The paper introduces AdaptAV, a system that continuously adapts vision models for autonomous vehicles by retraining them on the cloud using data uploaded from the vehicles. It leverages powerful cloud compute resources and a highly accurate oracle model to guide the retraining process, producing a new model that is then transmitted back to the vehicle. This approach aims to improve inference accuracy over time while maintaining the fast inference speeds required for on‑vehicle deployment.
arXiv:2607. 22714v1 Announce Type: cross Abstract: Real-time perception is a foundational requirement for advanced driver assistance systems (ADAS) and autonomous vehicles, yet embedded automotive platforms impose severe constraints on compute, memory, and power.
arXiv:2606. 02979v1 Announce Type: cross Abstract: We present a novel compact deep multi-task learning model to handle various autonomous driving perception tasks in one forward pass.
The paper introduces Recursive Block-Diagonal Coupling (RBDC), a training protocol that builds wide vision models by recursively coupling narrower, independently trained models in a parameter‑free block‑diagonal manner. RBDC allows flexible allocation of training budgets across all models and, when applied to vision transformers (DeiT) and convolutional networks (ResNet) on ImageNet, achieves a 30% reduction in FLOPs while maintaining similar test accuracies. Additionally, models trained with RBDC outperform those from existing growth methods at the same training FLOPs and serve as stronger backbones for downstream tasks such as object detection and instance segmentation.
arXiv:2608.28672v1 Announce Type: cross Abstract: Autonomous vehicles operate in dynamic, ever-changing environments where new scenarios and edge cases constantly emerge. As a result, static learning...
MILER is an end‑to‑end reinforcement learning framework that achieves zero‑shot sim‑to‑real transfer for autonomous driving in unstructured environments. It uses a custom semantic mid‑level representation (MLR) simulator for offline training, and during deployment it processes real camera and LiDAR data with BEVFusion to produce a compatible bird’s‑eye‑view representation. The policy’s actions are applied via a trajectory‑alignment strategy, allowing the system to drive 17.3 km on a 3.0 km test track without human intervention, all running on a Jetson AGX Orin.
The paper reviews end‑to‑end autonomous driving (E2E‑AD) training, framing it as a Data‑Strategy‑Platform system. It surveys recent advances in data pipelines, learning paradigms, and training infrastructures, and discusses how these layers interact to influence model performance, robustness, and deployability. The authors highlight current limitations and propose a future vision that prioritizes data value, foundation‑driven generalization, and integrated training‑testing loops for more robust, scalable, and trustworthy autonomous driving systems.
arXiv:2602. 21172v3 Announce Type: replace Abstract: Vision-Language-Action (VLA) models are advancing autonomous driving by replacing modular pipelines with unified end-to-end architectures.
LightEMMA is a longitudinal evaluation framework that tests the autonomous driving performance of vision‑language models (VLMs) without fine‑tuning or prompt engineering. Using this protocol, the authors evaluated 15 VLMs from five major families on the nuScenes prediction benchmark and found that larger, more capable models do not consistently outperform earlier generations. The study identifies common failure modes such as overreliance on historical actions and difficulty reconciling conflicting visual cues, underscoring the need for domain‑specific adaptation to enhance VLM safety in autonomous driving.
arXiv:2610.41834v1 Announce Type: new Abstract: Accurate BEV map prediction is a critical component of autonomous driving systems, enabling downstream planning and control. Recent approaches such as...
The paper surveys one‑stage object detectors for autonomous driving, covering the evolution from early models like YOLOv1 and SSD to recent real‑time architectures such as YOLOv10 and anchor‑free detectors like FCOS and CenterNet. It compares these methods on design choices, feature‑fusion strategies, loss functions, deployment trade‑offs, and benchmark performance, while also summarizing datasets, evaluation metrics, open challenges, and future research directions. The survey emphasizes how one‑stage detectors balance speed, accuracy, efficiency, and robustness, noting the gap between benchmark results and dependable real‑world performance.
arXiv:2606. 14010v1 Announce Type: cross Abstract: Vision-Language-Action (VLA) models have shown strong potential for end-to-end autonomous driving by jointly modeling visual perception, language reasoning, explainability and action prediction.
The paper introduces SR‑BEVS, a sparse recovery learning technique that enhances both clean accuracy and robustness to real‑world corruptions for camera‑based bird’s‑eye view (BEV) 3D object detection models. By pruning weights based on magnitude, generating diverse sparse models, retraining them with varied learning rates, and averaging the recovered models into a single dense model, the method achieves up to 33.8% improvement in corruption robustness and a 1.8% gain in clean accuracy over the Fast‑BEV baseline on the nuScenes dataset. The approach adds no inference overhead and preserves a connected low‑loss basin, suggesting applicability to other BEV models.