Robotic devices hold promise for aiding patients in orthopedic rehabilitation. However, current robotic-assisted physiotherapy methods struggle including biomechanical metrics in their control algorithms, crucial for safe and effective therapy. This paper introduces BATON, a Biomechanics-Aware Trajectory Optimization approach to robotic Navigation of human musculoskeletal loads. The method integrates a high-fidelity musculoskeletal model of the human shoulder into real-time control of robot-patient interaction during rotator cuff tendon rehabilitation. We extract skeletal dynamics and tendon loading information from an OpenSim shoulder model to solve an optimal control problem, generating strain-minimizing trajectories. Trajectories were realized on a healthy subject by an impedance-controlled robot while estimating the state of the subject's shoulder. Target poses were prescribed to design personalized rehabilitation across a wide range of shoulder motion avoiding high-strain areas. BATON was designed with real-time capabilities, enabling continuous trajectory replanning to address unforeseen variations in tendon strain, such as those from changing muscle activation of the subject.

翻译：机器人设备在辅助患者进行骨科康复方面展现出巨大潜力。然而，当前的机器人辅助物理治疗方法难以在其控制算法中纳入生物力学指标，而这对于安全有效的治疗至关重要。本文提出BATON，一种用于人体肌肉骨骼负荷机器人导航的生物力学感知轨迹优化方法。该方法将高保真的人体肩部肌肉骨骼模型集成到肩袖肌腱康复过程中机器人-患者交互的实时控制中。我们从OpenSim肩部模型中提取骨骼动力学和肌腱负荷信息，以求解最优控制问题，生成应变最小化的轨迹。通过阻抗控制机器人对健康受试者实现了这些轨迹，同时估算了受试者肩部的状态。通过设定目标姿势来设计个性化的康复方案，覆盖广泛的肩部运动范围并避开高应变区域。BATON设计具备实时处理能力，能够持续重新规划轨迹，以应对肌腱应力的意外变化，例如由受试者肌肉激活改变引起的变化。