SONG: ソーシャルナビゲーションのベンチマークのためのフォトリアリスティックな3Dガウスシミュレーションプラットフォーム
SONG: A Photorealistic 3D Gaussian Simulation Platform for Benchmarking Social Navigation
3Dガウススプラッティングを用いた高忠実度のソーシャルナビゲーションシミュレーションプラットフォームSONGを提案し、ベンチマークと評価指標を提供する。
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: Weiqi Huang, Dianyi Yang, Jiaxin Li, Shuangyi Dong, Hao Xu, Zan Wang, Wei Liang
分類: cs.RO
原文アブストラクト
Social navigation has progressed from simplified 2D environments toward a more general vision-based setting, in which a robot needs to achieve socially compliant behavior purely from onboard visual observations. Yet supporting simulation platforms have not kept pace: existing options either lack visual observations, lack moving human avatars, or fall short of real-world fidelity in appearance and pedestrian behavior, offering limited support for advancing vision-based social navigation. We introduce SONG, a SOcial Navigation platform powered by 3D Gaussian splatting (3DGS). It leverages 3DGS for both scene and avatar representations, drives pedestrians using semantically grounded trajectories generated by a large language model, and synthesizes their full-body motion with a trajectory-conditioned generator to produce continuous, natural movement. On top of the platform, we curate SONG-Bench, a set of evaluation episodes stratified by difficulty, and propose a multi-dimensional metric suite covering effectiveness, safety, and social compliance. A systematic evaluation of representative navigation baselines reveals three findings: (a) vision-based social navigation is far from solved; (b) a critical safety deficit precedes social etiquette; (c) real-world data matters more than model scale. Crucially, we demonstrate that fine-tuning on our curated data effectively improves the success rate in real-world environments. We hope our platform provides a faithful and rigorous testbed for the next generation of vision-based social navigation research.
