Latest Autonomous Driving Research Papers
The newest Autonomous Driving papers from across the field — arXiv, NeurIPS, CVPR, Nature, and more — refreshed daily and ranked by relevance. Distill AI tracks Autonomous Driving so you don’t have to: get the standout work delivered to your inbox every morning, with 2-sentence summaries and the option to chat with any paper.
Get the latest Autonomous Driving papers in your inbox — free →Recent papers
- Visual-SLAM for the detection of hidden tomatoes in greenhouses by Hierarchical Localization and GLOMAPfor robotized harvestingFernando Cañadas-Aránega, José C. Moreno, José L. Blanco-Claraco, Francisco Rodríguez · arXiv · Sep 10, 2026
Advanced crop monitoring inside greenhouses is becoming one of the primary objectives of research centers. High-performance sensors, such as LiDAR or stereo cameras, have traditionally been employed for this purpose, though these often have…
- MC-DeTra: Motion-Consistent Joint Object Detection and Socially-Aware Trajectory Forecasting in Bird's-Eye-View ImagesVladislav Diuzhev, Dmitry Yudin · arXiv · Sep 10, 2026
Unified models for object detection and trajectory forecasting aim to merge perception and prediction for autonomous driving, refining actor trajectories directly over shared bird's-eye-view (BEV) images rasterized from LiDAR and high-defin…
- CARLAverse: A Highly Modular, Distributed, and Multimodal Framework for Human-in-the-Loop SimulationPatrick Rebling, Philipp Nenninger, Reiner Kriesten · arXiv · Sep 10, 2026
The development of autonomous driving demands comprehensive testing in mixed-traffic scenarios involving vulnerable road users (VRUs), where purely artificial agents often fail to capture authentic human social negotiations. While human-in-…
- DWAT: Density-Weighted Adversarial Training for Robustness Beyond the Training Perturbation BudgetJieying Huang, Ruiming Zhu, Jia Xu, Yueyang Teng · Applied Sciences · Sep 10, 2026
Deep neural networks (DNNs) are widely deployed in safety-critical applications such as medical diagnosis and autonomous driving. Adversarial training (AT) is among the most effective defenses, casting robust optimization as a min–max probl…
- Van der Waals integration of 2D single-crystal transporter with quantum dots for scalable SWIR image sensorsLibin Tang, Pin Tian, Xiaokun Yang, Caimu Wang et al. · Materials Futures · Sep 10, 2026
Abstract Short-wave infrared imaging holds transformative potential in semiconductor inspection, biomedical diagnostics, and autonomous driving. However, its broad adoption is hindered by the high cost of incumbent technologies such as InGa…
- An Efficient Autonomous Driving Planning Method Based on Bidirectional Spatiotemporal Joint Search and OptimizationJinghan Xu, Yongming Li, Yuefeng Wang, Kewen Li et al. · Optimal Control Application... · Sep 10, 2026
ABSTRACT Trajectory planning is a critical component of autonomous driving systems. A planning system requires the algorithm to compute a drivable trajectory within a set time while ensuring safety, comfort, and efficiency. However, the spa…
- Research on Multi-Dimensional and Multi-Level Environmental Parameter System for Visual Perception of Urban Tunnel Portal Sections Based on Structure–Light–Traffic (SLT) CouplingMengdie Xu, Bo Liang, Haonan Long, Shuangkai Zhu · Applied Sciences · Sep 10, 2026
As a transition zone between open road environments and enclosed tunnel spaces, urban tunnel entrances undergo rapid variations in spatial structure, lighting conditions, and traffic-related semantic information over short distances. These …
- Data-Driven Risk Fields for Safer End-to-End Autonomous DrivingYuanxin Tian, Zhiyuan Liu, Jinhao Li, Liangfan Zhu et al. · arXiv · Sep 9, 2026
Safety is a fundamental requirement for autonomous driving, yet existing end-to-end driving models still lack explicit risk-aware learning capacities. Existing rule-based risk models provide interpretable safety priors, yet their absolute r…
- Data-Driven Risk Fields for Safer End-to-End Autonomous DrivingYuanxin Tian, Zhiyuan Liu, Jinhao Li, Zhenhua Xu et al. · arXiv · Sep 9, 2026
Safety is a fundamental requirement for autonomous driving, yet existing end-to-end driving models still lack explicit risk-aware learning capacities. Existing rule-based risk models provide interpretable safety priors, yet their absolute r…
