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
- Assuring Learning-Enabled Cyber-Physical Systems with Foundation Models: A Neuro-Symbolic Agenda for Testing, Verification, and Runtime AssuranceXi Zheng, Ivan Ruchkin, Hong Jin Kang, Tevfik Bultan et al. · arXiv · Oct 29, 2026
Learning-enabled cyber-physical systems (CPS), including autonomous vehicles and UAVs, increasingly incorporate foundation models, yet fragmented assurance practices provide insufficient support for system-level guarantees. We argue that re…
- PriorMaskMap: Robust Online Vectorized Map Construction with Biased PriorsHaoming Xu, Wei Li, Yu Hu · arXiv · Oct 29, 2026
Online vectorized map construction provides autonomous vehicles with essential, real-time semantic and geometric scene understanding. While leveraging prior maps presents an opportunity to improve accuracy, they are often biased due to outd…
- GOFish: Full Field-of-View Gaussian Splatting and Mesh ExtractionAllen Tu, Meher Gitika Karumuri, Shifan Zhu, Hailing Wang et al. · arXiv · Oct 27, 2026
Robots, autonomous vehicles, and consumer 360° cameras use fisheye lenses for wide fields of view (FoVs). Simulation-ready digital twins require photorealistic rendering across the full FoV and an aligned collision mesh. However, prior fish…
- Leveraging Distributed Sensing and Hyperdimensional Computing for Non-Line-of-Sight Passive Object SensingPlacido Mursia, Marco Rossanese, Francesco Devoti, Adrian Lendinez Ibanez et al. · arXiv · Oct 27, 2026
In smart factory environments, passive entities such as humans and movable obstacles may interfere with autonomous robot operations, posing significant safety risks. Detecting potential conflicts between robots and entities outside their fi…
- AuRaSim: A Ray-Tracing Based Automotive FMCW Radar Simulator for Dynamic ScenariosZhaoze Wang, Changxu Zhang, Tai Fei, Christopher Grimm et al. · arXiv · Oct 27, 2026
Modern simulators can generate synthetic camera and LiDAR data with accurate annotations for downstream tasks. In contrast, automotive radar simulation remains less mature because it requires not only a 3D engine to model dynamic objects in…
- KEPT: Conformal Keepouts Kept in Planning for Enclosed-Space Navigation in Degraded SensingEric Minwoo Kim, Jong-Kook Kim · arXiv · Oct 27, 2026
Autonomous vehicles in enclosed spaces such as tunnels and mines rely on range maps that smoke, dust and fog make inaccurate. Conformal prediction calibrates a keepout around the mapped walls that covers the true unsafe set at a chosen prob…
- FastBEVFusion: Simple Multi-Modal Fusion for 3D Object Detection at 50 FPSTom Sanitz, Emre Gülsoylu, Simone Frintrop, Christian Wilms · arXiv · Oct 27, 2026
Reliable real-time 3D object detection based on LiDAR and camera data is critical for safety in autonomous driving, where systems must accurately perceive their surroundings with minimal latency. Many state-of-the-art systems achieve high-q…
- Integrated Design and Reproducible Feasibility Analysis of a Four-Wheel Rover with Packet-Commanded Imaging, LiDAR Ranging, and Learning-Assisted Target RecognitionSabik Bin Sultan, Shafi Bin Sultan, Safwan Sadad, Aranya Abeer Khan Prapya et al. · arXiv · Oct 27, 2026
This study develops an integrated, reproducible design assessment for a four-wheel educational rover intended for the high-school remote-control division of the 2027 NASA Human Exploration Rover Challenge. The architecture combines commerci…
- Making Self-Driving Laboratories Auditable:A Unified Framework for Hybrid Actions,Measurements, and Safe ExecutionZihan Zhang, Zeyu Wu, Xin Zhang, Mingyu Luo et al. · arXiv · Oct 27, 2026
Self-driving laboratories (SDLs) are laboratory systems that couple experimental planning, automated execution, and measurement feedback in a closed loop. Integrating flexible robot control with the typed application programming interfaces …
- A new method for detecting aerosols: combining atmospheric detection LiDAR technology with intelligent driving technologyHao Yang, Xiaomeng Zhu, Duoyang Qiu, Xianyang Li et al. · Atmospheric measurement tec... · Oct 27, 2026
Abstract. The existing aerosol mobile detection system has problems such as over-reliance on labor power and difficulty in conducting continuous operations in toxic and polluted environments. This paper presents a new method for detecting a…
