基于强化学习的连续型机械臂自适应跟踪控制

针对空间主动碎片清除操作中连续型三臂节机器人系统跟踪问题，提出一种基于强化学习的自适应滑模控制算法。基于数据驱动的建模方法，采用BP神经网络对三臂节连续型机械臂进行建模，并作为预测模型指导强化学习实时调节所提出滑模控制器的控制参数，从而实现连续型机器人运动的实时跟踪控制。仿真结果表明：提出的数据驱动的预测模型对随机轨迹预测的相对误差保持在\pm \mathrm{1}\mathrm{\%}以内，能够高精度地反映系统动态特性。对比固定参数的滑模控制器，提出的自适应控制器在保证系统达到控制目标的同时具有更低的超调量和更短的调节时间，表现出更好的控制效果。

Reinforcement-learning-based Adaptive Tracking Control for a Space Continuum Robot Based on Reinforcement Learning

Aiming at the tracking control for three-arm space continuum robot in space active debris removal manipulation, an adaptive sliding mode control algorithm based on deep reinforcement learning is proposed. Through BP network, a data-driven dynamic model is developed as the predictive model to guide the reinforcement learning to adjust the sliding mode controller's parameters online, and finally realize a real-time tracking control. Simulation results show that the proposed data-driven predictive model can accurately predict the robot's dynamic characteristics with the relative error within \pm \mathrm{1}\mathrm{\%} to random trajectories. Compared with the fixed-parameter sliding mode controller, the proposed adaptive controller has a lower overshoot and shorter settling time and can achieve a better tracking performance.