- CLFTv2: Efficient Camera-LiDAR Fusion for Semantic Segmentation via Hierarchical Feature PyramidsToomas Tahves, Mauro Bellone, Raivo Sell · arXiv · Sep 9, 2026
Semantic segmentation for autonomous driving requires reliable detection of vulnerable road users (VRUs) despite heavy class imbalance. We introduce CLFTv2, a hierarchical camera-LiDAR fusion framework replacing global ViT attention with a …
- A Risk-Sensitive and Uncertainty-Aware Decision-Making and Control Framework for Safe and Robust Autonomous DrivingZhuoren Li, Ran Yu, Weiqi Zhang, Ming Liu et al. · arXiv · Sep 9, 2026
Reinforcement learning (RL) has demonstrated considerable potential for autonomous driving decision-making. However, its deployment in urban autonomous driving, particularly at highly interactive unsignalized intersections, remains challeng…
- Effects of augmented reality landmark visualization on incidental spatial knowledge acquisition in autonomous driving: a virtual reality experimentJiayan Zhao, Muxu Wang, Rui Li · Frontiers in Virtual Reality · Sep 9, 2026
Introduction The proliferation of autonomous driving raises concerns about the psychological and behavioral adaptations of future drivers. One emerging challenge is the potential degradation of spatial knowledge due to reduced navigation an…
- PlannerForge: LLM Agents for Scenario-Based Testing of Motion Planners in Autonomous DrivingYuan Gao, Sebastian Müller, Mattia Piccinini, Marc Kaufeld et al. · arXiv · Sep 8, 2026
Ensuring the safety of autonomous driving is a critical challenge. Scenario-based testing is a systematic process used to validate Autonomous Driving Systems (ADSs), but it remains a fragmented modular pipeline in which scenario generation,…
- DCLP++: Learning to Navigate with Footprint Clearance and Relative MotionShanze Wang, Wei Zhang · arXiv · Sep 8, 2026
We present DCLP++, a local navigation frameworkthat uses footprint clearance as the geometric basis for studying relative motion features in dynamic environments. Each valid LiDAR return is mapped to its shortest Euclidean distance from the…
- Quantifying the “Mechanicalness” of Autonomous Trajectory Tracking: A Real-Vehicle Comparison with Human DriversMei Cao, Xinjian Yuan, Zhaona Lu, Yanlun Ren et al. · Vehicles · Sep 7, 2026
Autonomous driving systems often exhibit trajectory tracking behavior that differs markedly from human drivers, a phenomenon intuitively described as "mechanicalness.'' This study moves beyond the traditional focus on tracking accuracy to s…
- SCENELANG: A language-driven informatics framework for multi-modal scene understanding and generation in autonomous driving simulationXin Li, Xiangyang Hu, Leyao Wang, Ruipeng Tong · Advanced Engineering Inform... · Sep 6, 2026
- Vestibular time constant and individual susceptibility to motion sickness in real-world drivingSeonghyun Kim, Jaesik Yang, Sung Kwang Hong, M. Ercan Altinsoy · Scientific Reports · Sep 6, 2026
Abstract Motion sickness is an important challenge for the acceptance of autonomous vehicles. Although the Motion Sickness Susceptibility Questionnaire (MSSQ) is widely used, it relies on retrospective self-report and does not directly capt…
- CrossDepth: Geometry-Constrained Attention for Generalizable Multi-View Surround Depth EstimationSamer Abualhanud, Max Mehltretter · arXiv · Sep 4, 2026
Reliable 3D understanding of the surrounding environment is a core requirement for autonomous driving. Multi-view surround camera rigs provide broad scene coverage, but the spatially adjacent images typically overlap only minimally. Consequ…
- FIRE-LIVWO: Robust LiDAR-Inertial-Visual-Wheel Odometry via Failure-Immune mmWave Radar EnhancementKun Hu, Menggang Li, Kaidi Wu, Zhiwen Jin et al. · arXiv · Sep 4, 2026
Achieving robust SLAM in large-scale underground coal mines with complex structures and severe degeneracies remains highly challenging. Dense smoke and dust cause substantial loss of visual information and degrade LiDAR point-cloud features…
- One Diffusion Model, Two Roles: Guided Trajectory Planning and Safety-Critical Scenario Generation in Closed-Loop SimulationArka Pal, Rajesh Kumar, Hannes Eriksson, Rémi Lacombe et al. · arXiv · Sep 4, 2026
Diffusion probabilistic models can capture the multi-modal, interaction-rich distribution of joint future trajectories in driving scenes. We show that a single pretrained diffusion traffic model can serve two complementary roles in the auto…
