The paper presents a study on using formal verification to assess end‑to‑end steering models for autonomous vehicles. Two small steering networks were trained in CARLA—one on clear conditions only and another on clear, fog, night, and low sun—and both were evaluated against a 2.19‑ft lane‑departure budget. By applying bound propagation, the authors computed steering drift across a vast range of disturbances, uncovering failures in the clear‑trained model that were not detected by simulation alone and suggesting potential failures between test cases.
By Menuka Ghalan, Charles Rodgers, Zachary D. Asher
The paper introduces a geo‑referenced smartphone dashcam dataset of 63,839 frames from South Texas and a baseline framework for assessing road lane quality. Three new metrics—Contrast Stability Index (CSI), Line Continuity Ratio (LCR), and Regression Lane Confidence Score (RLCS)—are proposed to evaluate lane‑marking visibility, continuity, and map consistency without dense human labels. Baseline models achieve strong performance, and pilot validation shows the metrics correlate better with human judgments than generic image‑quality measures.
By Shaif Chowdhury, Akhila Yeruvasu, Moshiur Rahman Tonmoy, Ayush Goyal, Dunren Che
arXiv:2607. 16156v1 Announce Type: new Abstract: Urban intersections are among the most hazardous locations in road networks, posing significant risks to vehicles and vulnerable road users (VRUs) such as pedestrians and cyclists.
By Tam Bang, Hussam Abubakr, Emiliano de la Garza Villarreal, Truc Phuong Nguyen, Austin Harris, Toru Hirano, Mina Sartipi, Yunfei Xu, Hoang H. Nguyen
arXiv:2609.39969v1 Announce Type: cross
Abstract: Physical LiDAR attacks are often evaluated using fixed primitives and manually selected parameters, despite their strong dependence on surrounding tr...
By Yiming Gao, Shaocheng Luo
arXiv:2606. 04513v1 Announce Type: new Abstract: Lane-level maps are critical infrastructure for autonomous driving and lane-level navigation, yet constructing and maintaining standardized lane networks for hundreds of cities remains highly labor-intensive.
By Deguo Xia, Zihan Li, Haochen Zhao, Dong Xie, Yuyao Kong, Xiyan Liu, Jizhou Huang, Mengmeng Yang, Diange Yang
arXiv:2606. 24129v1 Announce Type: new Abstract: For a wheelchair user, a standard blue line on a map is often a broken promise.
By ASM Mobarak Hossain, Nadim Mahmud, Vaskar Raychoudhury, Md Osman Gani
The paper evaluates infrastructure‑based radar for highway traffic monitoring using the newly introduced DRaT dataset, which pairs radar data with drone‑derived ground truth. It reports that radar achieves 78 % precision and 57 % recall for vehicle detection, tracks vehicles with an IDF1 score of 0.699, and estimates space‑mean speed with less than 4 % error while underestimating density and volume by about 23 %. The study also highlights deployment considerations and releases the dataset for reproducible research.
By Tianheng Zhu, Woei-chyi Chang, Alamss Riaz, Sogand Hasanzadeh, Yiheng Feng
The paper introduces a multi‑modal traffic sign detection framework that fuses camera and LiDAR data using an Intensity‑Aware Deformable Fusion module to align retro‑reflective LiDAR cues with visual features. It also presents a dual motion‑model tracker to handle non‑linear perspective changes and a semantic attribute classification pipeline that estimates occlusion, readability, sign embeddedness, and road relevance. Evaluated on a dataset covering more than 60 countries and 2,500 hours of driving, the system achieves an Object Miss Ratio of 0.49% across 221,068 sequences, indicating strong global generalization for autonomous driving.
By Meda Lazar, Sourab Sridhar, Shashwata Gupta, Alexandra Tripcea, Varun Ravi, Senthil Yogamani
arXiv:2610.35092v1 Announce Type: new
Abstract: For safety of the intended functionality (SOTIF) analysis according to ISO 21448, a machine learning object detector for light detection and ranging (L...
By Milin Patel, Rolf Jung
For a wheelchair user, a standard blue line on a map is often a broken promise. While platforms like OpenStreetMap (OSM) successfully capture where a path is, they frequently fail to convey how it physically feels to travel on it.
For safety of the intended functionality (SOTIF) analysis according to ISO 21448, a machine learning object detector for light detection and ranging (LiDAR) point clouds can meet a performance target,...
TerrainForge is a framework that generates counterfactual road geometry edits—such as crests, sags, speed humps, and friction changes—by linking a unified road model to four‑wheel vehicle dynamics. It propagates these edits through vehicle motion, camera viewpoint, and inter‑vehicle clearance, and validates the dynamics against CarSim and reconstructed Waymo scenes. The system also simulates thousands of road edits to train a surrogate model that predicts changes in the ego vehicle’s terminal gap, enabling efficient screening of safety‑critical edits.
By Yang Chen, Yicheng Zhu, zhenning Li, Tao Li, Zilin Bian