Dual-Loop Control Framework of a Self-Balancing Lower-Limb Exoskeleton for Assisted Walking

This article describes a dual-loop control framework of self-balancing lower-limb exoskeletons (SBLLEs) to estimate deformations and to stabilize SBLLEs for assisted walking tasks conducted on wearers with diverse physical parameters. First, considering the nonlinear time-varying characteristic of deformation and the time dependency and periodic nature of walking motion, a bidirectional long short-term memory (Bi-LSTM) neural network is utilized to estimate multiple deformations. In particular, the force sensor and Bi-LSTM-based deformation estimator (FBDE) loop are used to estimate and compensate for the deformation based on the force and moment signals. Second, a physical parameter-independent controller (PPIC) based on centroidal dynamics is proposed to stabilize exoskeletons that can accommodate wearers with varying physical parameters. The PPIC loop is also based on force and moment signals, indicating that only 6-D force sensors are necessary to estimate deformation and stabilize SBLLEs. Finally, a series of experiments is conducted on three subjects with varying physical parameters to validate the effectiveness of the dual-loop control framework. The results of walking experiments show that the dual-loop control framework can estimate deformation and stabilize the SBLLE during walking under different loads.