- Compatibility and future-proof testing for multi-agent systemsYueshan Li, Lorenzo Fiaschi, Andrea Censi, Emilio Frazzoli · arXiv · Oct 26, 2026
Independently developed autonomous agents, such as autonomous vehicles, must guarantee joint compatibility, such as safety and task-completion requirements, when they operate in a shared environment. Existing methods require a centrally des…
- Closed-Loop Aware Planning via Imitation-Free Speed Scoring for End-to-End Autonomous DrivingEmad Aghajanzadeh, Thomas Schwarzfischer, Marc Kaufeld, Moritz Thoma et al. · arXiv · Oct 26, 2026
End-to-end autonomous driving has predominantly relied on open-loop imitation learning for training, which presents two limitations. First, expert demonstrations show only one behavior per scenario, so the model cannot learn alternative val…
- OSWAM: An Effective World Action Model with One-Step Action GenerationGuowen Zhang, Liyi Chen, Xu Hu, Pengfei Wang et al. · arXiv · Oct 26, 2026
Direct-policy World Action Models (WAM) have demonstrated the benefits of decoupling action generation from explicit future visual prediction for efficient inference in autonomous driving and embodied control. However, they still require te…
- VPR-Space: A Benchmark for Visual Place Recognition in Space Analog DomainsRichard Fechner, Peer Neubert · arXiv · Oct 26, 2026
Visual Place Recognition (VPR) is an important means for loop closure detection in visual Simultaneous Localization and Mapping (SLAM). While state-of-the-art VPR and SLAM approaches excel in urban and feature-rich natural environments, the…
- Revisiting Direct Control: A Field Evaluation of Sensor Fusion Efficacy in Teleoperating Full-Scale Autonomous Vehicles via Bird's Eye ViewStanisław Kuczma, Sławomir K. Tadeja, Michał R. Nowicki · arXiv · Oct 26, 2026
In autonomous driving, robot teleoperation serves as a critical safety fallback mechanism, requiring operators to assume direct control in the event of system failure. While recent research has pivoted toward high-level supervisory control …
- DriveUniTok: A Unified Multimodal Tokenizer for Driving World-Action ModelsJingbo Xu, Hanchao Leng, JiaHui Huang, Hanbing Li et al. · arXiv · Oct 26, 2026
World models are emerging as a fundamental component of policy learning for real-world agents, enabling agents to predict future world states and plan actions within a learned representation of the dynamic environment. Existing approaches, …
- Cognitive and mental state-aware autonomous driving with multi-task electroencephalography-based deep learning framework for hazard perception, trust prediction, cognitive load estimation, and brain–computer interface integrationI. Mohamed Shiek Mothi, U. Sabura Banu, M. Mohamed Ismail · Engineering Applications of... · Oct 26, 2026
- End-to-End QoS Guarantee Techniques for Autonomous Driving Application Services in the SDN-based VNDN EnvironmentHuhnkuk Lim · Journal of the Institute of... · Oct 26, 2026
일반 차량과 달리 자율주행차량 응용 서비스는 매우 높은 수준의 QoS 요구사항을 종단 간 안정적으로 만족시켜 주어야 하나, 동적 차량 네트워크 환경하에 자율주행 응용 서비스를 위한 종단 간 QoS 지원 기술 연구는 전 세계적으로 극히 미비한 상황이다. 한편 완전 자율주행을 위해 차량 대 차량 통신(V2V), 차량 대 인프라 통신(V2I) 등을 이용한 차량 동적 네트워크의 생성 및 유지는 필수적이나 기존 VANET은 위치 중심 …
- IntNet: A Communication-Driven Multi-Agent Reinforcement Learning Framework for Cooperative Autonomous DrivingLeandro Parada, Kevin Yu, Panagiotis Angeloudis · arXiv · Oct 25, 2026
Achieving safety in autonomous driving through Multi-Agent Reinforcement Learning (MARL) is a critical yet challenging task due to non-stationarity, partial observability, and the need for effective coordination among agents. Although earli…
- Casino Protocol 24(English Paper Specification) Research Preprint Specification / Academic Report Mathematical Implementation of Autonomous Social Governance and Infrastructure Redistribution in Casino Protocol 24 — 1% Creation Redistribution Fee, Genesis Activation Flag, Risk Escrow, and 3C³ Multidimensional Knowledge Evaluation Algorithm —Hideo Kajino · Zenodo (CERN European Organ... · Oct 25, 2026
Abstract With the rapid social implementation of advanced AI models and autonomous decentralized infrastructures, the local exploitation of electrical energy, insufficient redistribution to knowledge creators (humans), and the opacity of li…
