Highway Traffic Modeling and Decision Making for Autonomous Vehicle Using Reinforcement Learning

You, Changxi; Lǚ, Jianbo; Filev, Dimitar; Tsiotras, Panagiotis

doi:10.1109/ivs.2018.8500675

Cited by 41 publications

(21 citation statements)

References 18 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Besides, reinforcement learning is proved to be an effective way for decision-making problem. Interaction between the vehicles and the environment can be formulated as a Markov Decision Process (MDP), then Q-learning algorithm [58,59] can be performed to optimize the route recommendation results for real-time navigation.…”

Section: Machine Learning-based Route Recommendationmentioning

confidence: 99%

Wireless recommendations for Internet of vehicles: Recent advances, challenges, and opportunities

Luo

et al. 2020

Intell. and Converged Netw.

View full text Add to dashboard Cite

Internet of Vehicles (IoV) is a distributed network of connected cars, roadside infrastructure, wireless communication networks, and central cloud platforms. Wireless recommendations play an important role in the IoV network, for example, recommending appropriate routes, recommending driving strategies, and recommending content. In this paper, we review some of the key techniques in recommendations and discuss what are the opportunities and challenges to deploy these wireless recommendations in the IoV.

show abstract

Section: Machine Learning-based Route Recommendationmentioning

confidence: 99%

Wireless recommendations for Internet of vehicles: Recent advances, challenges, and opportunities

Luo

et al. 2020

Intell. and Converged Netw.

View full text Add to dashboard Cite

show abstract

“…For decision making, the action space is typically a set of discretized decision choices. You, et al [7] adopted Q-learning method for vehicle decision making in highway driving scenarios, where the agent learns to accelerate, brake, overtake and make turns. Mukadam, et al [8] employed deep reinforcement learning, with Q-mask technique, to learn a high-level policy for tactical decision making which they broke down into five actions, including no action, accelerate, decelerate, left lane change and right lane change. For driving control problems, a number of studies treated the control action space as discrete to simplify the problem or improve learning efficiency.…”

Section: Related Workmentioning

confidence: 99%

Continuous Control for Automated Lane Change Behavior Based on Deep Deterministic Policy Gradient Algorithm

Wang

Chan

2019

2019 IEEE Intelligent Vehicles Symposium (IV)

View full text Add to dashboard Cite

Lane change is a challenging task which requires delicate actions to ensure safety and comfort. Some recent studies have attempted to solve the lane-change control problem with Reinforcement Learning (RL), yet the action is confined to discrete action space. To overcome this limitation, we formulate the lane change behavior with continuous action in a model-free dynamic driving environment based on Deep Deterministic Policy Gradient (DDPG). The reward function, which is critical for learning the optimal policy, is defined by control values, position deviation status, and maneuvering time to provide the RL agent informative signals. The RL agent is trained from scratch without resorting to any prior knowledge of the environment and vehicle dynamics since they are not easy to obtain. Seven models under different hyperparameter settings are compared. A video showing the learning progress of the driving behavior is available 2 . It demonstrates the RL vehicle agent initially runs out of road boundary frequently, but eventually has managed to smoothly and stably change to the target lane with a success rate of 100% under diverse driving situations in simulation.

show abstract

“…Firstly, the driving space is modeled with the road boundary, traffic lanes, position, speed, and acceleration of other vehicles in the feature space. Secondly, actions are defined as discrete behavior decisions [91,92] (lane changing, going straight, turning, etc.) or continuous control signal outputs [93,94] (steering angle and acceleration).…”

Section: The Driving Space In the Reinforcement Learning Decisionmentioning

confidence: 99%

“…As shown in Fig. 12 [91], this research is based on simulated feature space with the road boundary and vehicles as input, and behavior decisions as actions. Reinforcement learning relies on simulation since it needs to find the best driving policy by trial and error; therefore, it needs some adaption on real-road tests.…”

Section: The Driving Space In the Reinforcement Learning Decisionmentioning

confidence: 99%

See 1 more Smart Citation

Driving Space for Autonomous Vehicles

et al. 2019

View full text Add to dashboard Cite

Driving space for autonomous vehicles (AVs) is a simplified representation of real driving environments that helps facilitate driving decision processes. Existing literatures present numerous methods for constructing driving spaces, which is a fundamental step in AV development. This study reviews the existing researches to gain a more systematic understanding of driving space and focuses on two questions: how to reconstruct the driving environment, and how to make driving decisions within the constructed driving space. Furthermore, the advantages and disadvantages of different types of driving space are analyzed. The study provides further understanding of the relationship between perception and decision-making and gives insight into direction of future research on driving space of AVs.

show abstract

Highway Traffic Modeling and Decision Making for Autonomous Vehicle Using Reinforcement Learning

Cited by 41 publications

References 18 publications

Wireless recommendations for Internet of vehicles: Recent advances, challenges, and opportunities

Wireless recommendations for Internet of vehicles: Recent advances, challenges, and opportunities

Continuous Control for Automated Lane Change Behavior Based on Deep Deterministic Policy Gradient Algorithm

Driving Space for Autonomous Vehicles

Contact Info

Product

Resources

About