A Novel Direct Trajectory Planning Approach Based on Generative Adversarial Networks and Rapidly-Exploring Random Tree

Zhao, Cong; Zhu, Yifan; Du, Yuchuan; Liao, Feixiong; Chan, Ching-Yao

doi:10.1109/tits.2022.3164391

Cited by 51 publications

(24 citation statements)

References 31 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In our future research, we plan to extend driving scenarios with lane-changing behavior. Although lane changing does not have the highest priority in conservative driving strategies, it remains a challenging task with the requirements of safe and comfortable trajectory planning [25,30]. Meanwhile, the proposed intelligent speed control approach can be applied to several AVs with multi-agent RL and used to improve the driving performance in an environment of fully or partially AVs [31].…”

Section: Discussionmentioning

confidence: 99%

Safe, Efficient, and Comfortable Autonomous Driving Based on Cooperative Vehicle Infrastructure System

Chen

Zhao

Jiang

et al. 2023

IJERPH

Self Cite

View full text Add to dashboard Cite

Traffic crashes, heavy congestion, and discomfort often occur on rough pavements due to human drivers’ imperfect decision-making for vehicle control. Autonomous vehicles (AVs) will flood onto urban roads to replace human drivers and improve driving performance in the near future. With the development of the cooperative vehicle infrastructure system (CVIS), multi-source road and traffic information can be collected by onboard or roadside sensors and integrated into a cloud. The information is updated and used for decision-making in real-time. This study proposes an intelligent speed control approach for AVs in CVISs using deep reinforcement learning (DRL) to improve safety, efficiency, and ride comfort. First, the irregular and fluctuating road profiles of rough pavements are represented by maximum comfortable speeds on segments via vertical comfort evaluation. A DRL-based speed control model is then designed to learn safe, efficient, and comfortable car-following behavior based on road and traffic information. Specifically, the model is trained and tested in a stochastic environment using data sampled from 1341 car-following events collected in California and 110 rough pavements detected in Shanghai. The experimental results show that the DRL-based speed control model can improve computational efficiency, driving efficiency, longitudinal comfort, and vertical comfort in cars by 93.47%, 26.99%, 58.33%, and 6.05%, respectively, compared to a model predictive control-based adaptive cruise control. The results indicate that the proposed intelligent speed control approach for AVs is effective on rough pavements and has excellent potential for practical application.

show abstract

Section: Discussionmentioning

confidence: 99%

Safe, Efficient, and Comfortable Autonomous Driving Based on Cooperative Vehicle Infrastructure System

Chen

Zhao

Jiang

et al. 2023

IJERPH

Self Cite

View full text Add to dashboard Cite

show abstract

“…Past research indicates that investment in transportation infrastructure can be signifcant for the economic development of the country. Accordingly, many countries consider transportation as their economic sector in budget planning [9]. Reference [10] analyzed the communications between transportation infrastructure, fnancial infuence, and economic growth in the G-20 countries from 1961 to 2016.…”

Section: Review Of Literaturementioning

confidence: 99%

A Framework to Assess the Correlation between Transportation Infrastructure Access and Economics: Evidence from Iran

Faghihinejad

Fard

Roshanghalb

et al. 2022

Mathematical Problems in Engineering

View full text Add to dashboard Cite

One of the most important impacts of access to transportation infrastructure is the economic and social well-being of residents. However, it is important to know, how much of an impact it has? Which of the access routes-road, rail, or air-has more impact? What methods can be used to assess this effect? Does this effect vary from country to country? This study attempts to provide a framework to examine the correlation between the access of a country’s cities (to various types of rail, air, and road transportation networks) and the economic and social parameters of its inhabitants. For this purpose, the connection of the city to the rail network was calculated by taking into account the distance in time between the city and the nearest station. A city’s road access is calculated by finding the average road distance of a city to other cities in that country. A city’s access to air traffic is calculated based on the weekly flights of that city’s airport (if that city has an airport). To evaluate the performance of the proposed framework, a case study is conducted in Iran. The results of the case study show that the access of cities to transportation networks strongly influences economic development and population size in Iran. Pearson’s correlation coefficients between transport infrastructure and economic growth and population size are 0.641 and 0.725, respectively. It was also found that among the transport networks, road transport is more correlated with economic development and unemployment rate of Iranian cities compared to other transport modes.

show abstract

“…Meanwhile, robustness and generalization cannot be ensured because the design of the controllers only considered limited road profile examples. To deal with such issues, neural networks were designed in controllers to learn the characteristics of the systems and control policy (Konoiko et al., 2019; C. Zhao, Zhu, et al., 2022). However, offline training requires a large number of labeled samples, and it is hard to label optimal control results (Ming et al., 2020).…”

Section: Introductionmentioning

confidence: 99%

A hierarchical framework for improving ride comfort of autonomous vehicles via deep reinforcement learning with external knowledge

Chen

Zhao

et al. 2022

Computer aided Civil Eng

Self Cite

View full text Add to dashboard Cite

Ride comfort plays an important role in determining the public acceptance of autonomous vehicles (AVs). Many factors, such as road profile, driving speed, and suspension system, influence the ride comfort of AVs. This study proposes a hierarchical framework for improving ride comfort by integrating speed planning and suspension control in a vehicle-to-everything environment. Based on safe, comfortable, and efficient speed planning via dynamic programming, a deep reinforcement learning-based suspension control is proposed to adapt to the changing pavement conditions. Specifically, a deep deterministic policy gradient with external knowledge (EK-DDPG) algorithm is designed for the efficient selfadaptation of suspension control strategies. The external knowledge of action selection and value estimation from other AVs are combined into the loss functions of the DDPG algorithm. In numerical experiments, real-world pavements detected in 11 districts of Shanghai, China, are applied to verify the proposed method. Experimental results demonstrate that the EK-DDPG-based suspension control improves ride comfort on untrained rough pavements by 27.95% and 3.32%, compared to a model predictive control (MPC) baseline and a DDPG baseline, respectively. Meanwhile, the EK-DDPG-based suspension control improves computational efficiency by 22.97%, compared to the MPC baseline, and performs at the same level as the DDPD baseline. This study provides a generalized and computationally efficient approach for improving the ride comfort of AVs.

show abstract

A Novel Direct Trajectory Planning Approach Based on Generative Adversarial Networks and Rapidly-Exploring Random Tree

Cited by 51 publications

References 31 publications

Safe, Efficient, and Comfortable Autonomous Driving Based on Cooperative Vehicle Infrastructure System

Safe, Efficient, and Comfortable Autonomous Driving Based on Cooperative Vehicle Infrastructure System

A Framework to Assess the Correlation between Transportation Infrastructure Access and Economics: Evidence from Iran

A hierarchical framework for improving ride comfort of autonomous vehicles via deep reinforcement learning with external knowledge

Contact Info

Product

Resources

About