Lower-limb exoskeletons have the potential to transform the way we move^{1,2,3,4,5,6,7,8,9,10,11,12,13,14}, but current state-of-the-art controllers cannot accommodate the rich set of possible human behaviours that range from cyclic and predictable to transitory and unstructured. We introduce a task-agnostic controller that assists the user on the basis of instantaneous estimates of lower-limb biological joint moments from a deep neural network. By estimating both hip and knee moments in-the-loop, our approach provided multi-joint, coordinated assistance through our autonomous, clothing-integrated exoskeleton. When deployed during 28 activities, spanning cyclic locomotion to unstructured tasks (for example, passive meandering and high-speed lateral cutting), the network accurately estimated hip and knee moments with an average R² of 0.83 relative to ground truth. Further, our approach significantly outperformed a best-case task classifier-based method constructed from splines and impedance parameters. When tested on ten activities (including level walking, running, lifting a 25 lb (roughly 11 kg) weight and lunging), our controller significantly reduced user energetics (metabolic cost or lower-limb biological joint work depending on the task) relative to the zero torque condition, ranging from 5.3 to 19.7%, without any manual controller modifications among activities. Thus, this task-agnostic controller can enable exoskeletons to aid users across a broad spectrum of human activities, a necessity for real-world viability.

下肢外骨骼有可能改变我们的移动方式^{1,2,3,4,5,6,7,8,9,10,11,12,13,14}，但当前最先进的控制器无法容纳丰富的可能人类行为，从循环和可预测的到暂时的和非结构化的。我们引入了一个与任务无关的控制器，它根据深度神经网络对下肢生物关节矩的瞬时估计来协助用户。通过估计循环中的髋关节和膝关节力矩，我们的方法通过我们的自主、与服装集成的外骨骼提供了多关节、协调的帮助。当部署在 28 项活动中时，从循环运动到非结构化任务（例如，被动蜿蜒和高速横向切割），该网络准确估计了髋关节和膝关节力矩，相对于地面实况的平均 R² 为 0.83。此外，我们的方法明显优于由样条和阻抗参数构建的基于任务分类器的最佳方法。当对 10 项活动（包括水平行走、跑步、举起 25 磅（约 11 公斤）的重量和弓步）进行测试时，相对于零扭矩条件，我们的控制器显着降低了用户能量（代谢成本或下肢生物关节工作，具体取决于任务），范围从 5.3% 到 19.7%，活动之间没有任何手动控制器修改。因此，这种与任务无关的控制器可以使外骨骼在广泛的人类活动中为用户提供帮助，这是现实世界生存的必要条件。