TravSUITE：基于自监督、不确定性感知的逆强化学习（IRL）与地形估计的可通行性系统
TravSUITE: Traversability via Self-Supervised, Uncertainty-Aware IRL and Terrain Estimation
AI总结：
本文提出TravSUITE系统，通过自监督训练的体素映射器与联合预测可通行性的神经网络，结合风险适应机制，在越野高速导航中实现了减少80%导航错误、提升5%通行速度的前沿性能。
摘要：
越野场景中的可通行性分析仍是移动机器人的核心挑战，关键难点包括从多模态传感器数据构建准确且具表达性的局部地图，以及利用该地图设计可通行性规则以生成理想的导航行为，且系统需能应对复杂环境与高速带来的有限感知条件。本文提出TravSUITE，一种适用于越野高速导航的可通行性系统，其包含两大核心组件：1）高效体素映射器，利用视觉基础模型（VFMs）从车载传感器数据流构建丰富的几何-语义局部地图；2）统一神经网络，在鸟瞰图（BEV）中联合预测与可通行性相关的量，包括几何、语义、速度与代价。训练策略完全无标注且为自监督，借助地图补全、逆强化学习（IRL）等任务学习地图表示与可通行性。我们开展了全面的 ablation 研究及与前沿方法的对比，结果表明代价学习与辅助补全均对规划质量有显著贡献，二者结合是实现越野路径规划前沿性能的关键。我们还设计了简单的风险适应机制以在部署时利用方法的不确定性估计，真实硬件实验显示，补全与风险估计结合可减少80%的导航错误，并提升5%的自主通行速度。
英文摘要：
Traversability analysis in off-road settings remains a fundamental challenge for mobile robots. Key difficulties include constructing an accurate and expressive local map from multimodal sensor data, and using the map to design traversability rules that yield desirable navigation behavior. Importantly, this system must be resilient to the limited sensing regime brought about by complex environments and high speeds. In this paper, we present TravSUITE, a traversability system suitable for high-speed navigation in off-road environments. TravSUITE consists of two major components: 1) an efficient voxel mapper that leverages visual foundation models (VFMs) to build a rich geometric-semantic local map from streams of on-board sensor data, and 2) a unified neural network that jointly predicts traversability-relevant quantities in bird's eye view (BEV), including geometry, semantics, speed and cost. Our training strategy is entirely annotation-free and self-supervised, leveraging tasks such as map inpainting and inverse reinforcement learning (IRL) to learn both map representations and traversability. We perform a thorough ablation study and comparison to state-of-the-art approaches, and the results indicate that cost learning and auxiliary inpainting each contribute significantly to planning quality, and their combination is critical for achieving state-of-the-art performance in off-road path planning. We also design a simple risk adaptation mechanism to leverage our method's uncertainty estimates at deploy-time, and demonstrate that a combination of inpainting and risk estimation can result in 80% fewer navigation errors and 5% faster autonomous traversal speeds in real-world hardware experiments.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
