State of the Field
Recent advancements in autonomous driving are increasingly focused on enhancing safety and efficiency through innovative frameworks and technologies. The integration of natural language processing with dynamic maps is enabling more intuitive human-vehicle interactions, while novel transformer architectures are streamlining end-to-end driving systems by compressing multi-camera data without sacrificing accuracy. Additionally, diffusion models are being harnessed for motion planning, offering robust solutions to safety challenges in uncertain environments. Techniques such as risk-aware world model predictive control are addressing the limitations of traditional imitation learning by allowing vehicles to make informed decisions without relying solely on expert demonstrations. Furthermore, the development of anomaly detection frameworks is improving the identification of rare, high-risk scenarios, crucial for Level 4 autonomous vehicles. Collectively, these efforts are paving the way for more reliable and adaptable autonomous driving systems, with significant implications for urban mobility and transportation safety.
Papers
1–10 of 14Driving on Registers
We present DrivoR, a simple and efficient transformer-based architecture for end-to-end autonomous driving. Our approach builds on pretrained Vision Transformers (ViTs) and introduces camera-aware reg...
Talk2DM: Enabling Natural Language Querying and Commonsense Reasoning for Vehicle-Road-Cloud Integrated Dynamic Maps with Large Language Models
Dynamic maps (DM) serve as the fundamental information infrastructure for vehicle-road-cloud (VRC) cooperative autonomous driving in China and Japan. By providing comprehensive traffic scene represent...
DualShield: Safe Model Predictive Diffusion via Reachability Analysis for Interactive Autonomous Driving
Diffusion models have emerged as a powerful approach for multimodal motion planning in autonomous driving. However, their practical deployment is typically hindered by the inherent difficulty in enfor...
CycleBEV: Regularizing View Transformation Networks via View Cycle Consistency for Bird's-Eye-View Semantic Segmentation
Transforming image features from perspective view (PV) space to bird's-eye-view (BEV) space remains challenging in autonomous driving due to depth ambiguity and occlusion. Although several view transf...
SToRM: Supervised Token Reduction for Multi-modal LLMs toward efficient end-to-end autonomous driving
In autonomous driving, end-to-end (E2E) driving systems that predict control commands directly from sensor data have achieved significant advancements. For safe driving in unexpected scenarios, these ...
PRAM-R: A Perception-Reasoning-Action-Memory Framework with LLM-Guided Modality Routing for Adaptive Autonomous Driving
Multimodal perception enables robust autonomous driving but incurs unnecessary computational cost when all sensors remain active. This paper presents PRAM-R, a unified Perception-Reasoning-Action-Memo...
IRL-DAL: Safe and Adaptive Trajectory Planning for Autonomous Driving via Energy-Guided Diffusion Models
This paper proposes a novel inverse reinforcement learning framework using a diffusion-based adaptive lookahead planner (IRL-DAL) for autonomous vehicles. Training begins with imitation from an expert...
SaFeR: Safety-Critical Scenario Generation for Autonomous Driving Test via Feasibility-Constrained Token Resampling
Safety-critical scenario generation is crucial for evaluating autonomous driving systems. However, existing approaches often struggle to balance three conflicting objectives: adversarial criticality, ...
Natural Language Instructions for Scene-Responsive Human-in-the-Loop Motion Planning in Autonomous Driving using Vision-Language-Action Models
Instruction-grounded driving, where passenger language guides trajectory planning, requires vehicles to understand intent before motion. However, most prior instruction-following planners rely on simu...
TaCarla: A comprehensive benchmarking dataset for end-to-end autonomous driving
Collecting a high-quality dataset is a critical task that demands meticulous attention to detail, as overlooking certain aspects can render the entire dataset unusable. Autonomous driving challenges r...