Learning-based Initialization of Trajectory Optimization for Path-following Problems of Redundant Manipulators

TL;DR

This paper introduces a learning-based method to generate high-quality initial trajectories for redundant manipulators, significantly improving the efficiency and effectiveness of trajectory optimization in path-following tasks.

Contribution

It proposes a novel example-guided reinforcement learning approach with a null-space imitation reward to produce feasible initial trajectories, enhancing optimization performance.

Findings

Improved optimality and efficiency in trajectory optimization.

Enhanced applicability demonstrated in simulation and real-world experiments.

Significant reduction in time to generate initial trajectories.

Abstract

Trajectory optimization (TO) is an efficient tool to generate a redundant manipulator's joint trajectory following a 6-dimensional Cartesian path. The optimization performance largely depends on the quality of initial trajectories. However, the selection of a high-quality initial trajectory is non-trivial and requires a considerable time budget due to the extremely large space of the solution trajectories and the lack of prior knowledge about task constraints in configuration space. To alleviate the issue, we present a learning-based initial trajectory generation method that generates high-quality initial trajectories in a short time budget by adopting example-guided reinforcement learning. In addition, we suggest a null-space projected imitation reward to consider null-space constraints by efficiently learning kinematically feasible motion captured in expert demonstrations. Our statistical evaluation in simulation shows the improved optimality, efficiency, and applicability of TO when we plug in our method's output, compared with three other baselines. We also show the performance improvement and feasibility via real-world experiments with a seven-degree-of-freedom manipulator.