The paper presents a low‑cost, self‑supervised method for detecting wheel tracks on snow‑covered roads using synchronized RGB and long‑wave infrared (RGB‑I) imagery. Training labels are automatically generated by projecting future wheel trajectories from GNSS data, and a neural network is trained to identify wheel tracks on featureless, white‑out road surfaces. Experimental results show the approach is effective in visually monotonous adverse environments, providing a robust alternative for winter autonomy. The ThermalTrack dataset is released for further research.
arXiv:2607. 16366v1 Announce Type: cross Abstract: Robotic navigation in unstructured environments requires robust situational awareness to safely traverse hazards such as steep slopes and rocky terrain.
arXiv:2307. 06647v4 Announce Type: replace-cross Abstract: We propose DeepIPCv2, an end-to-end autonomous driving framework that integrates LiDAR-based environmental perception with command-specific control learning.
The paper presents a foundation-guided auto‑annotation pipeline that improves standard autonomous driving object detectors in adverse weather. By benchmarking YOLOv8, Co‑DETR, and SAM3 on a custom dataset of 25 operational scenarios, the authors find SAM3 to be the most robust and use it offline to generate pseudo‑labels. Fine‑tuning YOLOv8 on these labels boosts overall mAP by 16.04% and yields significant gains in specific conditions such as Residential Direct Sunlight (32.73%) and Highway Fog (28.65%).
arXiv:2609.05523v1 Announce Type: cross Abstract: This paper presents a one-stage learning framework that maps monocular roadside-camera images directly to vehicle states in a ground-fixed coordinate...
arXiv:2602. 07343v2 Announce Type: replace-cross Abstract: Robust semantic segmentation of road scenes under adverse illumination, lighting, and shadow conditions remain a core challenge for autonomous driving applications.
Self-Supervised Monocular Depth Estimation (MDE) has garnered attention in recent years due to its independence from ground truth. However, most existing models are limited to a single scale and exhibit considerable performance degradation in complex driving environments.
The paper introduces FlexDepth, a family of self‑supervised monocular depth estimation models designed for robust driving perception. FlexDepth uses a two‑stage static‑dynamic decoupled training strategy and a Scale‑Driven Decoder that selects components based on scale size, enabling efficient feature fusion and high‑precision depth maps. Experiments on driving benchmarks show state‑of‑the‑art performance across arbitrary scales with minimal computational cost, with the smallest model (Flex‑Nano) achieving 37.6 FPS on mobile devices.
Standard deployment-ready object detectors for autonomous vehicles degrade in adverse weather and lighting conditions without being trained on extensive domain-specific data. While large-scale vision...
FLINT is a lightweight traversability estimator that uses a 21.6‑million‑parameter backbone—38 times smaller than comparable foundation models—to predict traversability from a single RGB camera. It achieves higher accuracy on held‑out terrain probes and runs at 14.7 FPS on CPU, outperforming a deployed foundation‑model system (WildOS) on 23 of 24 field logs. In closed‑loop field trials, FLINT’s best self‑supervised head reached 99% autonomy, surpassing a human‑label‑trained baseline on the same course.
arXiv:2607. 10565v1 Announce Type: cross Abstract: End-to-end motion planning has emerged as a promising paradigm in autonomous driving, directly mapping raw sensor data to control commands via deep neural networks.
arXiv:2606. 12603v1 Announce Type: cross Abstract: Autonomous long-horizon sidewalk navigation is essential for micro-mobility applications such as robotic food delivery and assistive electronic wheelchairs.
The paper proposes a label‑free 3D perception framework where roadside units (RSUs) act as unsupervised teachers for self‑driving cars. RSUs learn local 3D detectors from unlabeled data and broadcast predictions to passing vehicles, which use these as pseudo‑labels to train an ego‑centric detector. In a CARLA simulation, the method achieves 82.3% AP for vehicle detection, approaching a fully supervised upper bound of 94.4%, and demonstrates scalability and complementarity with existing ego‑centric approaches.