Real-Time Generation of Near-Minimum-Energy Trajectories via Constraint-Informed Residual Learning

TL;DR

This paper introduces a residual learning-based method for real-time near-minimum-energy trajectory generation in industrial robotics, significantly reducing computation time while maintaining high energy efficiency.

Contribution

It presents a novel residual learning paradigm that efficiently approximates optimal control solutions for manipulators, enabling real-time energy-efficient trajectory planning.

Findings

Achieves 87.3% of optimal energy performance near training data

Maintains 50.8% performance far from training data

Operates two to three orders of magnitude faster than traditional methods

Abstract

Industrial robotics demands significant energy to operate, making energy-reduction methodologies increasingly important. Strategies for planning minimum-energy trajectories typically involve solving nonlinear optimal control problems (OCPs), which rarely cope with real-time requirements. In this paper, we propose a paradigm for generating near minimum-energy trajectories for manipulators by learning from optimal solutions. Our paradigm leverages a residual learning approach, which embeds boundary conditions while focusing on learning only the adjustments needed to steer a standard solution to an optimal one. Compared to a computationally expensive OCP-based planner, our paradigm achieves 87.3% of the performance near the training dataset and 50.8% far from the dataset, while being two to three orders of magnitude faster.