Research map / Large language models / Agents, code and math
Asynchronous Large Language Model Enhanced Planner for Autonomous Driving
Yuan Chen, Zi-han Ding, Ziqin Wang, Yan Wang, Lijun Zhang, Si Liu
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 |
|---|---|---|---|
| replace MLP waypoint regression head with a real-time planner after the LLM (ablation) | AsyncDriver · nuPlan Hard20 | Score: 33.91 -> 62.01 | Improved |
| add Adaptive Injection Block (ablation) | AsyncDriver · nuPlan Hard20 | Score: 62.01 -> 62.84 | Improved |
| add Alignment Assistance Module (ablation) | AsyncDriver · nuPlan Hard20 | Score: 62.84 -> 63.78 | Improved |
| add LoRA fine-tuning of the LLM (ablation) | AsyncDriver · nuPlan Hard20 | Score: 63.78 -> 64.03 | Improved |
| pre-train LoRA weights with Reasoning1K (ablation) | AsyncDriver · nuPlan Hard20 | Score: 64.03 -> 65.00 | Improved |
| use pretrained LLM instead of non-pretrained transformer with learnable instruction embedding (ablation) | AsyncDriver · nuPlan Hard20 | Score: 63.59 -> 65.00 | Improved |
| scale non-pretrained transformer from 256 to 5120 dimensions (ablation) | cross-attention replacement of LLM · nuPlan Hard20 | Score: 63.27 -> 63.59 | No clear effect |
| run LLM at a sparse interval (up to 149 frames) while real-time planner runs every frame (ablation) | AsyncDriver · nuPlan Hard20 | Score | No clear effect |
| adopt PDM scorer for trajectory refinement in AsyncDriver | AsyncDriver · nuPlan Hard20 | Score: 65.00 -> 67.48 | Improved |
Closest papers by meaning
- Graph-enhanced Large Language Models in Asynchronous Plan Reasoning (ICML 2024 · similarity 0.90)
- Distilling Multi-modal Large Language Models for Autonomous Driving (CVPR 2025 · similarity 0.89)
- LLMs Can Plan Only If We Tell Them (ICLR 2025 · similarity 0.88)
- OneVL: One-Step Latent Reasoning and Planning with Vision-Language Explanation (NeurIPS 2026 · similarity 0.88)
- HCRMP: An LLM-Hinted Contextual Reinforcement Learning Framework for Autonomous Driving (NeurIPS 2025 · similarity 0.88)
- LMDrive: Closed-Loop End-to-End Driving with Large Language Models (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.
