Benchmarking local motion planners for navigation of mobile manipulators

TL;DR

This paper introduces a simulation framework for benchmarking local motion planners in mobile manipulators, enabling fair comparison of their performance in generating feasible trajectories under consistent conditions.

Contribution

It presents a versatile benchmarking framework compatible with ROS, allowing evaluation of local planners like DWA and TEB under standardized metrics.

Findings

DWA and TEB are effectively evaluated using the proposed metrics.

The framework facilitates comparison of local planners in a controlled environment.

Software is adaptable to any ROS-based local planner.

Abstract

There are various trajectory planners for mobile manipulators. It is often challenging to compare their performance under similar circumstances due to differences in hardware, dissimilarity of tasks and objectives, as well as uncertainties in measurements and operating environments. In this paper, we propose a simulation framework to evaluate the performance of the local trajectory planners to generate smooth, and dynamically and kinematically feasible trajectories for mobile manipulators in the same environment. We focus on local planners as they are key components that provide smooth trajectories while carrying a load, react to dynamic obstacles, and avoid collisions. We evaluate two prominent local trajectory planners, Dynamic-Window Approach (DWA) and Time Elastic Band (TEB) using the metrics that we introduce. Moreover, our software solution is applicable to any other local planners used in the Robot Operating System (ROS) framework, without additional programming effort.