# Closed-Loop Refinement and Execution for Learned Driving Planners

arXiv: https://arxiv.org/abs/2610.00992 · HTML: https://mlsanity.com/paper/2610.00992/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in Imitation-learning end-to-end planners, one of 9 directions in End-to-end autonomous driving.
- Builds on 19 of its 26 references that are in the map.
- First posted on arXiv 1 Oct 2026.

## Placed in

- End-to-end autonomous driving / [Imitation-learning end-to-end planners](https://mlsanity.com/driving/imitation-learning-end-to-end-planners/)

## Builds on (most cited first, 19 of 19)

- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [Planning-oriented Autonomous Driving](https://mlsanity.com/paper/2212.10156/) (2022)
- [VAD: Vectorized Scene Representation for Efficient Autonomous Driving](https://mlsanity.com/paper/2303.12077/) (2023)
- [Bench2Drive: Towards Multi-Ability Benchmarking of Closed-Loop End-To-End Autonomous Driving](https://mlsanity.com/paper/2406.03877/) (2024)
- [Parting with Misconceptions about Learning-based Vehicle Motion Planning](https://mlsanity.com/paper/2306.07962/) (2023)
- [Is Ego Status All You Need for Open-Loop End-to-End Autonomous Driving?](https://mlsanity.com/paper/2312.03031/) (2023)
- [DriveTransformer: Unified Transformer for Scalable End-to-End Autonomous Driving](https://mlsanity.com/paper/2503.07656/) (2025)
- [Differentiable Integrated Motion Prediction and Planning with Learnable Cost Function for Autonomous Driving](https://mlsanity.com/paper/2207.10422/) (2022)
- [SafetyNet: Safe planning for real-world self-driving vehicles using machine-learned policies](https://mlsanity.com/paper/2109.13602/) (2021)
- [NeuroNCAP: Photorealistic Closed-loop Safety Testing for Autonomous Driving](https://mlsanity.com/paper/2404.07762/) (2024)
- [Centaur: Robust End-to-End Autonomous Driving with Test-Time Training](https://mlsanity.com/paper/2503.11650/) (2025)
- [Hydra-NeXt: Robust Closed-Loop Driving with Open-Loop Training](https://mlsanity.com/paper/2503.12030/) (2025)
- [Test-Time Trajectory Optimization for Autonomous Driving](https://mlsanity.com/paper/2606.07170/) (2026)
- [Enhance Planning with Physics-informed Safety Controller for End-to-end Autonomous Driving](https://mlsanity.com/paper/2405.00316/) (2024)
- [Predictive Control for Autonomous Driving with Uncertain, Multi-modal Predictions](https://mlsanity.com/paper/2310.20561/) (2023)
- [A Barrier-Certified Optimal Coordination Framework for Connected and Automated Vehicles](https://mlsanity.com/paper/2203.16418/) (2022)
- [A Safety-Prioritized Receding Horizon Control Framework for Platoon Formation in a Mixed Traffic Environment](https://mlsanity.com/paper/2205.10673/) (2022)
- [CorrA: Leveraging Large Language Models for Dynamic Obstacle Avoidance of Autonomous Vehicles](https://mlsanity.com/paper/2503.02076/) (2025)
- [VisioPath: Vision-Language Enhanced Model Predictive Control for Safe Autonomous Navigation in Mixed Traffic](https://mlsanity.com/paper/2507.06441/) (2025)

## Abstract (arXiv)

Learning-based driving planners are usually trained and evaluated in open loop against logged trajectories. In closed loop, a trajectory with small displacement error can still stall the vehicle, steer it into a conflict with surrounding agents, or be executed with abrupt braking. We introduce Closed-Loop Refinement and Execution (CLRE), a hierarchical receding-horizon control framework designed to mitigate these failure modes while leaving the upstream planner frozen and adding no new learned model. The upper layer treats the nominal trajectory as a reference and solves a finite-horizon optimal control problem that trades route progress against interaction with predicted agents. Solving it from several initializations gives a candidate set, and a prediction-conditioned oriented-bounding-box (OBB) feasibility test retains only candidates whose minimum predicted OBB clearance over the horizon meets a threshold. The lower layer executes the lowest-cost survivor, or a route-centerline backup when none remains, through the tracking controller supplied with the planner, augmented by a range-based speed bound and a saturated proportional braking law. In closed-loop simulation on the 220-route Bench2Drive validation set with VAD as the upstream planner, CLRE raises the driving score from 42.26 to 55.89 and route completion from 55.69 to 71.51, and reduces collision events from 117 to 97.