用视觉强化学习让机器人轻柔抓取易损物品，无需复杂传感器
Sim-to-Real Gentle Manipulation of Deformable and Fragile Objects with Stress-Guided Reinforcement Learning
- 引入应力惩罚奖励，让机器人主动减少对脆弱物体的挤压
- 仿真训练后零样本迁移至真实世界，抓豆腐时应力降低36.5%
- 通过刚性到柔性物体渐进式训练，提升泛化能力
机器人抓取易变形和易碎物品面临巨大挑战，过度应力会导致不可逆损伤。现有方法依赖精确物体模型或专用传感器与夹爪，增加复杂性且泛化能力差。为此，我们提出一种基于视觉的强化学习方法，通过引入应力惩罚奖励显式抑制损伤。为加速学习，采用离线演示并设计从刚性体到柔性体的渐进式训练课程。在仿真与真实场景中评估表明，仿真中训练的策略可零样本迁移到真实世界，完成豆腐抓取与推动等任务。结果表明，所学策略具备损伤感知的轻柔操作行为，相比普通强化学习策略，对脆弱物体施加的应力降低36.5%的同时达成任务目标。
原文摘要 · Abstract (English)
Robotic manipulation of deformable and fragile objects presents significant challenges, as excessive stress can lead to irreversible damage to the object. While existing solutions rely on accurate object models or specialized sensors and grippers, this adds complexity and often lacks generalization. To address this problem, we present a vision-based reinforcement learning approach that incorporates a stress-penalized reward to discourage damage to the object explicitly. In addition, to bootstrap learning, we incorporate offline demonstrations as well as a designed curriculum progressing from rigid proxies to deformables. We evaluate the proposed method in both simulated and real-world scenarios, showing that the policy learned in simulation can be transferred to the real world in a zero-shot manner, performing tasks such as picking up and pushing tofu. Our results show that the learned policies exhibit a damage-aware, gentle manipulation behavior, demonstrating their effectiveness by decreasing the stress applied to fragile objects by 36.5% while achieving the task goals, compared to vanilla RL policies.
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。