Lower limb amputations and neuromuscular impairments severely restrict mobility, necessitating advancements beyond conventional prosthetics. Motorized bionic limbs offer promise, but their utility depends on mimicking the evolving synergy of human movement in various settings. In this context, we present a novel model for bionic prostheses' application that leverages camera-based motion capture and wearable sensor data, to learn the synergistic coupling of the lower limbs during human locomotion, empowering it to infer the kinematic behavior of a missing lower limb across varied tasks, such as climbing inclines and stairs. We propose a model that can multitask, adapt continually, anticipate movements, and refine. The core of our method lies in an approach which we call -- multitask prospective rehearsal -- that anticipates and synthesizes future movements based on the previous prediction and employs a corrective mechanism for subsequent predictions. We design an evolving architecture that merges lightweight, task-specific modules on a shared backbone, ensuring both specificity and scalability. We empirically validate our model against various baselines using real-world human gait datasets, including experiments with transtibial amputees, which encompass a broad spectrum of locomotion tasks. The results show that our approach consistently outperforms baseline models, particularly under scenarios affected by distributional shifts, adversarial perturbations, and noise.

翻译：下肢截肢和神经肌肉损伤严重限制了行动能力，亟需超越传统假肢的革新方案。动力仿生肢体展现出潜力，但其效用取决于能否模拟人类在各种场景下不断演化的运动协同性。在此背景下，我们提出一种新型仿生假肢应用模型，该模型利用基于摄像头的动作捕捉和可穿戴传感器数据，学习人类行走过程中下肢的协同耦合关系，使其能够推断缺失下肢在不同任务（如爬坡和上楼梯）中的运动学行为。我们提出的模型具备多任务处理、持续适应、运动预测和自我优化能力。该方法的核心是一种被命名为"多任务前瞻性复现"的技术——该技术基于先前预测来预判和合成未来运动，并通过矫正机制优化后续预测。我们设计了一种渐进式架构，在共享主干网络上集成轻量级任务特定模块，兼顾特异性和可扩展性。基于真实人体步态数据集（包括针对胫骨截肢者的实验，涵盖广泛运动任务），我们通过与多种基线模型的实证对比验证了模型性能。结果显示，我们的方法在分布偏移、对抗扰动和噪声干扰等场景下始终优于基线模型。