In the landscape of technological innovation, autonomous racing is a dynamic and challenging domain that not only pushes the limits of technology, but also plays a crucial role in advancing and fostering a greater acceptance of autonomous systems. This paper thoroughly explores challenges and advances in autonomous racing vehicle design and performance, focusing on Roborace and the Indy Autonomous Challenge (IAC). This review provides a detailed analysis of sensor setups, architectural nuances, and test metrics on these cutting-edge platforms. In Roborace, the evolution from Devbot 1.0 to Robocar and Devbot 2.0 is detailed, revealing insights into sensor configurations and performance outcomes. The examination extends to the IAC, which is dedicated to high-speed self-driving vehicles, emphasizing developmental trajectories and sensor adaptations. By reviewing these platforms, the analysis provides valuable insight into autonomous driving racing, contributing to a broader understanding of sensor architectures and the challenges faced. This review supports future advances in full-scale autonomous racing technology.

Advanced vehicle control is a fundamental building block in the development of autonomous driving systems. Reinforcement learning (RL) promises to achieve control performance superior to classical approaches while keeping computational demands low during deployment. However, standard RL approaches like soft-actor critic (SAC) require extensive amounts of training data to be collected and are thus impractical for real-world application. To address this issue, we apply recently developed data-efficient deep RL methods to vehicle trajectory control. Our investigation focuses on three methods, so far unexplored for vehicle control: randomized ensemble double Q-learning (REDQ), probabilistic ensembles with trajectory sampling and model predictive path integral optimizer (PETS-MPPI), and model-based policy optimization (MBPO). We find that in the case of trajectory control, the standard model-based RL formulation used in approaches like PETS-MPPI and MBPO is not suitable. We, therefore, propose a new formulation that splits dynamics prediction and vehicle localization. Our benchmark study on the CARLA simulator reveals that the three identified data-efficient deep RL approaches learn control strategies on a par with or better than SAC, yet reduce the required number of environment interactions by more than one order of magnitude.

In the face of growing urban populations and the escalating number of vehicles on the roads, managing transportation efficiently and ensuring safety have become critical challenges. To tackle these issues, the development of intelligent control systems for vehicles is paramount. This paper presents a comprehensive study on vehicle control for collision avoidance, leveraging the power of Federated Deep Reinforcement Learning (FDRL) techniques. Our main goal is to minimize travel delays and enhance the average speed of vehicles while prioritizing safety and preserving data privacy. To accomplish this, we conducted a comparative analysis between the local model, Deep Deterministic Policy Gradient (DDPG), and the global model, Federated Deep Deterministic Policy Gradient (FDDPG), to determine their effectiveness in optimizing vehicle control for collision avoidance. The results obtained indicate that the FDDPG algorithm outperforms DDPG in terms of effectively controlling vehicles and preventing collisions. Significantly, the FDDPG-based algorithm demonstrates substantial reductions in travel delays and notable improvements in average speed compared to the DDPG algorithm.

This paper demonstrates the integration model-based design approaches or vehicle control, with validation in a freely available open-source simulator. Continued interest in autonomous vehicles and their deployment is driven by the potential benefits of their use. However, it can be challenging to transition new theoretical approaches into unknown simulation environments. Thus, it is critical for experts from other fields, whose insights may be necessary to continue to advance autonomy, to be able to create control applications with the potential to transition to practice. In this article, we will explain how to use the CAT Vehicle simulator and ROS packages to create and test vehicle controllers. The methodology of developing the control system in this article takes the approach of model-based design using Simulink, and the ROS Toolbox, followed by code generation to create a standalone C++ ROS node. Such ROS nodes can be integrated through roslaunch in the CAT Vehicle ROS package.

MTA-BME Lendület Machine Tool Vibration Research Group, Department of Applied Mechanics, Budapest University of Technology and Economics, Budapest 1111, Hungary (kiss a@mm.bme.hu). Abstract: Safe longitudinal control is discussed for a connected automated truck traveling behind a preceding connected vehicle. A controller is proposed based on control barrier function theory and predictor feedback for provably safe, collision-free behavior by taking into account the significant response time of the truck as input delay and the uncertainty of its dynamical model as input disturbance. The benefits of the proposed controller compared to control designs that neglect the delay or treat the delay as disturbance are shown by numerical simulations. Keywords: control, safety, time delay, disturbance, connected automated vehicle 1. INTRODUCTION Control systems are often subject to strict safety requirements that must be met before deployment in practice.

This work gives introduction to traffic control by connected automated vehicles. The influence of vehicle control on vehicular traffic and traffic control strategies are discussed and compared. It is highlighted that vehicle-to-everything connectivity allows connected automated vehicles to access the state of the traffic behind them such that feedback can be utilized to mitigate evolving congestions. Numerical simulations demonstrate that such connectivity-based traffic control is beneficial for smoothness and energy efficiency of highway traffic. The dynamics and stability of traffic flow, under the proposed controllers, are analyzed in detail to construct stability charts that guide the selection of stabilizing control gains.

Lecture: Self-Driving Cars (Prof. Andreas Geiger, University of Tübingen) Course Website with Slides, Lecture Notes, Problems and Solutions: https://uni-tuebingen.d

When humans play virtual racing games, they use visual environmental information on the game screen to understand the rules within the environments. In contrast, a state-of-the-art realistic racing game AI agent that outperforms human players does not use image-based environmental information but the compact and precise measurements provided by the environment. In this paper, a vision-based control algorithm is proposed and compared with human player performances under the same conditions in realistic racing scenarios using Gran Turismo Sport (GTS), which is known as a high-fidelity realistic racing simulator. In the proposed method, the environmental information that constitutes part of the observations in conventional state-of-the-art methods is replaced with feature representations extracted from game screen images. We demonstrate that the proposed method performs expert human-level vehicle control under high-speed driving scenarios even with game screen images as high-dimensional inputs. Additionally, it outperforms the built-in AI in GTS in a time trial task, and its score places it among the top 10% approximately 28,000 human players.

Connected and autonomous vehicles (CAVs) are promising due to their potential safety and efficiency benefits and have attracted massive investment and interest from government agencies, industry, and academia. With more computing and communication resources are available, both vehicles and edge servers are equipped with a set of camera-based vision sensors, also known as Visual IoT (V-IoT) techniques, for sensing and perception. Tremendous efforts have been made for achieving programmable communication, computation, and control. However, they are conducted mainly in the silo mode, limiting the responsiveness and efficiency of handling challenging scenarios in the real world. To improve the end-to-end performance, we envision that future CAVs require the co-design of communication, computation, and control. This paper presents our vision of the end-to-end design principle for CAVs, called 4C, which extends the V-IoT system by providing a unified communication, computation, and control co-design framework. With programmable communications, fine-grained heterogeneous computation, and efficient vehicle controls in 4C, CAVs can handle critical scenarios and achieve energy-efficient autonomous driving. Finally, we present several challenges to achieving the vision of the 4C framework.

Continuous innovations and advancements in communication technologies, as well as digital technologies coupled with price reduction of sensors, are constantly enhancing the level of automation in our day- to-day lives. Autonomous vehicles (AV), also known as self-driving, driverless, or robotic vehicles, are those in which some aspect of vehicle control is automated by the car. With technological advancements in external sensing, path planning, vehicle control, and more, innovations in autonomous and highly automated vehicle development are increasingly finding their way into consumer vehicles in the form of active safety, driver assistance systems, and limited automated driving features. Innovations in AV may fundamentally transform how the current transportation system works and change the way (and probably change our lives) in terms of how we travel. As is the case in all disruptions, AVs will bring slowdown and present new opportunities in the form of new business models.