot dynamics and fed to the same encoder, enabling online adaptation without wrist force/torque sensors. In simulation across five fixed arm configurations with randomized hand forces and commanded base heights, FAME improves mean standing success to 73.84%, compared to 51.40% for the curriculum-only baseline and 29.44% for the base policy. We further deploy the learned policy on a full-scale Unitree H12 humanoid and evaluate robustness in representative load-interaction scenarios, including asymmetric single-arm load and symmetric bimanual load. Code and videos are available on https://fame10.github.io/Fame/
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。