- OmniTraj: Pre-training on heterogeneous data for adaptive and zero-shot human trajectory predictionYang Gao, Po‐Chien Luan, Kaouther Messaoud, Lan Feng et al. · Transportation Research Par... · Sep 4, 2026
Accurate trajectory prediction of vulnerable road users is a cornerstone of safe autonomous driving and intelligent transportation systems. While large-scale pre-training has advanced this field, achieving robust zero-shot generalization re…
- A Low-Cost, Open Platform for End-to-End Autonomous Driving on a Miniature Ackermann VehicleGustavo Claudio Karl Couto, Eric Aislan Antonelo, Gabriel George Zipperer · arXiv · Sep 3, 2026
This paper presents a low-cost, open experimental platform for research in end-to-end autonomous driving with miniature Ackermann vehicles. The platform combines a physical vehicle, a printed urban track, data collection tools, trajectory r…
- Corner Cases: Headland Coverage Path Planning for Autonomous Driving in Arable FarmingRiikka Soitinaho, Timo Oksanen · arXiv · Sep 3, 2026
This paper presents a new method for headland coverage path planning for arable fields. Several earlier approaches suggest covering the headland with nested polygons and smooth turns, however, covering the field corners entirely requires ma…
- Continuous Actions from Discrete Minds: Latent-Aligned Planning for End-to-End Autonomous DrivingRuoyu Yao, Yusen Xie, Qingzhao Liu, Pei Liu et al. · arXiv · Sep 3, 2026
Bridging the gap between the discrete reasoning of Vision-Language Models and the continuous, physics-constrained nature of autonomous driving remains a significant challenge. In this work, we introduce LaPla, a unified Vision-Language-Acti…
- RoughSense: Lightweight Terrain-Induced Rover Vibration Prediction Using Point Clouds and IMU FeedbackGabriel Manuel Garcia, Stephanie Aravecchia, Miguel Angel Olivares-Mendez · arXiv · Sep 3, 2026
Autonomous navigation in space requires reliable terrain assessment for safe operations, especially in underground environments with limited communication, computing resources, and power budget. This paper presents a lightweight method for …
- From Grey Infrastructure to Ecological Void: A Study on the Dynamical Time Density Structure of “Taigyoun Space” in Autonomous Driving EnvironmentsTaig Youn Cho, Xiao Yu Xiao, In Young Cho · Architectural research · Sep 3, 2026
Abstract Modern urban streets, largely built on Cartesian orthogonal grids, are geometrically inefficient. Traffic signals further interrupt movement, creating “voids of time” and cutting effective road utility to below 50%. These inefficie…
- Toward Robust LiDAR Semantic Segmentation for Real-World Deployment: Evaluation under Coarse Labels, Adverse Conditions, and Domain ShiftsSamir Abou Haidar, Alexandre Chariot, Mehdi Darouich, Cyril Joly et al. · arXiv · Sep 2, 2026
LiDAR-based semantic segmentation is a core perception module for autonomous vehicles and mobile robots. Despite the strong performance of recent state-of-the-art methods on standard benchmarks, existing evaluation protocols remain focused …
- From Proxy Learning to Driving Decisions: A Transfer-Based Framework for Evaluating Future-Aware Autonomous Driving PlannersYikai Wu · arXiv · Sep 2, 2026
Future-aware representations and world models are increasingly used in proposal-based autonomous-driving planners to improve trajectory selection. However, improvements in proxy objectives or restricted subsets are often interpreted as plan…
- Pre-Lane-change Signal in Transitional Autonomous Vehicles: Results from Controlled ExperimentsZeyu Mu, Danjue Chen, Abhinav Sharma, George F. List · arXiv · Sep 2, 2026
This paper investigates how a production transitional autonomous vehicle (tAV) develops and executes mandatory lane-change decisions. Using 150 controlled mandatory lane changes from the NC-tALC experiments, the study examines whether the e…
- CrashDiffuser: VLM-Guided Collision Intent Reasoning for Fine-Grained Safety-Critical Traffic Scenario GenerationShucheng Zhang, Yuang Zhang, Bingzhang Wang, Muhammad Monjurul Karim et al. · arXiv · Sep 2, 2026
Generating safety-critical scenarios is essential for evaluating autonomous driving systems. However, existing generators primarily focus on inducing collisions and offer limited control over where contact occurs on the target vehicle. In t…