IEEE International Conference on Robotics and Automation (ICRA) 2023
Received an outstanding planning paper award at ICRA 2023.
(As award papers, only 15 papers were selected among a competitive pool of 1,341 accepted submissions.)
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.