← Back to the feed
Energy & materialsResearch findings

Proposal of a Method to Improve End-to-End Driving Planning Using Human Driving Cognition

Original published 2025.11.03 17:34 KSTAdded to Blackdeck 2026.11.07 02:27 KST

What has changed?

Introduces contrastive learning between visual feature networks and EEG large models to learn latent human driving cognition

Key points

  1. Proposes a comparative learning framework using human driving cognition data
  2. Improves end-to-end planning performance by integrating cognitive data from EEG and vision models
  3. Significantly outperforms baseline models in planning tasks

Connect it to your work

Enhances end-to-end driving planning by incorporating human cognitive data through comparative learning

What remains unproven

This research note is based on an abstract; check the original for test conditions and application scope.

Originals used for this note

Links open the original publisher in a new tab.

  1. arxivEmbodied Cognition Augmented End2End Autonomous Driving