Xubin Tong

In meal delivery robot path planning, enabling the robot to find an optimal path that avoids obstacles within its workspace is a crucial step. Usually, the traditional ant colony optimization (ACO) suffers from slow convergence and blind search behavior in path planning, lacking dynamic obstacle avoidance functionality. Meanwhile, the dynamic window approach (DWA) tends to become entrapped in local optima during local path planning. It is therefore proposed that a hybrid path planning algorithm be developed, based on an improved IACO and DWA algorithm. To address issues such as aimless search, slow convergence speed, and low path smoothness in ACO, the concept of gravity from gravity search algorithms is introduced to direct the search. The acceleration of convergence is achieved through the implementation of path sorting and the administration of additional pheromone to superior paths in pheromone updates. The transition paths are optimized to address the issue of excessive path transitions in ACO, resulting in smoother paths. The key nodes of the obtained globally optimal path are used as local target points, serving as multiple target points for DWA operation to enable dynamic obstacle avoidance. Simulation results indicate that compared to the ACO, the IACO reduces path length by up to 30.03% and decreases path turns by up to 71.43% in four different static maps. In other static comparison experiments, the IACO demonstrated superior performance compared to the other tested algorithms. In dynamic experiments, the proposed fusion algorithm can plan smooth paths that successfully avoid both static and dynamic obstacles.

The motion control system of a lower-limb exoskeleton rehabilitation robot (LLERR) is designed to assist patients in lower-limb rehabilitation exercises. This research designed a motion controller for an LLERR-based on the Twin Delayed Deep Deterministic policy gradient (TD3) algorithm to control the lower-limb exoskeleton for gait training in a staircase environment. Commencing with the establishment of a mathematical model of the LLERR, the dynamics during its movement are systematically described. The TD3 algorithm is employed to plan the motion trajectory of the LLERR’s right-foot sole, and the target motion curve of the hip (knee) joint is deduced inversely to ensure adherence to human physiological principles during motion execution. The control strategy of the TD3 algorithm ensures that the movement of each joint of the LLERR is consistent with the target motion trajectory. The experimental results indicate that the trajectory tracking errors of the hip (knee) joints are all within 5°, confirming that the LLERR successfully assists patient in completing lower-limb rehabilitation training in a staircase environment. The primary contribution of this study is to propose a non-linear control strategy tailored for the staircase environment, enabling the planning and control of the lower-limb joint motions facilitated by the LLERR.