Research map / Probabilistic and scientific modeling / Molecules and proteins
Prediction by Anticipation: An Action-Conditional Prediction Method Based on Interaction Learning
Ershad Banijamali, Mohsen Rohani, Elmira Amirloo, Jun Luo, Pascal Poupart
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 rule-based modules (ablation) | PA · NGSIM I-80 (k=20) | MSE: 7.2 -> 6.2 | Improved |
| add rule-based modules (ablation) | PA-DL · NGSIM I-80 (k=20) | MSE: 10.8 -> 6.7 | Improved |
| add conditioned latent prior (BCDE) (ablation) | PA · NGSIM I-80 (k=20) | MSE: 6.9 -> 6.2 | Improved |
| add conditioned latent prior (BCDE) (ablation) | PA-DL · NGSIM I-80 (k=20) | MSE: 8.4 -> 6.7 | Improved |
| add motion encoding (ablation) | PA · NGSIM I-80 (k=20) | MSE: 6.7 -> 6.2 | Improved |
| add motion encoding (ablation) | PA-DL · NGSIM I-80 (k=20) | MSE: 8.1 -> 6.7 | Improved |
| add rule-based modules (ablation) | PA · Argoverse (k=20) | TP: 72.12 -> 83.17 | Improved |
| add rule-based modules (ablation) | PA-DL · Argoverse (k=20) | TP: 70.55 -> 87.98 | Improved |
| add SSIM term to reconstruction loss (ablation) | PA · Argoverse (k=10) | TP: 87.56 -> 90.14 | Improved |
| add SSIM term to reconstruction loss (ablation) | PA · NGSIM I-80 (k=1) | MSE: 2.9 -> 2.9 | No clear effect |
| add SSIM term to reconstruction loss (ablation) | PA-DL · Argoverse (k=20) | TP: 85.15 -> 87.98 | Improved |
| use anticipation-based PA instead of FM-MPUR | action-conditional prediction · NGSIM I-80 rare actions (k=20) | ALL: 76.4 -> 180.4 | Improved |
Closest papers by meaning
- BAT: Behavior-Aware Human-Like Trajectory Prediction for Autonomous Driving (AAAI 2024 · similarity 0.87)
- Dual-View Interaction-Aware Lane Change Prediction for Autonomous Driving (AAAI 2025 · similarity 0.86)
- Progressive Risk Estimation for Accident Anticipation (NeurIPS 2026 · similarity 0.86)
- DriveGPT: Scaling Autoregressive Behavior Models for Driving (ICML 2025 · similarity 0.86)
- Motion Forecasting in Continuous Driving (NeurIPS 2024 · similarity 0.85)
- DeMo: Decoupling Motion Forecasting into Directional Intentions and Dynamic States (NeurIPS 2024 · similarity 0.85)
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.
