Constrained motion planning of free-float dual-arm space manipulator via deep reinforcement learning

Space manipulator has complex kinetic and dynamic properties due to its free-float base. Moreover, the motion planning of a dual-arm manipulator is even more challenging due to the extra motion constraints between arms. To this end, a deep reinforcement learning based motion planning method is proposed to solve the complex constrained motion planning problem of free-floating dual-arm space manipulator. Firstly, the Generalized Jacobian Matrix is used to establish the kinematic model of the manipulator system. Based on this model, the Deep Deterministic Policy Gradients algorithm is adopted to realize the complex constrained motion planning. Meanwhile, the self-collision avoidance and velocity constraint of the end-effector are taken into consideration in the planning process to improve the robustness of the algorithm. Finally, trajectories of individual joint are obtained under both motionless and spinning scenarios, and simulation tests are conducted to demonstrate the performance of the proposed planning methods. (c) 2020 Elsevier Masson SAS. All rights reserved.