CUTE-Planner: Confidence-aware Uneven Terrain Exploration Planner

2025-11-17

AI Summary

Planetary exploration robots face significant challenges in mapping non-planar terrains—such as lunar crater regions—due to high uncertainty in elevation estimation, the absence of uncertainty-aware exploration strategies, and poorly understood mechanisms by which uncertainty impacts navigation safety and map quality. To address these issues, this paper proposes a confidence-aware collaborative mapping and navigation framework. Its core contributions are: (1) joint modeling of traversability and elevation uncertainty; (2) an adaptive exploration strategy prioritizing low-confidence regions; and (3) integration of Kalman-filter-derived confidence scores into a graph-based planning (GBP) framework to enable safety-aware path planning. Simulation results demonstrate that the method reduces terrain elevation uncertainty by 69%, achieves a 100% mission success rate, and significantly outperforms the baseline GBP approach—yielding simultaneous improvements in exploration efficiency, map reliability, and navigation safety.

Technology Category

• Intelligent Robots: Localization, Mapping, and Navigation
• Planning, Routing, and Scheduling: Planning under Uncertainty
• Reasoning under Uncertainty: Uncertainty Representations

Application Category

• Graph Algorithms and Modeling for the Web: Efficient manipulation of static and dynamic Web-related graphs
• Web Mining and Content Analysis: Robustness and generalizability of Web mining methods
• Search and Retrieval-Augmented AI: Web evaluation methodologies and metrics

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.

Problem

• Addresses elevation uncertainty near complex terrain features like craters
• Integrates safe path planning with confidence-aware exploration strategies
• Improves navigation safety and map reliability for planetary robots

Innovation

• Integrates safe path generation with adaptive confidence updates
• Uses Kalman-based elevation estimation for traversability scoring
• Prioritizes exploration of traversable low-confidence regions