Edge-Assisted V2X Motion Planning and Power Control Under Channel Uncertainty

Article Computer Science, Hardware & Architecture

Federated Deep Learning Meets Autonomous Vehicle Perception: Design and Verification

Shuai Wang et al.

Summary: In order to address the challenges of rare and occluded perception in open driving scenarios, a federated learning assisted connected autonomous vehicle (FLCAV) is proposed, which establishes federated deep neural networks (DNNs) from distributed data captured by vehicles and road sensors. Networking and training frameworks are presented to solve the problems of network management and sensor deployment, respectively.

IEEE NETWORK (2023)

Add to Collection

Article Engineering, Civil

On-Ramp Merging Strategies of Connected and Automated Vehicles Considering Communication Delay

Yukun Fang et al.

Summary: Improper handling of on-ramp merging can lead to decreased traffic efficiency and increased collision risk. Cooperative control for connected and automated vehicles (CAVs) can mitigate these negative effects and improve safety and traffic efficiency.

IEEE TRANSACTIONS ON INTELLIGENT TRANSPORTATION SYSTEMS (2022)

Add to Collection

Article Engineering, Civil

Collision Avoidance Predictive Motion Planning Based on Integrated Perception and V2V Communication

Shiyao Zhang et al.

Summary: Autonomous vehicles play an important role in improving transportation operations and services. However, current research often neglects the necessary interaction between different approaches. To address this problem, we propose a motion planning strategy for autonomous vehicles based on motion prediction and V2V communication, and learn optimal motion planning using deep learning techniques.

IEEE TRANSACTIONS ON INTELLIGENT TRANSPORTATION SYSTEMS (2022)

Add to Collection

Article Engineering, Electrical & Electronic

Massive Access in Secure NOMA Under Imperfect CSI: Security Guaranteed Sum-Rate Maximization With First-Order Algorithm

Zongze Li et al.

Summary: This article introduces a novel approach to address channel uncertainties in secure NOMA schemes by transforming probabilistic constraints and decoupling variables. This method maximizes the total rate while enhancing security.

IEEE JOURNAL ON SELECTED AREAS IN COMMUNICATIONS (2021)

Add to Collection

Article Computer Science, Information Systems