Deep Reinforcement Learning for Autonomous Driving: A Survey

Kiran, B Ravi; Sobh, Ibrahim; Talpaert, Victor; Mannion, Patrick; Sallab, Ahmad A. Al; Yogamani, Senthil; Pérez, Patrick

doi:10.48550/arxiv.2002.00444

Cited by 27 publications

(33 citation statements)

References 88 publications

(97 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Automated and semi-automated vehicles are gaining popularity in assisting our daily transportation. There is a considerable amount of studies in the past decade focusing on autonomous driving applications [1]- [6]. Specifically, a large number of research activities based on deep learning have been conducted for advanced driving assistance systems (ADAS) and automated driving applications, aiming to automate as much of the driving task as possible.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

A Survey of Deep Reinforcement Learning Algorithms for Motion Planning and Control of Autonomous Vehicles

Ye¹,

Zhang

Pin³

et al. 2021

Preprint

View full text Add to dashboard Cite

In this survey, we systematically summarize the current literature on studies that apply reinforcement learning (RL) to the motion planning and control of autonomous vehicles. Many existing contributions can be attributed to the pipeline approach, which consists of many hand-crafted modules, each with a functionality selected for the ease of human interpretation. However, this approach does not automatically guarantee maximal performance due to the lack of a systemlevel optimization. Therefore, this paper also presents a growing trend of work that falls into the end-to-end approach, which typically offers better performance and smaller system scales. However, their performance also suffers from the lack of expert data and generalization issues. Finally, the remaining challenges applying deep RL algorithms on autonomous driving are summarized, and future research directions are also presented to tackle these challenges.

show abstract

Section: Introductionmentioning

confidence: 99%

“…On the other hand, reinforcement learning (RL) algorithms have been extensively applied to vehicle decision making and control problems [5], [6]. Specifically, RL is able to learn in a trial-and-error way and does not require explicit human labeling or supervision on each data sample.…”

Section: Introductionmentioning

confidence: 99%

A Survey of Deep Reinforcement Learning Algorithms for Motion Planning and Control of Autonomous Vehicles

Ye¹,

Zhang

Pin³

et al. 2021

Preprint

View full text Add to dashboard Cite

show abstract

“…According to [1], a general AD system is composed of several subsystems, including sensing, navigation, decision-making, planning, and control. The key challenge of the intersection scenario is the interaction between the autonomous driving vehicle(ADV) and social vehicles, which mainly possess challenges on the decisionmaking and control modules [2]. Since the behavioral intention of social vehicles is uncertain, the ADV is forced to negotiate and make decisions quickly under strong interactions, otherwise, traffic accidents are very likely to occur.…”

Section: Introductionmentioning

confidence: 99%

A Reinforcement Learning Benchmark for Autonomous Driving in Intersection Scenarios

Liu¹,

Zhang²,

Zhao³

2021

Preprint

View full text Add to dashboard Cite

In recent years, control under urban intersection scenarios becomes an emerging research topic. In such scenarios, the autonomous vehicle confronts complicated situations since it must deal with the interaction with social vehicles timely while obeying the traffic rules. Generally, the autonomous vehicle is supposed to avoid collisions while pursuing better efficiency. The existing work fails to provide a framework that emphasizes the integrity of the scenarios while being able to deploy and test reinforcement learning(RL) methods. Specifically, we propose a benchmark for training and testing RL-based autonomous driving agents in complex intersection scenarios, which is called RL-CIS. Then, a set of baselines are deployed consists of various algorithms. The test benchmark and baselines are to provide a fair and comprehensive training and testing platform for the study of RL for autonomous driving in the intersection scenario, advancing the progress of RL-based methods for intersection autonomous driving control. The code of our proposed framework can be found at https://github.com/liuyuqi123/ ComplexUrbanScenarios.

show abstract

“…5 Junbo Zhao is with Zhejiang University, Hangzhou, China. 6 Xiao-Yun Zhou is with PAII Inc., MD, USA. * corresponding author.…”

Section: Introductionmentioning

confidence: 99%

“…Hence, novel solutions are necessitated to provide better and safe healthcare service. Robotics has been a popular paradigm to automate many traditional manual tasks, for example, autonomous driving [4], [5], [6] and autonomous surgical operation [7], [8], [9]. Some robots have been developed and widely used for veinpuncture.…”

Section: Introductionmentioning

confidence: 99%

VeniBot: Towards Autonomous Venipuncture with Semi-supervised Vein Segmentation from Ultrasound Images

Chen,

Wang,

Lai

et al. 2021

Preprint

View full text Add to dashboard Cite

In the modern medical care, venipuncture is an indispensable procedure for both diagnosis and treatment. In this paper, unlike existing solutions that fully or partially rely on professional assistance, we propose VeniBot -a compact robotic system solution integrating both novel hardware and software developments. For the hardware, we design a set of units to facilitate the supporting, positioning, puncturing and imaging functionalities. For the software, to move towards a full automation, we propose a novel deep learning framework -semi-ResNeXt-Unet for semi-supervised vein segmentation from ultrasound images. From which, the depth information of vein is calculated and used to enable automated navigation for the puncturing unit. VeniBot is validated on 40 volunteers, where ultrasound images can be collected successfully. For the vein segmentation validation, the proposed semi-ResNeXt-Unet improves the dice similarity coefficient (DSC) by 5.36%, decreases the centroid error by 1.38 pixels and decreases the failure rate by 5.60%, compared to fully-supervised ResNeXt-Unet.

show abstract

Deep Reinforcement Learning for Autonomous Driving: A Survey

Cited by 27 publications

References 88 publications

A Survey of Deep Reinforcement Learning Algorithms for Motion Planning and Control of Autonomous Vehicles

A Survey of Deep Reinforcement Learning Algorithms for Motion Planning and Control of Autonomous Vehicles

A Reinforcement Learning Benchmark for Autonomous Driving in Intersection Scenarios

VeniBot: Towards Autonomous Venipuncture with Semi-supervised Vein Segmentation from Ultrasound Images

Contact Info

Product

Resources

About