面向非结构化、茂密植被环境的基于交互的在线自适应可通行性估计
Online Adaptive Traversability Estimation through Interaction for Unstructured, Densely Vegetated Environments
AI总结：
本文提出一种仅用激光雷达的在线自适应可通行性估计方法，通过机器人-环境交互自监督训练概率体素模型，仅需8分钟数据即可适应茂密植被环境，并在25W GPU平台上实现与离线模型相当的导航性能。
摘要：
在茂密植被环境中导航对自主地面车辆构成重大挑战。基于学习的系统通常利用先验数据和现场数据来预测地形可通行性，但在遇到由快速环境变化或新异条件引起的分布外元素时，性能往往会下降。本文提出了一种新颖的、仅使用激光雷达的在线自适应可通行性估计（TE）方法，该方法利用通过机器人-环境交互收集的自监督数据直接在机器人上训练模型。所提出的方法利用概率性三维体素表示来整合激光雷达测量数据和机器人经验，从而创建一个显著的环境模型。为确保计算效率，采用基于稀疏图的表示来更新随时间演化的体素分布。在自然地形中使用无人地面车辆进行的大量实验表明，该系统仅需8分钟的运行数据即可适应复杂环境，达到0.63的马修斯相关系数（MCC）分数，并能在茂密植被环境中实现安全导航。本研究考察了基于体素的TE方法的不同训练策略，并为提高适应性提供了训练策略建议。所提出的方法在一个计算资源有限的机器人平台上（25W GPU）得到验证，达到了与离线训练模型相当的精度，同时在不同环境中保持了可靠的性能。
英文摘要：
Navigating densely vegetated environments poses significant challenges for autonomous ground vehicles. Learning-based systems typically use prior and in-situ data to predict terrain traversability but often degrade in performance when encountering out-of-distribution elements caused by rapid environmental changes or novel conditions. This paper presents a novel, lidar-only, online adaptive traversability estimation (TE) method that trains a model directly on the robot using self-supervised data collected through robot-environment interaction. The proposed approach utilises a probabilistic 3D voxel representation to integrate lidar measurements and robot experience, creating a salient environmental model. To ensure computational efficiency, a sparse graph-based representation is employed to update temporarily evolving voxel distributions. Extensive experiments with an unmanned ground vehicle in natural terrain demonstrate that the system adapts to complex environments with as little as 8 minutes of operational data, achieving a Matthews Correlation Coefficient (MCC) score of 0.63 and enabling safe navigation in densely vegetated environments. This work examines different training strategies for voxel-based TE methods and offers recommendations for training strategies to improve adaptability. The proposed method is validated on a robotic platform with limited computational resources (25W GPU), achieving accuracy comparable to offline-trained models while maintaining reliable performance across varied environments.
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。
