The automotive industry's transformative conver-gence of cutting-edge technologies, such
as the Internet of Things (loT), electronic voice assistants, and custom APls, have paved the …

This paper explores the emerging knowledge-driven autonomous driving technologies. Our
investigation highlights the limitations of current autonomous driving systems, in particular …

The construction of transportation 5.0 or the so-called society-centered intelligent
transportation systems (ITS) has aroused higher requirements for the intelligent sensing …

Pedestrian and Vehicle Detection (PVD) is important to auto-driving. However, existing deep-
network-based PVD methods suffer from a low inference speed due to large redundancy …

Accurate position is important for intelligent vehicles especially in unknown environments
without prior information. Light Detection and Ranging (LiDAR) has shown great potential in …

Robust Semantic segmentation based on visual images is an effective method for intelligent
vehicles to perceive road scenes. It can help intelligent vehicles quickly obtain the positions …

As one of the most fundamental topics in reinforcement learning (RL), sample efficiency is
essential to the deployment of deep RL algorithms. Unlike most existing exploration …

Test-time adaptation (TTA) has been proven to effectively improve the adaptability of deep
learning semantic segmentation models facing continuous changeable scenes. However …

Autonomous driving is no more a topic of science fiction. Advancement of autonomous
driving technologies are now reliable. Effectively harnessing the information is essential for …

Intelligent Transportation Systems (ITS) is an evolving technology that has many
applications to improve traffic safety and management. The utilization of advanced sensors …