← Back to the feed
AI & softwareResearch findings

Enhancing Imitation Planners via Sequence of Experts

Original published 2025.12.15 17:50 KSTAdded to Blackdeck 2026.11.06 03:52 KST

What has changed?

Introduces a temporal alternation policy to improve closed-loop robustness without increasing model size or data

Key points

  1. Addresses performance degradation in closed-loop settings due to error accumulation in imitation learning
  2. Proposes a temporal alternation policy that enhances robustness through expert sequence alternation
  3. Consistently improves performance across all evaluated models on large-scale nuPlan benchmarks

Connect it to your work

Improves closed-loop performance in imitation learning without model or data expansion

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. arxivSequence of Expert: Boosting Imitation Planners for Autonomous Driving through Temporal Alternation