Bi-Level Image-Guided Ergodic Exploration with Applications to Planetary Rovers

TL;DR

This paper introduces a bi-level, image-guided ergodic exploration method for mobile robots, enhancing object detection and coverage efficiency, demonstrated on planetary rover geological surveys with real Mars images.

Contribution

It extends ergodic exploration with learned image classifiers and a bi-level optimization framework, improving object localization and exploration efficiency in planetary environments.

Findings

Enhanced rock formation localization over naive methods

Reduced exploration path length via bi-level optimization

Effective application to Mars rover geological surveys

Abstract

We present a method for image-guided exploration for mobile robotic systems. Our approach extends ergodic exploration methods, a recent exploration approach that prioritizes complete coverage of a space, with the use of a learned image classifier that automatically detects objects and updates an information map to guide further exploration and localization of objects. Additionally, to improve outcomes of the information collected by our robot's visual sensor, we present a decomposition of the ergodic optimization problem as bi-level coarse and fine solvers, which act respectively on the robot's body and the robot's visual sensor. Our approach is applied to geological survey and localization of rock formations for Mars rovers, with real images from Mars rovers used to train the image classifier. Results demonstrate 1) improved localization of rock formations compared to naive approaches while 2) minimizing the path length of the exploration through the bi-level exploration.