A Recurrent Neural Network Based Bicriteria Repetitive Motion Collision Avoidance Scheme for Motion Planning of Dual Redundant Manipulators

To achieve low joint-angle drift and avoid mutual collision between dual redundant manipulators (DRMs) when they are doing collaboration works, a recurrent neural network based bicriteria repetitive motion collision avoidance (BRMCA) scheme is proposed for motion planning of DRMs. By designing a combined optimization objective encompassing both repetitive motion criterion and collision avoidance criterion, the BRMCA scheme has larger feasible region and less constraint contradiction issues compared with traditional inequality constraints based method. Furthermore, by incorporating velocity-level kinematic model and physical limits of DRMs into the scheme, a time varying quadratic programming (TVQP) problem is formulated. The linear variational inequality-based primal-dual neural network (LVI-PDNN) is used to solve the proposed scheme due to the high accuracy and low computation complexity. Finally, through comparison simulations of tracking Circle-shape and C-shape trajectories between BRMCA scheme and minimum velocity norm (MVN) scheme, it exhibits that the proposed BRMCA scheme can achieve low joint-angle drift, collision avoidance and high tracking accuracy when DRMs are doing cooperative tasks.

I. Introduction

In recent years, research on robot manipulators has been rapidly growing in various fields, such as medical apparatus [1], manufacturing industry [2] and humanoid robots [3], [4]. Redundant manipulators possess higher flexibility compared with non-redundant manipulators due to their redundancy on degrees-of-freedoms (DOFs), which guarantees that they can finish primary tasks of the end-effector as well as subtasks.