Parallel Learning-Based Steering Control for Autonomous Driving

Self Cite

248

Interest in autonomous driving (AD) and intelligent vehicles (IVs) is growing at a rapid pace due to the convenience, safety, and economic benefits. Although a number of surveys have reviewed research achievements in this field, they are still limited in specific tasks, lack of systematic summary and research directions in the future. Here we propose a Survey of Surveys (SoS) for total technologies of AD and IVs that reviews the history, summarizes the milestones, and provides the perspectives, ethics, and future research directions. To our knowledge, this article is the first SoS with milestones in AD and IVs, which constitutes our complete research work together with two other technical surveys. We anticipate that this article will bring novel and diverse insights to researchers and abecedarians, and serve as a bridge between past and future.

Section: Future Directionsmentioning

confidence: 99%

Milestones in Autonomous Driving and Intelligent Vehicles: Survey of Surveys

Chen

Huang

et al. 2023

Self Cite

248

“…In the future, we plan to integrate the proposed two-stage approach with the cognitive world model to better generalize SDV trajectory planning. The world model [50] can be used to simulate the prediction of various possible traffic events during the driving process, provide the potential to evaluate planning behavior and ensure safe and reasonable trajectory planning in the actual system. In addition, the world model is updated through continuous learning based on empirical data to ensure the cognitive alignment of the world model with the real world.…”

Section: Ablation Studymentioning

confidence: 99%

Safety-Balanced Driving-Style Aware Trajectory Planning in Intersection Scenarios With Uncertain Environment

Chen

Tang²,

Dai

et al. 2023

This paper proposes a two-stage trajectory planning method for self-driving vehicles (SDVs) in intersection scenarios with uncertain social circumstances while considering other traffic participants, which are human-driving vehicles (HDVs) with different driving styles. The mixture-of-experts approach is first utilized to learn from human-driving trajectory data to construct a multimodal motion planner, which uses a Transformer to model the interactions between vehicles by explicitly considering their driving styles to facilitate the integrated network to achieve scene-consistent multimodal trajectory prediction and candidate trajectory generation. Second, based on the generated trajectories for the SDV and the predicted trajectories for the other HDVs, each candidate planning trajectory is evaluated via a safety-balanced value function. After that, the trajectory with the highest value is selected for implementation. Such a method plans a safe and efficient driving trajectory in complex and uncertain scenarios. The experimental results demonstrate the efficiency and effectiveness of the designed method as well as the robustness and reasonableness of the SDVs' maneuver decisions at an intersection considering the behavioral dynamics of HDVs.

“…Moreover, the automatic execution of smart contracts reduces the need for manual handling and management, thereby enhancing the timeliness of decision-making. This can be further integrated with advanced AI technologies exemplified by foundation models [26], and intelligent testing methods represented by scenario engineering [27]- [29], to ensure the optimality of decisions.…”

Section: The Characteristics Of Dao-secured V2x Infrastructuresmentioning

confidence: 99%

The Road Ahead: DAO-Secured V2X Infrastructures for Safe and Smart Vehicular Management

Dai,

Vallati,

Guo

et al. 2023

Vehicle-to-Everything (V2X) technology relies on wireless communication and coordination, aiming to improve road safety and traffic efficiency by orchestrating the interaction among the vehicles, infrastructures, and various entities. However, existing organizational and operational forms of V2X infrastructures encounter significant challenges, such as the capability to guarantee communication security, privacy, and efficiency especially when a centralized management system is used. The emerging Decentralized Autonomous Organizations and Operations (DAOs) present a solution to these challenges. DAOs embed managerial and operational protocols within a blockchain via smart contracts, facilitating smooth and efficient management of organizations without the necessity for centralized oversight. This letter introduces DAOs into the coordination of V2X infrastructures. Through a tripartite functional architecture including organization, coordination, and execution, we can achieve intelligent collaborative management among road infrastructures and vehicles. The DAO-secured V2X infrastructures are anticipated to augment the safety and efficiency of vehicular management in complex road scenarios, holding applicable potential for developing the intelligent roadways of tomorrow.