We introduce SoftAct, a framework for teaching soft robot hands to perform human-like manipulation skills by explicitly reasoning about contact forces. Leveraging immersive virtual reality, our system captures rich human demonstrations, including hand kinematics, object motion, dense contact patches, and detailed contact force information. Unlike conventional approaches that retarget human joint trajectories, SoftAct employs a two-stage, force-aware retargeting algorithm. The first stage attributes demonstrated contact forces to individual human fingers and allocates robot fingers proportionally, establishing a force-balanced mapping between human and robot hands. The second stage performs online retargeting by combining baseline end-effector pose tracking with geodesic-weighted contact refinements, using contact geometry and force magnitude to adjust robot fingertip targets in real time. This formulation enables soft robotic hands to reproduce the functional intent of human demonstrations while naturally accommodating extreme embodiment mismatch and nonlinear compliance. We evaluate SoftAct on a suite of contact-rich manipulation tasks using a custom non-anthropomorphic pneumatic soft robot hand. SoftAct's controller reduces fingertip trajectory tracking RMSE by up to 55 percent and reduces tracking variance by up to 69 percent compared to kinematic and learning-based baselines. At the policy level, SoftAct achieves consistently higher success in zero-shot real-world deployment and in simulation. These results demonstrate that explicitly modeling contact geometry and force distribution is essential for effective skill transfer to soft robotic hands, and cannot be recovered through kinematic imitation alone. Project videos and additional details are available at https://soft-act.github.io/.

翻译：我们提出SoftAct框架，通过显式推理接触力来教软体机器人手执行类人操作技能。借助沉浸式虚拟现实，我们的系统捕获丰富的演示数据，包括手部运动学、物体运动、密集接触区域和详细的接触力信息。与传统方法仅重定向人类关节轨迹不同，SoftAct采用两阶段力感知重定向算法：第一阶段将演示接触力归因于单个手指，并按比例分配机器人手指，建立人与机器人手之间的力平衡映射；第二阶段通过基线末端执行器姿态跟踪与测地线加权接触修正相结合，利用接触几何和力幅值实时调整机器人指尖目标。该公式使软体机器人手能够复现人类演示的功能意图，同时自然适应极端本体差异和非线性柔顺性。我们在定制非拟人化气动软体机器人手上对一系列接触密集型操作任务进行SoftAct评估。与运动学和学习基线相比，SoftAct控制器将指尖轨迹跟踪均方根误差降低高达55%，跟踪方差降低高达69%。在策略层面，SoftAct在零样本真实世界部署和仿真中均取得更高成功率。结果表明，显式建模接触几何和力分布对软体机器人手技能迁移至关重要，且无法通过单纯运动学模仿实现。项目视频及更多详情见https://soft-act.github.io/。