# EvoPSF: Online Evolution of Autonomous Driving Models via Planning-State Feedback

arXiv: https://arxiv.org/abs/2508.11453 · HTML: https://mlsanity.com/paper/2508.11453/

## 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 27 of its 33 references that are in the map.
- First posted on arXiv 15 Aug 2025.

## 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, 27 of 27)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [nuScenes: A multimodal dataset for autonomous driving](https://mlsanity.com/paper/1903.11027/) (2019)
- [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)
- [End-to-end Autonomous Driving: Challenges and Frontiers](https://mlsanity.com/paper/2306.16927/) (2023)
- [TransFuser: Imitation with Transformer-Based Sensor Fusion for Autonomous Driving](https://mlsanity.com/paper/2205.15997/) (2022)
- [ST-P3: End-to-end Vision-based Autonomous Driving via Spatial-Temporal Feature Learning](https://mlsanity.com/paper/2207.07601/) (2022)
- [A Comprehensive Survey on Test-Time Adaptation under Distribution Shifts](https://mlsanity.com/paper/2303.15361/) (2023)
- [VADv2: End-to-End Vectorized Autonomous Driving via Probabilistic Planning](https://mlsanity.com/paper/2402.13243/) (2024)
- [A Brief Review of Domain Adaptation](https://mlsanity.com/paper/2010.03978/) (2020)
- [Hydra-MDP: End-to-end Multimodal Planning with Multi-target Hydra-Distillation](https://mlsanity.com/paper/2406.06978/) (2024)
- [SparseDrive: End-to-End Autonomous Driving via Sparse Scene Representation](https://mlsanity.com/paper/2405.19620/) (2024)
- [GenAD: Generative End-to-End Autonomous Driving](https://mlsanity.com/paper/2402.11502/) (2024)
- [Scene as Occupancy](https://mlsanity.com/paper/2306.02851/) (2023)
- [Robust Test-Time Adaptation in Dynamic Scenarios](https://mlsanity.com/paper/2303.13899/) (2023)
- [Enhancing End-to-End Autonomous Driving with Latent World Model](https://mlsanity.com/paper/2406.08481/) (2024)
- [A review of domain adaptation without target labels](https://mlsanity.com/paper/1901.05335/) (2019)
- [Can Autonomous Vehicles Identify, Recover From, and Adapt to Distribution Shifts?](https://mlsanity.com/paper/2006.14911/) (2020)
- [VLP: Vision Language Planning for Autonomous Driving](https://mlsanity.com/paper/2401.05577/) (2024)
- [DriveTransformer: Unified Transformer for Scalable End-to-End Autonomous Driving](https://mlsanity.com/paper/2503.07656/) (2025)
- [Beyond Model Adaptation at Test Time: A Survey](https://mlsanity.com/paper/2411.03687/) (2024)
- [Centaur: Robust End-to-End Autonomous Driving with Test-Time Training](https://mlsanity.com/paper/2503.11650/) (2025)
- [Domain Adaptive Object Detection for Autonomous Driving under Foggy Weather](https://mlsanity.com/paper/2210.15176/) (2022)
- [Pixel and Feature Level Based Domain Adaption for Object Detection in Autonomous Driving](https://mlsanity.com/paper/1810.00345/) (2018)
- [Generative Planning with 3D-vision Language Pre-training for End-to-End Autonomous Driving](https://mlsanity.com/paper/2501.08861/) (2025)
- [DARTH: Holistic Test-time Adaptation for Multiple Object Tracking](https://mlsanity.com/paper/2310.01926/) (2023)
- [RoCA: Robust Cross-Domain End-to-End Autonomous Driving](https://mlsanity.com/paper/2506.10145/) (2025)

## Abstract (arXiv)

Recent years have witnessed remarkable progress in autonomous driving, with systems evolving from modular pipelines to end-to-end architectures. However, most existing methods are trained offline and lack mechanisms to adapt to new environments during deployment. As a result, their generalization ability diminishes when faced with unseen variations in real-world driving scenarios. In this paper, we break away from the conventional "train once, deploy forever" paradigm and propose EvoPSF, a novel online Evolution framework for autonomous driving based on Planning-State Feedback. We argue that planning failures are primarily caused by inaccurate object-level motion predictions, and such failures are often reflected in the form of increased planner uncertainty. To address this, we treat planner uncertainty as a trigger for online evolution, using it as a diagnostic signal to initiate targeted model updates. Rather than performing blind updates, we leverage the planner's agent-agent attention to identify the specific objects that the ego vehicle attends to most, which are primarily responsible for the planning failures. For these critical objects, we compute a targeted self-supervised loss by comparing their predicted waypoints from the prediction module with their actual future positions, selected from the perception module's outputs with high confidence scores. This loss is then backpropagated to adapt the model online. As a result, our method improves the model's robustness to environmental changes, leads to more precise motion predictions, and therefore enables more accurate and stable planning behaviors. Experiments on both cross-region and corrupted variants of the nuScenes dataset demonstrate that EvoPSF consistently improves planning performance under challenging conditions.