Research map / Multi-agent systems and games / Human-AI and goal-conditioned
Leveraging Future Relationship Reasoning for Vehicle Trajectory Prediction
Daehee Park, Hobin Ryu, Yunseo Yang, Jegyeong Cho, Jiwon Kim, Kuk-Jin Yoon
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| use lane-based Future Relationship modeling instead of past-only interaction modeling | Trajectory prediction model · nuScenes, 10 predictions | mADE: 1.04 -> 0.88 | Improved |
| use lane-based Future Relationship modeling instead of past-only interaction modeling | Trajectory prediction model · nuScenes, 6sec | mADE_1: 3.23 -> 2.89 | Improved |
| use lane-based Future Relationship modeling instead of past-only interaction modeling | Trajectory prediction model · Argoverse, 3sec | mADE_1: 1.41 -> 1.33 | Improved |
| add Future Relationship modeling (ablation) | Ours (Full) · nuScenes, F=1 | mADE: 3.21 -> 2.89 | No clear effect |
| add Future Relationship modeling (ablation) | Ours (Full) · nuScenes, F=5 | mADE: 1.26 -> 1.19 | Improved |
| add GCN smoothing to waypoint occupancy (ablation) | Ours (Full) · nuScenes, F=1 | mADE: 3.04 -> 2.89 | Improved |
| use asymmetric rather than hard symmetric interaction modeling (ablation) | Ours (Full) · nuScenes, F=1 | mADE: 2.99 -> 2.89 | Improved |
| use a Gaussian mixture rather than a single Gaussian prior (ablation) | Ours (Full) · nuScenes, F=5 | mADE: 1.20 -> 1.19 | Improved |
| sample stochastic interaction edges rather than predicting only their mean (ablation) | Ours (Full) · nuScenes, F=5 | mADE: 1.28 -> 1.19 | Improved |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.
- THOMAS — THOMAS: Trajectory Heatmap Output with learned Multi-Agent Sampling (ICLR 2022) · better on 1 of 1 shared result
Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.
Closest papers by meaning
- LaPred: Lane-Aware Prediction of Multi-Modal Future Trajectories of Dynamic Agents (CVPR 2021 · similarity 0.89)
- M2I: From Factored Marginal Trajectory Prediction to Interactive Prediction (CVPR 2022 · similarity 0.89)
- SWIFT: A Small-World Interaction Framework for Flow-Aware Trajectory Prediction in Autonomous Driving (TPAMI 2026 · similarity 0.89)
- FJMP: Factorized Joint Multi-Agent Motion Prediction Over Learned Directed Acyclic Interaction Graphs (CVPR 2023 · similarity 0.89)
- Density-Adaptive Model Based on Motif Matrix for Multi-Agent Trajectory Prediction (CVPR 2024 · similarity 0.88)
- HPNet: Dynamic Trajectory Forecasting with Historical Prediction Attention (CVPR 2024 · similarity 0.87)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
