让大模型按需工作，既快又准地辅助自动驾驶决策
AdaDrive: Self-Adaptive Slow-Fast System for Language-Grounded Autonomous Driving
- 动态判断何时调用大模型，只在复杂场景触发
- 根据路况和信心度调节大模型影响程度，实现平滑融合
- 适合追求高精度与实时性平衡的自动驾驶研究者
将大语言模型（LLMs）有效融入自动驾驶系统，需兼顾高层推理能力与实时效率。现有方法或频繁激活大模型导致计算开销过大，或采用固定调度无法适应动态驾驶环境。为此，我们提出AdaDrive，一种自适应协同的慢-快框架，智能决定大模型参与决策的时机与方式。其一，通过新颖的自适应激活损失，基于对比学习机制动态判断是否调用大模型，仅在复杂或关键场景下触发；其二，引入连续可调的自适应融合策略，根据场景复杂度与预测置信度调节大模型影响强度，实现与传统规划器的无缝协作。实验表明，该框架在语言驱动的自动驾驶基准上，显著提升决策准确率，同时保持高效运行。代码已开源。
原文摘要 · Abstract (English)
Effectively integrating Large Language Models (LLMs) into autonomous driving requires a balance between leveraging high-level reasoning and maintaining real-time efficiency. Existing approaches either activate LLMs too frequently, causing excessive computational overhead, or use fixed schedules, failing to adapt to dynamic driving conditions. To address these challenges, we propose AdaDrive, an adaptively collaborative slow-fast framework that optimally determines when and how LLMs contribute to decision-making. (1) When to activate the LLM: AdaDrive employs a novel adaptive activation loss that dynamically determines LLM invocation based on a comparative learning mechanism, ensuring activation only in complex or critical scenarios. (2) How to integrate LLM assistance: Instead of rigid binary activation, AdaDrive introduces an adaptive fusion strategy that modulates a continuous, scaled LLM influence based on scene complexity and prediction confidence, ensuring seamless collaboration with conventional planners. Through these strategies, AdaDrive provides a flexible, context-aware framework that maximizes decision accuracy without compromising real-time performance. Extensive experiments on language-grounded autonomous driving benchmarks demonstrate that AdaDrive state-of-the-art performance in terms of both driving accuracy and computational efficiency. Code is available at https://github.com/ReaFly/AdaDrive.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。