Research map / Multi-agent systems and games / Human-AI and goal-conditioned
Rules of the Road: Predicting Driving Behavior With a Convolutional Model of Semantic Interactions
Check your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (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 other-entity state features to target-entity input (ablation) | Gaussian Regression · San Francisco vehicle forecasting, 5 sec | mean L2: 3.91 -> 3.36 | Helped |
| Add road-map and traffic-light features (ablation) | Gaussian Regression with target and other-entity inputs · San Francisco vehicle forecasting, 5 sec | mean L2: 3.36 -> 3.03 | Helped |
| Add an RNN decoder to the full-input Gaussian Regression model (ablation) | Gaussian Regression · San Francisco vehicle forecasting | RMSE: 1.90 -> 1.82 | Helped |
| Add an RNN decoder to the full-input Grid map model (ablation) | Grid map · San Francisco vehicle forecasting | RMSE: 2.05 -> 1.99 | Helped |
| Use the best trajectory among the top 5 instead of a single prediction | GMM-CVAE · San Francisco vehicle forecasting | RMSE: 2.33 -> 1.58 | Helped |
| Use the best trajectory among the top 5 instead of a single prediction | Grid map · San Francisco vehicle forecasting | RMSE: 1.99 -> 1.25 | Helped |
| Use sampled multimodal Gaussian trajectories instead of Gaussian Regression | Vehicle forecasting model · San Francisco vehicle forecasting | RMSE: 1.82 -> 2.33 | Hurt |
| Use semantic scene and entity inputs instead of physics-only prediction | Gaussian Regression versus Linear · San Francisco vehicle forecasting, 1 sec and 5 sec | mean L2: 0.37 -> 0.44; 5.87 -> 2.99 | Mixed |
Closest papers by meaning
- SGDrive: Scene-to-Goal Hierarchical World Cognition for Autonomous Driving (CVPR 2026 · similarity 0.88)
- Trajeglish: Traffic Modeling as Next-Token Prediction (ICLR 2024 · similarity 0.88)
- DriveSpatial: A Benchmark for Spatiotemporal Intelligence in VLMs for Autonomous Driving (NeurIPS 2026 · similarity 0.88)
- Driving in the Occupancy World: Vision-Centric 4D Occupancy Forecasting and Planning via World Models for Autonomous Driving (AAAI 2025 · similarity 0.88)
- DriveCombo: Benchmarking Compositional Traffic Rule Reasoning in Autonomous Driving (CVPR 2026 · similarity 0.87)
- MAPLM: A Real-World Large-Scale Vision-Language Benchmark for Map and Traffic Scene Understanding (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.