Research map / Multi-agent systems and games / Human-AI and goal-conditioned
PiP: Planning-informed Trajectory Prediction for Autonomous Driving
Haoran Song, Wenchao Ding, Yuxuan Chen, Shaojie Shen, Michael Yu Wang, Qifeng Chen
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 |
|---|---|---|---|
| add ego planning input (planning-coupled module) (ablation) | PiP-noPlan · NGSIM 5s | RMSE (m): 4.27 -> 4.04 | Improved |
| add ego planning input (planning-coupled module) (ablation) | PiP-noPlan · HighD 5s | RMSE (m): 2.81 -> 2.63 | Improved |
| add ego planning input (planning-coupled module) (ablation) | PiP-noPlan · NGSIM 5s | NLL (nats): 5.42 -> 5.32 | Improved |
| add ego planning input (planning-coupled module) (ablation) | PiP-noPlan · HighD 5s | NLL (nats): 5.05 -> 4.99 | Improved |
| add ego planning input (planning-coupled module) (ablation) | PiP-noPlan · HighD 1s | NLL (nats): 0.20 -> 0.14 | Improved |
| add ego planning input (planning-coupled module) (ablation) | PiP-noPlan · NGSIM 1s | NLL (nats): 1.68 -> 1.72 | Hurt |
| add target fusion module (ablation) | PiP-noFusion · NGSIM 5s | RMSE (m): 4.07 -> 4.04 | Improved |
| add target fusion module (ablation) | PiP-noFusion · HighD 5s | RMSE (m): 2.63 -> 2.63 | No clear effect |
| add target fusion module (ablation) | PiP-noFusion · NGSIM 5s | NLL (nats): 5.33 -> 5.32 | Improved |
| add target fusion module (ablation) | PiP-noFusion · HighD 5s | NLL (nats): 5.01 -> 4.99 | Improved |
| replace CS-LSTM with PiP (planning-informed, same maneuver decoder) | CS-LSTM · NGSIM 5s | RMSE (m): 4.37 -> 4.04 | Improved |
Closest papers by meaning
- Hybrid-Prediction Integrated Planning for Autonomous Driving (TPAMI 2025 · similarity 0.87)
- CoverNet: Multimodal Behavior Prediction Using Trajectory Sets (CVPR 2020 · similarity 0.87)
- HalentNet: Multimodal Trajectory Forecasting with Hallucinative Intents (ICLR 2021 · similarity 0.87)
- Int2Planner: An Intention-based Multi-modal Motion Planner for Integrated Prediction and Planning (AAAI 2025 · similarity 0.87)
- DeMo: Decoupling Motion Forecasting into Directional Intentions and Dynamic States (NeurIPS 2024 · similarity 0.87)
- BAT: Behavior-Aware Human-Like Trajectory Prediction for Autonomous Driving (AAAI 2024 · similarity 0.86)
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.
