A Generalised Method for Adaptive Longitudinal Control Using Reinforcement Learning

Pathak, Shashank; Bag, Suvam; Nadkarni, Vijay

doi:10.1007/978-3-030-01370-7_37

Cited by 3 publications

(3 citation statements)

References 10 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The authors in [13] propose an end-to-end vision-based ACC solution based on deep RL using the double deep Q-networks method, and which is able to generate a better gap regulated as well as a smoother speed trajectory when compared to a traditional radar-based ACC or human-in-the-loop simulation. Also, the authors in [17] proposed an RL-based ACC solution that is capable of mimicking human-like behavior and is able to accommodate uncertainties, requiring minimal domain knowledge when compared to traditional non-RL-based ACCs in congested traffic scenarios in a crowded highway as well as countryside roads. The work in [26] evaluates the safety impact of ACCs in traffic oscillations on freeways also by using a modified version of IDM in order to simulate the car-following movements using Matlab2014b software, concluding that an ACC system can significantly improve safety only when parameter settings such as larger time gaps, smaller time delays, and larger maximum deceleration rates are maintained.…”

Section: Related Workmentioning

confidence: 99%

“…More than that, because ACCs are typically approached as a model-based controller design based on an Intelligent Driver Model (IDM), despite performing decently on highways, they lack the ability to adapt to environments or driving preferences, and thus, an RL-based ACC approach is seen as more favorable towards fully autonomous cars which can be fully trusted by humans. Some of the main reasons for this are the advantages of an RL-based ACC approach such as that it does not require a dataset and that training can be realized irrespective of the environment [17].…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Increasing the Safety of Adaptive Cruise Control Using Physics-Guided Reinforcement Learning

et al. 2021

View full text Add to dashboard Cite

This paper presents a novel approach for improving the safety of vehicles equipped with Adaptive Cruise Control (ACC) by making use of Machine Learning (ML) and physical knowledge. More exactly, we train a Soft Actor-Critic (SAC) Reinforcement Learning (RL) algorithm that makes use of physical knowledge such as the jam-avoiding distance in order to automatically adjust the ideal longitudinal distance between the ego- and leading-vehicle, resulting in a safer solution. In our use case, the experimental results indicate that the physics-guided (PG) RL approach is better at avoiding collisions at any selected deceleration level and any fleet size when compared to a pure RL approach, proving that a physics-informed ML approach is more reliable when developing safe and efficient Artificial Intelligence (AI) components in autonomous vehicles (AVs).

show abstract

Section: Related Workmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Increasing the Safety of Adaptive Cruise Control Using Physics-Guided Reinforcement Learning

et al. 2021

View full text Add to dashboard Cite

show abstract

“…Readers are referred to Scale (32) for a full list of those public selfdriving datasets, which are filtered by data type, traffic scenario diversity, and annotation. On the other hand, a plethora of research papers (33)(34)(35)(36)(37) have been proposed to accomplish mMP using different learning approaches. With all that being said, it is highly possible that mMP will be the future of AVs, for both level-2 commercial vehicles and the higher-level FSD cars according to the definition of the Society of Automotive Engineers.…”

mentioning

confidence: 99%

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

Zhou

Laval

Zhou

et al. 2021

Transportation Research Record

View full text Add to dashboard Cite

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

show abstract

How do drivers respond to driving risk during car-following? Risk-response driver model and its application in human-like longitudinal control

Zhao

Ren

Wang

2020

Accident Analysis & Prevention

View full text Add to dashboard Cite

A Generalised Method for Adaptive Longitudinal Control Using Reinforcement Learning

Cited by 3 publications

References 10 publications

Increasing the Safety of Adaptive Cruise Control Using Physics-Guided Reinforcement Learning

Increasing the Safety of Adaptive Cruise Control Using Physics-Guided Reinforcement Learning

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

How do drivers respond to driving risk during car-following? Risk-response driver model and its application in human-like longitudinal control

Contact Info

Product

Resources

About