PrismAD: 意味的Mixture-of-Plannersによる分離型計画法を用いたエンドツーエンド自動運転
PrismAD: Decoupled Planning via Semantic Mixture-of-Planners for End-to-End Autonomous Driving
自動運転の計画タスクを、相互作用・幾何・意図の3つの専門家に分離し、意味的ルーターで適応的に統合するフレームワークを提案した。
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: Kang Ding, Zhigui Lin, Hongsong Wang, Jie Gui, Qi Liu, Zhe Wang, Luqi Tang, Lei He
分類: cs.RO, cs.CV
原文アブストラクト
This letter presents PrismAD, a decoupled end-to-end autonomous driving framework based on a Semantic Mixture-of-Planners. Existing planners usually aggregate heterogeneous scene tokens into a coupled representation space, forcing a single planning branch to jointly model agent interaction, road geometry, and driving intention. Such coupling may weaken factor-specific reasoning and obscure the contribution of different planning cues. To address this limitation, PrismAD partitions scene tokens into interaction, geometry, and intent groups, and assigns them to independent planning experts with the same architecture but separate parameters. Each expert learns a specialized motion-planning representation, while a semantics-aware router adaptively aggregates expert predictions with separate routing weights for motion prediction and ego planning. Sparse top-$K$ activation with noisy gating is further introduced to improve routing robustness and reduce unnecessary expert computation. Extensive experiments on the nuScenes open-loop dataset and NeuroNCAP closed-loop benchmark demonstrate that PrismAD exhibits competitive performance. Our code will be released soon.
