Lune

AAAI2024Top-tier venue

EDA: Evolving and Distinct Anchors for Multimodal Motion Prediction

Longzhong Lin, Xuewu Lin, Tianwei Lin, Lichao Huang, Rong Xiong, Yue Wang

Abstract

Motion prediction is a crucial task in autonomous driving, and one of its major challenges lands in the multimodality of future behaviors. Many successful works have utilized mixture models which require identification of positive mixture components, and correspondingly fall into two main lines: prediction-based and anchor-based matching. The prediction clustering phenomenon in prediction-based matching makes it difficult to pick representative trajectories for downstream tasks, while the anchor-based matching suffers from a limited regression capability. In this paper, we introduce a novel paradigm, named Evolving and Distinct Anchors (EDA), to define the positive and negative components for multimodal motion prediction based on mixture models. We enable anchors to evolve and redistribute themselves under specific scenes for an enlarged regression capacity. Furthermore, we select distinct anchors before matching them with the ground truth, which results in impressive scoring performance. Our approach enhances all metrics compared to the baseline MTR, particularly with a notable relative reduction of 13.5% in Miss Rate, resulting in state-of-the-art performance on the Waymo Open Motion Dataset. Appendix and code are available at https://github.com/Longzhong-Lin/EDA.

Ask Lune

Know this paper in minutes, not an afternoon.

Lune can read every page of it and the top-tier papers that cite it, and gives you its claims, its evidence and its limits, each one cited to the paper it comes from. No skimming, no AI slop.

6 top-tier papers have cited it since. Know what they found before your reviewers do.

Questions to start from

Lune can draw on

the full paper · the top-tier papers that cite it · related work

Get the answer

Free to start. No credit card required.

Lineage

  • UniMotion: A Unified Motion Framework for Simulation, Prediction and Planning cites Large Scale Interactive Motion Forecasting for Autonomous Driving : The Waymo Open Motion Dataset
  • UniMotion: A Unified Motion Framework for Simulation, Prediction and Planning cites Reasoning Multi-Agent Behavioral Topology for Interactive Autonomous Driving
  • UniMotion: A Unified Motion Framework for Simulation, Prediction and Planning cites HiVT: Hierarchical Vector Transformer for Multi-Agent Motion Prediction
  • Large Scale Interactive Motion Forecasting for Autonomous Driving : The Waymo Open Motion Dataset cites PRECOG: PREdiction Conditioned on Goals in Visual Multi-Agent Settings
  • ModeSeq: Taming Sparse Multimodal Motion Prediction with Sequential Mode Modeling cites Large Scale Interactive Motion Forecasting for Autonomous Driving : The Waymo Open Motion Dataset
  • ModeSeq: Taming Sparse Multimodal Motion Prediction with Sequential Mode Modeling cites PRECOG: PREdiction Conditioned on Goals in Visual Multi-Agent Settings
  • ModeSeq: Taming Sparse Multimodal Motion Prediction with Sequential Mode Modeling cites HiVT: Hierarchical Vector Transformer for Multi-Agent Motion Prediction
  • DeMo: Decoupling Motion Forecasting into Directional Intentions and Dynamic States cites Latent Variable Sequential Set Transformers for Joint Multi-Agent Motion Prediction
  • DeMo: Decoupling Motion Forecasting into Directional Intentions and Dynamic States cites DenseTNT: End-to-end Trajectory Prediction from Dense Goal Sets
  • DenseTNT: End-to-end Trajectory Prediction from Dense Goal Sets cites Large Scale Interactive Motion Forecasting for Autonomous Driving : The Waymo Open Motion Dataset
  • DenseTNT: End-to-end Trajectory Prediction from Dense Goal Sets cites PRECOG: PREdiction Conditioned on Goals in Visual Multi-Agent Settings
  • Reasoning Multi-Agent Behavioral Topology for Interactive Autonomous Driving cites Large Scale Interactive Motion Forecasting for Autonomous Driving : The Waymo Open Motion Dataset
  • Reasoning Multi-Agent Behavioral Topology for Interactive Autonomous Driving cites DenseTNT: End-to-end Trajectory Prediction from Dense Goal Sets
  • Reasoning Multi-Agent Behavioral Topology for Interactive Autonomous Driving cites HiVT: Hierarchical Vector Transformer for Multi-Agent Motion Prediction
  • Perceiving the Near, Reasoning the Distant: Coherent Long-Horizon Trajectory Prediction for Autonomous Driving cites Large Scale Interactive Motion Forecasting for Autonomous Driving : The Waymo Open Motion Dataset
  • Perceiving the Near, Reasoning the Distant: Coherent Long-Horizon Trajectory Prediction for Autonomous Driving cites Latent Variable Sequential Set Transformers for Joint Multi-Agent Motion Prediction
  • Perceiving the Near, Reasoning the Distant: Coherent Long-Horizon Trajectory Prediction for Autonomous Driving cites DeMo: Decoupling Motion Forecasting into Directional Intentions and Dynamic States
  • Perceiving the Near, Reasoning the Distant: Coherent Long-Horizon Trajectory Prediction for Autonomous Driving cites HiVT: Hierarchical Vector Transformer for Multi-Agent Motion Prediction
  • HiVT: Hierarchical Vector Transformer for Multi-Agent Motion Prediction cites PRECOG: PREdiction Conditioned on Goals in Visual Multi-Agent Settings
  • HiVT: Hierarchical Vector Transformer for Multi-Agent Motion Prediction cites DenseTNT: End-to-end Trajectory Prediction from Dense Goal Sets
Builds onCited byLeft to right by year; the more cited, the higher.

