Autonomous Driving
Overview
Autonomous driving studies how vehicles can sense their surroundings, anticipate other road users, and choose safe, effective actions in traffic. Systems range from modular stacks that connect camera, LiDAR, and radar perception to prediction and model-predictive control, to end-to-end policies trained with imitation learning, reinforcement learning, or vision-language and world models. Researchers evaluate these methods on datasets such as nuScenes, Waymo, and Argoverse, in simulators such as CARLA and nuPlan, and through physical vehicle tests. A central challenge is turning strong benchmark results into reliable closed-loop behavior across rare events, changing conditions, and real-world deployment constraints.
Latest papers
576 papers41 papers in the last four weeks, down 21% on the four weeks before. 0.3% of all new papers.
Visual Geometry Foundation-Aware Gaussians for Single-Frame Surround-View Driving Reconstruction
Cross-View Sequential Visual Localization with Spatio-Temporal Context Modeling for Autonomous Driving
Structure-Enhanced Features and Quality-Aware Dynamic Anchor Scoring for Robust Lane Detection
GeoRoute: Geometry-Aware Hybrid Inference for Traffic Future-Frame Prediction
DH-VLM: Dual-Horizon Cooperative Latent Reasoning for Autonomous Driving
UnsDrive: Towards Robust End-to-End Autonomous Driving in Unstructured Scenes
Can Webcam Gaze Constrain Mesa-Objectives in Driving Models? An Instrument Precision Analysis
From Operational Design Domain to Action: A Systematic Behavioral Taxonomy for Autonomous Driving
Scalable High-Speed Lateral Control for Single-Body and Articulated Autonomous Vehicles
Enhancing Autonomous Vehicle Navigation with a Clothoid-Based Lateral Controller
SimWAM: A Simple World Action Model for End-to-End Autonomous Driving
CMU-Drive and V2V-VLA: Cooperative Multi-agent Unified Driving with Reasoning Benchmark and Vehicle-to-Vehicle Vision-Language-Action Models
Game-Theoretic Inverse Reinforcement Learning for Modeling Competitive Human Driving: A Cut-in Prediction Study
NSF-HRPT: Neural Semantic Field meets Hierarchical Risk Perception Tree for Safety-Critical Scenario Assessment
Pivot-Centric Trajectory Prediction: Bridging Long Horizons via Dynamical Guidance
pivots'' and focusing on predicting pivot points along extended trajectories, we divide the long-term prediction task into short-term sub-tasks at various scales. Specifically, PCTP decouples the long-term trajectory predicting process into two processes: pivot prediction and pivot-based trajectory refinement. The pivot prediction process aims to utilize global map context and agent-to-agent interactions to identify these pivot points'', while the pivot-based trajectory refinement process focuses on local map details and refines the short-term trajectory based on predicted ``pivot points''. Compared with existing methods, PCTP provides more intermediate guidance while reducing compounding errors. Moreover, PCTP is a flexible approach that can be integrated into most state-of-the-art trajectory prediction models. Experimental results show that PCTP improves the prediction accuracy of leading models on both Argoverse I and Argoverse II datasets with minimal impact on model size. Specifically, PCTP combined with QCNet outperforms all published ensemble-free methods on the Argoverse II leaderboard at submission.