Nuero-fuzzy multi-objective trajectory planning of redundant manipulators

In this paper, the problem of multi-objective trajectory planning is studied for redundant planar serial manipulators using a data-driven hybrid neuro-fuzzy system. A first pre-processing step involves an offline planning generating a large dataset of multi-objective trajectories, covering mostly the robot workspace. The optimized criteria are travelling time, consumed energy, and singularity avoidance. The offline planning is initialized through a cycloidal minimum time parameterized trajectory in joint space. This trajectory is then optimized using an augmented Lagrangian technique. The outcomes of this pre-processing step allow building a Tsukamoto neuro-fuzzy inference system to learn and capture the robot multi-objective dynamic behavior. Once this system is trained and optimized, it is used in a generalization phase to achieve online planning. Simulation results showing the effectiveness of the proposal are presented and discussed.