analiza aiqbench
MineXplore introduces a high-fidelity, open-source simulation benchmark for autonomous navigation in GPS-denied underground environments, addressing a critical gap in training data for mining robotics. By leveraging real-world mine geometry and GPU-accelerated pipelines, it enables reproducible reinforcement learning experiments that validate policy stability under realistic topological constraints. This resource is particularly relevant for researchers developing RL agents for complex, non-convex search spaces where standard benchmarks fail to capture environmental fidelity.
MineXplore: An Open-Source Reinforcement Learning Exploration Benchmark for GNSS-Denied Underground Environment
arXiv:2606.04569v1 Announce Type: new Abstract: Underground mines present extreme conditions for autonomous robot navigation: GPS is denied, lighting is degraded, and tunnel topology is loop-rich and non-convex. Simulation benchmarks grounded in real production-mine geometry and compatible with GPU-accelerated learning pipelines do not yet exist in the open-source ecosystem. We present MineXplore, an open-source MuJoCo-based navigation benchmark derived from the Leung et al. 2017 Chilean underground copper mine dataset. The environment reconstructs a 104,423 sq.m tunnel network through an six-stage contour-to-MJCF pipeline incorporating octagonal wall cross-sections, LiDAR-sourced jagged wall geometry, three terrain friction zones, a global 5 degree incline, and periodic spot lighting. Geometric fidelity is validated at an Intersection over Union (IoU) of 0.9538 against the source survey map, and surface texture similarity scores 79.4% across six structural dimensions. A single-agent PPO baseline trained via RLlib across five independent random seeds achieves a best rolling coverage of 88.89% (3 of 5 seeds reaching the 90% coverage target), confirming that MineXplore supports stable and reproducible policy learning under realistic underground sensing and topology.
Abstract:Underground mines present extreme conditions for autonomous robot navigation: GPS is denied, lighting is degraded, and tunnel topology is loop-rich and non-convex. Simulation benchmarks grounded in real production-mine geometry and compatible with GPU-accelerated learning pipelines do not yet exist in the open-source ecosystem. We present MineXplore, an open-source MuJoCo-based navigation benchmark derived from the Leung et al. 2017 Chilean underground copper mine dataset. The environment reconstructs a 104,423 sq.m tunnel network through an six-stage contour-to-MJCF pipeline incorporating octagonal wall cross-sections, LiDAR-sourced jagged wall geometry, three terrain friction zones, a global 5 degree incline, and periodic spot lighting. Geometric fidelity is validated at an Intersection over Union (IoU) of 0.9538 against the source survey map, and surface texture similarity scores 79.4% across six structural dimensions. A single-agent PPO baseline trained via RLlib across five independent random seeds achieves a best rolling coverage of 88.89% (3 of 5 seeds reaching the 90% coverage target), confirming that MineXplore supports stable and reproducible policy learning under realistic underground sensing and topology.
Robotics (cs.RO)
arXiv:2606.04569 [cs.RO]
(or arXiv:2606.04569v1 [cs.RO] for this version)
https://doi.org/10.48550/arXiv.2606.04569 arXiv-issued DOI via DataCite (pending registration)
Text integral sub licența deschisă a publicației · 184 cuvinte
Subiecte conexe
Easy-to-Use Shielding for Reinforcement Learning
arXiv · 3 iun. 2026
Reasoning or Memorization? Direction-Aware Diversity Exploration in LLM Reinforcement Learning
arXiv · 10 iun. 2026
Bidirectional Voronoi-biased Exploration Curriculum for Reinforcement Learning
arXiv · 5 oct. 2026
Policy Split: Incentivizing Dual-Mode Exploration in LLM Reinforcement with Dual-Mode Entropy Regularization
arXiv · 5 iun. 2026