Image-Based Trajectory Tracking Through Unknown Environments Without Absolute Positioning

This article describes a stereo image-based visual servoing (VS) system for trajectory tracking by a nonholonomic robot without externally derived pose information nor a known visual map of the environment. It is called trajectory servoing (TS). The critical component is a feature-based, indirect simultaneous localization and mapping (SLAM) method to provide a pool of available features with estimated depth, so that they may be propagated forward in time to generate image feature trajectories for VS. Short and long distance experiments show the benefits of TS for navigating unknown areas without absolute positioning. Empirically, TS has better trajectory tracking performance than pose-based feedback when both rely on the same underlying SLAM system.

Automated summary

This article presents a stereo image-based visual servoing system for trajectory tracking of a nonholonomic robot. The system does not require externally derived pose information or a known visual map of the environment. It utilizes a feature-based, indirect SLAM method to provide a pool of available features with estimated depth, which are then propagated forward in time to generate image feature trajectories for visual servoing. Experimental results demonstrate the benefits of the system for navigating unknown areas without absolute positioning.