Obstacle detection and tracking represent a critical component in robot autonomous navigation. In this paper, we propose ODTFormer, a Transformer-based model to address both obstacle detection and tracking problems. For the detection task, our approach leverages deformable attention to construct a 3D cost volume, which is decoded progressively in the form of voxel occupancy grids. We further track the obstacles by matching the voxels between consecutive frames. The entire model can be optimized in an end-to-end manner. Through extensive experiments on DrivingStereo and KITTI benchmarks, our model achieves state-of-the-art performance in the obstacle detection task. We also report comparable accuracy to state-of-the-art obstacle tracking models while requiring only a fraction of their computation cost, typically ten-fold to twenty-fold less. The code and model weights will be publicly released.

翻译：障碍物检测与跟踪是机器人自主导航中的关键组成部分。本文提出ODTFormer——一种基于Transformer的模型，以同时解决障碍物检测与跟踪问题。在检测任务中，我们的方法利用可变形注意力构建3D代价体，并以体素占据网格的形式逐步解码。我们进一步通过连续帧之间的体素匹配来跟踪障碍物。整个模型可通过端到端方式进行优化。通过在DrivingStereo和KITTI基准上的大量实验，我们的模型在障碍物检测任务中达到了最先进的性能。同时，我们报告的障碍物跟踪精度与最先进模型相当，而计算成本仅为其十分之一至二十分之一。代码与模型权重将公开发布。