Autonomous driving (AD) endows vehicles with the capability to drive partly or entirely without human intervention. AD agents generate driving policies based on online perception results, which are crucial to the realization of safe, efficient, and comfortable driving behaviors, particularly in high-dimensional and stochastic traffic scenarios. Currently, deep reinforcement learning (DRL) techniques to derive and validate AD policies have witnessed vast research efforts and have shown rapid development in recent years. However, a comprehensive interpretation and evaluation of their strengths and limitations concerning the full-stack AD tasks remain uncharted. This paper presents a survey of this body of work, which is conducted at three levels. First, it analyzes the multi-level AD task characteristics and delves deeply into the current DRL methodologies primarily employed in AD. Second, a taxonomy of the literature studies is constructed from the system perspective, identifying six modes of DRL model integration into an AD architecture that span the entire spectrum of AD policy processes, from perception understanding and decision-making to motion control, as well as verification and validation. Each literature review comprehensively encompasses the main elements of designing such a system, including modeling partially observable environments, state and action spaces, reward structuring, and the design and training methodologies of neural network models. Finally, an in-depth foresight is conducted on how the eight critical issues of AD application development are addressed by the DRL models tailored for real-world AD challenges.

Local mapping is valuable for many real-time applications of intelligent vehicle systems. Multivehicle cooperative local mapping can bring considerable benefits to vehicles operating in some challenging scenarios. In this paper, we introduce a method of occupancy grid map merging, dedicated to multivehicle cooperative local mapping purpose in outdoor environments. In a general map merging framework, we propose an objective function based on occupancy likelihood and provide some concrete procedures designed in the spirit of genetic algorithm to optimize the defined objective function. Based on the introduced method, we further describe a strategy of indirect vehicle-to-vehicle (V2V) relative pose (RP) estimation, which can serve as a general solution for multivehicle perception association. We present a variety of experiments that validate the effectiveness of the proposed occupancy grid map merging method. We also demonstrate several useful application examples of the indirect V2V RP estimation strategy.

Vehicle-to-Everything (V2X) communication enhances the capability of autonomous driving through better safety, efficiency, and comfort. In particular, sensor data sharing, known as cooperative perception, is a crucial technique to accommodate vulnerable road users in a cooperative intelligent transport system (ITS). In this paper, we describe a roadside perception unit (RSPU) that combines sensors and roadside units (RSUs) for infrastructure-based cooperative perception. We propose a software called AutoC2X that we designed to realize cooperative perception for RSPUs and vehicles. We also propose the concept of networked RSPUs, which is the inter-connection of RSPUs along a road over a wired network, and helps realize broader cooperative perception. We evaluated the RSPU system and the networked RSPUs through a field test, numerical analysis, and simulation experiments. Field evaluation showed that, even in the worst case, our RSPU system can deliver messages to an autonomous vehicle within 100 ms. The simulation result shows that the proposed priority algorithm achieves a wide perception range with a high delivery ratio and low latency, especially under heavy road traffic conditions.

This paper explores the potential for communication-efficient federated learning (FL) in modern distributed systems. FL is an emerging distributed machine learning technique that allows for the distributed training of a single machine learning model across multiple geographically distributed clients. This paper surveys the various approaches to communication-efficient FL, including model updates, compression techniques, resource management for the edge and cloud, and client selection. We also review the various optimization techniques associated with communication-efficient FL, such as compression schemes and structured updates. Finally, we highlight the current research challenges and discuss the potential future directions for communication-efficient FL.

Big data is a rapidly growing field, and new developments are constantly emerging to address various challenges. One such development is the use of federated learning for recommendation systems (FRSs). An FRS provides a way to protect user privacy by training recommendation models using intermediate parameters instead of real user data. This approach allows for cooperation between data platforms while still complying with privacy regulations. In this paper, we explored the current state of research on FRSs, highlighting existing research issues and possible solutions. Specifically, we looked at how FRSs can be used to protect user privacy while still allowing organizations to benefit from the data they share. Additionally, we examined potential applications of FRSs in the context of big data, exploring how these systems can be used to facilitate secure data sharing and collaboration. Finally, we discuss the challenges associated with developing and deploying FRSs in the real world and how these challenges can be addressed.

Existing potential functions (PFs) utilized in autonomous vehicles mainly focus on solving the path-planning problems in some conventional driving scenarios; thus, their performance may not be satisfactory in the context of emergency obstacle avoidance. Therefore, we propose a novel model predictive path-planning controller (MPPC) combined with PFs to handle complex traffic scenarios (e.g., emergency avoidance when a sudden accident occurs). Specifically, to enhance the safety of the PFs, we developed an MPPC to handle an emergency case with a sigmoid-based safe passage embedded in the MPC constraints (SPMPC) with a specific triggering analysis algorithm on monitoring traffic emergencies. The presented PF-SPMPC algorithm was compiled in a comparative simulation study using MATLAB/Simulink and CarSim. The algorithm outperformed the latest PF-MPC approach to eliminate the severe tire oscillations and guarantee autonomous driving safety when handling the traffic emergency avoidance scenario.