Review of Learning-Based Longitudinal Motion Planning for Autonomous Vehicles: Research Gaps Between Self-Driving and Traffic Congestion

نویسندگان

چکیده

Self-driving technology companies and the research community are accelerating pace of use machine learning longitudinal motion planning (mMP) for autonomous vehicles (AVs). This paper reviews current state art in mMP, with an exclusive focus on its impact traffic congestion. The identifies availability congestion scenarios datasets, summarizes required features training mMP. For methods, major methods both imitation non-imitation surveyed. emerging technologies adopted by some leading AV companies, such as Tesla, Waymo, Comma.ai, also highlighted. It is found that: (i) industry has been mostly focusing long tail problem related to safety overlooked congestion, (ii) public self-driving datasets have not included enough scenarios, lack necessary input features/output labels train (iii) although reinforcement approach can integrate mitigation into goal, mMP method still behavior cloning, whose capability learn a congestion-mitigating remains be seen. Based review, study gaps development. Some suggestions future studies proposed: enrich data collection facilitate learning, incorporate combine efficiency safety-oriented technical route, domain knowledge from traditional car-following theory improve string stability

برای دانلود رایگان متن کامل این مقاله و بیش از 32 میلیون مقاله دیگر ابتدا ثبت نام کنید

ثبت نام

اگر عضو سایت هستید لطفا وارد حساب کاربری خود شوید

منابع مشابه

On-Road Motion Planning for Autonomous Vehicles

We present a motion planner for autonomous on-road driving, especially on highways. It adapts the idea of a on-road state lattice. A focused search is performed in the previously identified region in which the optimal trajectory is most likely to exist. The main contribution of this paper is a computationally efficient planner which handles dynamic environments generically. The Dynamic Programm...

متن کامل

Safe Motion Planning for Autonomous Driving

Self-driving cars have the potential to revolutionize transportation by making it cheaper, safer, and more efficient. In this thesis we describe a novel motion planning system, which translates high-level navigation goals into low-level actions for controlling a vehicle. Specifically, the motion planning system is responsible for choosing at each time step an appropriate velocity and steering a...

متن کامل

Sampling Based Motion Planning for Heavy Duty Autonomous Vehicles

The automotive industry is undergoing a revolution where the more traditional mechanical values are replaced by an ever increasing number of Advanced Driver Assistance Systems (ADAS) where advanced algorithms and software development are taking a bigger role. Increased safety, reduced emissions and the possibility of completely new business models are driving the development and most automotive...

متن کامل