Research map / Probabilistic and scientific modeling / Molecules and proteins
Safety-Aware Motion Prediction With Unseen Vehicles for Autonomous Driving
Xuanchi Ren, Tao Yang, Li Erran Li, Alexandre Alahi, 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 hard loss (ablation) | Ours · nuScenes val | Missing Rate (%): 18.00 -> 1.37 | Improved |
| add hard loss (ablation) | Ours · nuScenes val | Unseen Recall 0.3 (%): 36.98 -> 63.28 | Improved |
| add soft loss (ablation) | Ours · nuScenes val | Missing Rate (%): 5.85 -> 1.37 | Improved |
| add unseen loss (ablation) | Ours · nuScenes val | Missing Rate (%): 6.60 -> 1.37 | Improved |
| add unseen loss (ablation) | Ours · nuScenes val | Unseen Recall 0.3 (%): 49.78 -> 63.28 | Improved |
| add unseen-aware self-attention unit (ablation) | Ours · nuScenes val | Missing Rate (%): 5.66 -> 1.37 | Improved |
| add unseen-aware self-attention unit (ablation) | Ours · nuScenes val | Unseen Recall 0.3 (%): 39.97 -> 63.28 | Improved |
| add hard loss (ablation) | Ours · nuScenes val | Aggressiveness: 1.39 -> 2.48 | Hurt |
| add soft loss (ablation) | Ours · nuScenes val | Aggressiveness: 3.53 -> 2.48 | Improved |
| add unseen loss (ablation) | Ours · nuScenes val | MSE: 6.53 -> 10.61 | Hurt |
| add handcrafted Poisson unseen-vehicle protocol to Trajectron++ | Ours · nuScenes val | Unseen Recall 0.3 (%): 20.40 -> 20.98 | No clear effect |
| use earliest occupancy map model instead of P3 on Lyft | Ours · nuScenes val | Missing Rate (%): 9.20 -> 3.97 | Improved |
Closest papers by meaning
- Driving in the Occupancy World: Vision-Centric 4D Occupancy Forecasting and Planning via World Models for Autonomous Driving (AAAI 2025 · similarity 0.86)
- DeepAccident: A Motion and Accident Prediction Benchmark for V2X Autonomous Driving (AAAI 2024 · similarity 0.85)
- OOSTraj: Out-of-Sight Trajectory Prediction With Vision-Positioning Denoising (CVPR 2024 · similarity 0.85)
- Future-Aware End-to-End Driving: Bidirectional Modeling of Trajectory Planning and Scene Evolution (NeurIPS 2025 · similarity 0.85)
- SmartPretrain: Model-Agnostic and Dataset-Agnostic Representation Learning for Motion Prediction (ICLR 2025 · similarity 0.85)
- SafeAuto: Knowledge-Enhanced Safe Autonomous Driving with Multimodal Foundation Models (ICML 2025 · similarity 0.84)
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.