- Graph-Based Spatial-Velocity Clustering and Tracking of Unlabeled Radar Point Clouds for Autonomous Vehicles with a Novel Temporal Precision MetricParisa Hatami, Hoang H. Nguyen, Maged Shoman, Mina Sartipi · Transportation Research Rec... · Oct 25, 2026
Robust and accurate perception of the environment is crucial for autonomous driving systems. Radar sensors offer unique advantages over LiDAR and cameras, such as robustness to adverse weather, long detection range, and instantaneous veloci…
- Multi‐Stage Social Value Orientation‐Based Lane‐Changing Driving for Autonomous VehiclesNongrui Qin, Lei Cai, Yilang Luo, Ming Yue et al. · Advanced Intelligent Systems · Oct 25, 2026
While intelligent driving systems are being gradually deployed on public roads, they still face numerous practical challenges. Among these, the hybrid traffic environment—comprising both autonomous vehicles and human drivers—presents signif…
- Casino Protocol 24 Revised Version (English Translation) Research Preprint Specification / Academic Report Mathematical Implementation of Autonomous Social Governance and Infrastructure Redistribution in Casino Protocol 24 — 1% Creation Redistribution Fee, Designated Account-Linked Genesis Activation Flag, Risk Escrow, and 3C³ Multidimensional Knowledge Evaluation Algorithm —Hideo Kajino · Zenodo (CERN European Organ... · Oct 25, 2026
Abstract With the rapid social implementation of advanced AI models and autonomous decentralized infrastructures, the local exploitation of electrical energy, insufficient redistribution to knowledge creators (humans), and the opacity of li…
- C-DFF: Concept-Level Diagnostics for Mechanism Parity in Simulation-Based Validation of Autonomous Driving PerceptionDanial Safaei, Siddartha Khastgir, Matthew Higgins, Jeroen Ploeg et al. · arXiv · Oct 24, 2026
Simulation is widely used in autonomous-driving validation, but matching task outputs between real and synthetic images does not guarantee that a system relies on the same visual evidence. This creates a validation gap for transfer, especia…
- Robust Offset-Free Lane-Keeping Control Framework for Vision-Only Automated VehiclesDer-Hau Lee · arXiv · Oct 23, 2026
Achieving accurate, real-time lane-keeping control during high-speed cornering on large-curvature roads while ensuring robust vehicle stability is a critical challenge in autonomous driving. To address this challenge, this study developed a…
- An Adaptive Local Trajectory Planning Method for DWA Based on the ACT-R Cognitive MechanismLiwen Wang, Aijuan Li, Máté Zöldy, Wang Xibo et al. · International Journal of Ad... · Oct 23, 2026
To address the issues of fixed evaluation weights and the lack of historical experience utilization in the traditional Dynamic Window Approach (DWA) for autonomous vehicles in complex dynamic environments, this paper proposes an adaptive lo…
- Causal Analysis of Failures of Cyber-Physical Systems with Continuous InputsTom Yaacov, David A. Kelly, Khen Elimelech, Hana Chockler · arXiv · Oct 22, 2026
Modern autonomous Cyber-Physical Systems (CPSs), such as self-driving cars, operate in increasingly complex environments while expected to maintain high reliability. The black-box nature of many of these systems makes it impossible to fully…
- UP3D: Utilizing Pseudo Points to Enhance 3D Object DetectionYujian Mo, Yan Xiang Wu · International Journal of Pa... · Oct 22, 2026
LiDAR-based 3D object detection is a critical engineering component in autonomous driving systems, yet its performance is fundamentally constrained by the sparsity and range-dependent density of point clouds, especially under sparse LiDAR o…
- EDSANet: An Evolutionary Dual Self-Attention Network for Early Prediction of Lane-Change in Autonomous DrivingNasim Shahanwaj Kothiwale, N. Meenakshi, Nasim Husen Sayyad · Iranian Journal of Science ... · Oct 22, 2026
- Temporal Naive Bayes: an efficient probabilistic framework for real-time maneuver recognition and anomaly monitoring in autonomous drivingMurilo G. Correia, Álisson Assis Cardoso · PeerJ Computer Science · Oct 22, 2026
The capacity to anticipate and identify anomalous behavior remains fundamental to the safety and operational reliability of autonomous mobile systems. Yet temporal modeling approaches currently available tend to demand substantial computati…