Competitive and temporal Hebbian learning for production of robot trajectories

This paper proposes an unsupervised neural algorithm for trajectory production of a 6-DOF robotic arm. The model encodes these trajectories in a single training iteration by using competitive and temporal Hebbian learning rules and operates by producing the current and the next position for the robotic arm. In this paper we will focus on trajectories with at least one common point. These types of trajectories introduce some ambiguities, but even so, the neural algorithm is able to reproduce them accurately and unambiguously due to context units used as part of the input. In addition, the proposed model is shown to be fault-tolerant