歩道ロボットのためのハイブリッド2D-3D学習による単眼3D占有知覚
Monocular 3D Occupancy Perception for Robots on Sidewalks via Hybrid 2D-3D Learning
歩道を走行するロボット向けに、LiDAR-RGBペアデータと大規模な非ペア単眼画像を組み合わせたハイブリッド学習で3D占有予測を行うフレームワークWalkOCCを提案し、新たな歩道データセットSidewalk3Dも導入した。
詳しい要約
1. どんなもの?
2. 先行研究と比べてどこがすごい?
3. 技術・手法の肝は?
4. どうやって有効だと検証した?
5. 議論はある?
6. 次に読むべき論文は?
※ AIが要旨から生成した要約です。正確性は原文をご確認ください。
著者: Yukai Ma, Joe Lin, Liu Liu, Honglin He, Lulu Ricketts, Brad Squicciarini, Yong Liu, Bolei Zhou
分類: cs.RO
原文アブストラクト
Sidewalks in the real world are crowded, cluttered, and less structured than roads, making 3D occupancy prediction a key ingredient for the safe navigation of mobile robots such as delivery bots and electric wheelchairs. Existing occupancy learning pipelines are largely designed for on-road autonomous driving and often train on large-scale paired LiDAR-RGB datasets with dense 3D supervision and multiple camera inputs, which are costly to collect and do not adequately capture sidewalk-specific characteristics. We propose WalkOCC, a hybrid Ray-marching monocular 3D occupancy perception framework for robots operating on sidewalks. WalkOCC explicitly couples geometric grounding from LiDAR-RGB paired data with scalable learning from large-scale unpaired monocular images. It bootstraps pseudo occupancy supervision from paired sequences and jointly learns image-level representations on additional 2D-only data. It yields stable optimization and improved generalization without requiring costly 3D occupancy annotations. Extensive experiments demonstrate consistent gains in prediction accuracy, fine-grained segmentation of subtle urban structures such as curbs and gutters, and robustness to environmental and cross-embodiment shifts compared with self-supervised image-based baselines. To facilitate evaluation and benchmarking, we also introduce Sidewalk3D, a large-scale sidewalk perception dataset with LiDAR-camera paired sequences collected across multiple locations and time periods, along with 3D semantic occupancy annotations for evaluation. Code and data will be made available.
