🛰️ Daily AI Frontier
‹ back to 2026-07-22

Cognitive Dual-Process Planning for Autonomous Driving with Structured Scene Knowledge and Verifiable Reasoning-Action Consistency

Research Autonomous Driving

Ranking

Overall 64
Content 75
Popularity 40

Observed public metrics from 1 member.

Merged summary

TL;DR - A dual-process VLM planner routes routine driving scenes to fast action prediction and complex scenes to structured reasoning with rule-based consistency checks. It improves reasoning-action reliability while reducing latency by 17.39% versus always using slow reasoning.

  • An automated data engine generates machine-parsable structured chain-of-thought supervision without manually annotating each rationale.
  • A lightweight visual Arbiter estimates scene complexity before language decoding and selects the fast or slow planning path.
  • A deterministic validator checks whether structured reasoning agrees with the final action and supplies verifiable rewards for GRPO.
  • On 574 verified NAVSIM samples, the planner achieved 80.14% planning accuracy and 97.20% logical consistency.

Sources (1)

Cognitive Dual-Process Planning for Autonomous Driving with Structured Scene Knowledge and Verifiable Reasoning-Action Consistency

arXiv cs.RO Zhongyao Yang, Haoyu Li, Yu Yan, Zhuangxuan Yu, Jiangfeng Nan, Jinrui Nan 2026-07-21 arXiv:2607.19194
Public signals Semantic Scholar citations 0 · Semantic Scholar influential citations 0
Providers: Hugging Face · N/A OpenAlex · N/A Publisher · N/A Semantic Scholar · Citations 0 · Influential citations 0 X · N/A Fetched 2026-08-03 02:50:35.691450 UTC

TL;DR - A dual-process VLM planner routes routine driving scenes to fast action prediction and complex scenes to structured reasoning with rule-based consistency checks. It improves reasoning-action reliability while reducing latency by 17.39% versus always using slow reasoning.

  • An automated data engine generates machine-parsable structured chain-of-thought supervision without manually annotating each rationale.
  • A lightweight visual Arbiter estimates scene complexity before language decoding and selects the fast or slow planning path.
  • A deterministic validator checks whether structured reasoning agrees with the final action and supplies verifiable rewards for GRPO.
  • On 574 verified NAVSIM samples, the planner achieved 80.14% planning accuracy and 97.20% logical consistency.
item →