发表机构
University of Southern California; Jet Propulsion Laboratory, California Institute of Technology; Washington State University（南加州大学; 加州理工学院喷气推进实验室; 华盛顿州立大学）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
本文提出基于火星2020毅力号数据集的不确定性感知多模态可穿越性估计框架，在AUROC和F1上超越现有方法，并集成到路径规划器中。
AI 中文摘要
火星上的自主导航要求车辆能够在多样且视觉上具有挑战性的环境中区分可穿越的地形。然而，基于学习的地外环境导航进展一直受到缺乏大规模数据集的限制。自着陆于杰泽罗陨石坑以来，火星2020“毅力号”火星车已穿越了包括沙丘、岩石地带和平坦基岩在内的地形。因此，本文提出了一个跨越500个火星日和45公里轨迹的数据集，这些轨迹由人类操作员和机载规划器ENav共同驱动。我们的数据集包含灰度立体图像对、位姿、加速度计读数、摇臂转向架角度以及倾斜和车轮滑移的估计。基于该数据集，我们引入了一个不确定性感知的可穿越性估计框架，该框架从多模态驾驶经验中学习地形表征。我们在火星2020数据集上将我们提出的方法与现有方法进行比较，结果表明我们的方法达到了0.874的AUROC和0.758的F1分数，分别比最强基线高出0.058和0.156，同时还实现了最高的平均精度和召回率。最后，我们展示了视觉表征可以集成到路径规划器（如ENav）中，并在物理火星车测试平台上进行了验证。视频、代码和M2020数据集将在该https URL上提供。
英文摘要
Autonomous navigation on Mars requires vehicles to distinguish between traversable terrains across diverse and visually challenging environments. However, progress in learning-based navigation for off-world environments has been limited by the lack of large-scale datasets. Since landing in Jezero Crater, the Mars 2020 Perseverance rover has traversed terrain ranging from sandy dunes, rocky patches, and flat bedrocks. As a result, this paper presents a dataset spanning 500 sols and 45km of trajectories driven by both human operators and the onboard planner, ENav. Our dataset contains grayscale stereo image pairs, poses, accelerometer readings, rocker-bogie angles, and estimates of tilt and wheel slip. Building on this dataset, we introduce an uncertainty-aware traversability-estimation framework that learns terrain representations from multimodal driving experience. We compare our proposed method against existing approaches on the Mars 2020 dataset and show that our method achieves an AUROC of 0.874 and an F1 score of 0.758, outperforming the strongest baseline by 0.058 and 0.156, respectively, while also achieving the highest average precision and recall. Finally, we show that the visual representations can be integrated into path planners, such as ENav, on a physical rover test bed. Videos, code, and the M2020 dataset will be available at https://darren-chiu.github.io/learning-to-drive-on-mars.
