A Bi-Criteria Obstacle Avoidance Scheme Synthesized by Time-Varying Penalty Strategy Neural Network for Mobile Parallel Manipulators

In order to enable the mobile parallel manipulator to avoid obstacles and achieve repetitive motion as well as avoid velocity spikes, a bi-criteria obstacle avoidance scheme synthesized by time-varying penalty strategy (BCOA-TVPS) neural network is proposed and designed. To do so, first, the bi-criteria are composed of repetitive motion criterion and infinite norm velocity minimization criterion, and the constraints consider the vector-based obstacle avoidance constraints. Second, the bi-criteria obstacle avoidance scheme is reformulated as a constrained time-varying quadratic programming (QP) problem. Third, a time-varying penalty strategy (TVPS) neural network is adopted to solve the QP problem. Finally, two kinds of trajectory tracking experiments verify the effectiveness and applicability of the proposed BCOA-TVPS scheme.