Cited by top-tier papers6

  1. Reasoning Multi-Agent Behavioral Topology for Interactive Autonomous DrivingHaochen Liu, Li Chen, Yu Qiao, Chen Lv et al.NeurIPS 2024 · 52 citations
  2. DeMo: Decoupling Motion Forecasting into Directional Intentions and Dynamic StatesBozhou Zhang, Nan Song, Li ZhangNeurIPS 2024 · 34 citations
  3. UniMotion: A Unified Motion Framework for Simulation, Prediction and PlanningNan Song, Junzhe Jiang, Jingyu Li, Xiatian Zhu et al.NeurIPS 2025 · 2 citations
  4. Perceiving the Near, Reasoning the Distant: Coherent Long-Horizon Trajectory Prediction for Autonomous DrivingHua Hu, Zikang Zhou, Qian Zhou, Zihao Wen et al.CVPR 2026 · 1 citation
  5. ModeSeq: Taming Sparse Multimodal Motion Prediction with Sequential Mode ModelingZikang Zhou, Hengjian Zhou, Haibo Hu, Zihao Wen et al.CVPR 2025

Builds on12

  1. Large Scale Interactive Motion Forecasting for Autonomous Driving : The Waymo Open Motion DatasetScott Ettinger, Shuyang Cheng, Benjamin Caine, Chenxi Liu et al.ICCV 2021 · 817 citations
  2. DenseTNT: End-to-end Trajectory Prediction from Dense Goal SetsJunru Gu, Chen Sun, Hang ZhaoICCV 2021 · 563 citations
  3. PRECOG: PREdiction Conditioned on Goals in Visual Multi-Agent SettingsNicholas Rhinehart, Rowan McAllister, Kris Kitani, Sergey LevineICCV 2019 · 407 citations
  4. HiVT: Hierarchical Vector Transformer for Multi-Agent Motion PredictionZikang Zhou, Luyao Ye, Jianping Wang, Kui Wu et al.CVPR 2022 · 379 citations
  5. Latent Variable Sequential Set Transformers for Joint Multi-Agent Motion PredictionRoger Girgis, Florian Golemo, Felipe Codevilla, Martin Weiss et al.ICLR 2022 · 200 citations

Related papers

  1. MotionLM: Multi-Agent Motion Forecasting as Language ModelingAri Seff, Brian Cera, Dian Chen, Mason Ng et al.ICCV 2023 · 186 citations
  2. ProphNet: Efficient Agent-Centric Motion Forecasting with Anchor-Informed ProposalsXishun Wang, Tong Su, Fang Da, Xiaodong YangCVPR 2023
  3. Motion Transformer with Global Intention Localization and Local Movement RefinementShaoshuai Shi, Li Jiang, Dengxin Dai, Bernt SchieleNeurIPS 2022 · 515 citations
  4. M2I: From Factored Marginal Trajectory Prediction to Interactive PredictionQiao Sun, Xin Huang, Junru Gu, Brian C. Williams et al.CVPR 2022 · 104 citations
  5. Multimodal Motion Prediction With Stacked TransformersYicheng Liu, Jinghuai Zhang, Liangji Fang, Qinhong Jiang et al.CVPR 2021
Dusk over the sea between two cliffs drawn in fine vertical lines