Real-time collision-free path planning of robot manipulators using neural network approaches

In this paper, a novel neural network approach to real-time collision-free path planning of robot manipulators in a nonstationary environment is proposed, which is based on a biologically inspired neural network model for dynamic trajectory generation of a point mobile robot. The state space of the proposed neural network is the joint space of the robot manipulators, where the dynamics of each neuron is characterized by a shunting equation or an additive equation. The real-time robot path is planned through the varying neural activity landscape that represents the dynamic environment. The proposed model for robot path planning with safety consideration is capable of planning a real-time "comfortable" path without suffering from the "too close" nor "too far" problems. The model algorithm is computationally efficient. The computational complexity is linearly dependent on the neural network size. The effectiveness and efficiency are demonstrated through simulation studies.