Research map / Vision-language and multimodal / Robot action and navigation
E3AD: An Emotion-Aware Vision-Language-Action Model for Human-Centric End-to-End Autonomous Driving
Yihong Tang, Haicheng Liao, Tong Nie, Junlin He, Ao Qu, Kehua Chen, Wei Ma, Zhenning Li, Lijun Sun, Chengzhong Xu
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 egocentric pathway to spatial reasoning (ablation) | E3AD · Talk2Car visual grounding | IoU: 74.48 -> 80.12 | Improved |
| add allocentric pathway (ablation) | E3AD · Talk2Car visual grounding | IoU: 76.48 -> 80.12 | Improved |
| add emotion modeling (ablation) | E3AD · Visual grounding Long-text | IoU: 74.12 -> 77.86 | Improved |
| add emotion modeling (ablation) | E3AD · Visual grounding Ambiguous | IoU: 73.57 -> 77.05 | Improved |
| add DPO emotion-action alignment (ablation) | E3AD · Talk2Car visual grounding | IoU: 79.55 -> 80.12 | Improved |
| add DPO emotion-action alignment (ablation) | E3AD · Visual grounding Ambiguous | IoU: 77.09 -> 77.05 | No clear effect |
| add allocentric pathway (ablation) | E3AD · Waypoint planning | ADE: 4.27 -> 3.88 | Improved |
| add egocentric pathway (ablation) | E3AD · Waypoint planning | ADE: 4.12 -> 3.88 | Improved |
| add emotion modeling (ablation) | E3AD · Waypoint planning | ADE: 3.93 -> 3.88 | Improved |
| add DPO alignment (ablation) | E3AD · Waypoint planning | FDE: 6.86 -> 6.64 | Improved |
| use E3AD (Qwen2.5-VL-7B, LoRA) instead of strongest baseline PTPC | trajectory planning · Talk2Car-Trajectory end-to-end | ADE: 4.54 -> 3.88 | Improved |
| use larger generic VLM (Qwen2.5-VL-72B) instead of E3AD | trajectory planning · Talk2Car-Trajectory end-to-end | ADE: 3.88 -> 12.51 | Hurt |
Closest papers by meaning
- Less Language, More Latents: Annotation-Efficient VLAs for Driving (NeurIPS 2026 · similarity 0.88)
- LaST-VLA: Thinking in Latent Spatio-Temporal Space for Vision-Language-Action in Autonomous Driving (NeurIPS 2026 · similarity 0.88)
- Explicit Geometric Chain-of-Thought for Vision-Language-Action in Autonomous Driving (NeurIPS 2026 · similarity 0.86)
- AutoVLA: A Vision-Language-Action Model for End-to-End Autonomous Driving with Adaptive Reasoning and Reinforcement Fine-Tuning (NeurIPS 2025 · similarity 0.86)
- DriveSpatial: A Benchmark for Spatiotemporal Intelligence in VLMs for Autonomous Driving (NeurIPS 2026 · similarity 0.86)
- SGDrive: Scene-to-Goal Hierarchical World Cognition for Autonomous Driving (CVPR 2026 · 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.
