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
- Addresses performance degradation in closed-loop settings due to error accumulation in imitation learning
- Proposes a temporal alternation policy that enhances robustness through expert sequence alternation
- 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.