CUTE-Planner: Confidence-aware Uneven Terrain Exploration Planner

TL;DR

This paper introduces CUTE-Planner, a novel exploration framework for planetary robots that manages terrain uncertainty and enhances safety by integrating confidence-aware planning and adaptive updates, significantly reducing elevation uncertainty and improving mission success.

Contribution

The paper presents a new confidence-aware exploration framework that combines safe path planning, adaptive confidence updates, and prioritization of low-confidence regions, addressing limitations of existing methods.

Findings

Achieved 69% reduction in elevation uncertainty compared to baseline.

Attained 100% mission success rate in simulated lunar experiments.

Improved exploration safety and map reliability over traditional methods.

Abstract

Planetary exploration robots must navigate uneven terrain while building reliable maps for space missions. However, most existing methods incorporate traversability constraints but may not handle high uncertainty in elevation estimates near complex features like craters, do not consider exploration strategies for uncertainty reduction, and typically fail to address how elevation uncertainty affects navigation safety and map quality. To address the problems, we propose a framework integrating safe path generation, adaptive confidence updates, and confidence-aware exploration strategies. Using Kalman-based elevation estimation, our approach generates terrain traversability and confidence scores, then incorporates them into Graph-Based exploration Planner (GBP) to prioritize exploration of traversable low-confidence regions. We evaluate our framework through simulated lunar experiments using a novel low-confidence region ratio metric, achieving 69% uncertainty reduction compared to baseline GBP. In terms of mission success rate, our method achieves 100% while baseline GBP achieves 0%, demonstrating improvements in exploration safety and map reliability.