3,397 Hits in 4.6 sec

Automated Speed and Lane Change Decision Making using Deep Reinforcement Learning [article]

Carl-Johan Hoel, Krister Wolff, Leo Laine
2018 arXiv   pre-print
A Deep Q-Network agent was trained in a simulated environment to handle speed and lane change decisions for a truck-trailer combination.  ...  This paper introduces a method, based on deep reinforcement learning, for automatically generating a general purpose decision making function.  ...  ACKNOWLEDGMENT This work was partially supported by the Wallenberg Artificial Intelligence, Autonomous Systems and Software Program (WASP), funded by Knut and Alice Wallenberg Foundation, and partially  ... 
arXiv:1803.10056v1 fatcat:dunwm26gbvfbjhocyse2pdldlm

Driving Decision and Control for Autonomous Lane Change based on Deep Reinforcement Learning [article]

Tianyu Shi, Pin Wang, Xuxin Cheng, Ching-Yao Chan, Ding Huang
2019 arXiv   pre-print
Finally, a polynomial lane change trajectory is generated and Pure Pursuit Control is implemented for path tracking.  ...  We demonstrate the effectiveness of this framework in simulation, from both the decision-making and control layers.  ...  In one previous work [12] , we presented a reinforcement learning based approach for automated lane change maneuver, which let the agent explore the unforeseen environment and make the correct decision  ... 
arXiv:1904.10171v2 fatcat:ey22jtjj2vajrlf355rj2b7gee

Automated Lane Change Strategy using Proximal Policy Optimization-based Deep Reinforcement Learning [article]

Fei Ye, Xuxin Cheng, Pin Wang, Ching-Yao Chan, Jiucai Zhang
2020 arXiv   pre-print
In this study, we propose an automated lane change strategy using proximal policy optimization-based deep reinforcement learning, which shows great advantages in learning efficiency while still maintaining  ...  The trained agent is able to learn a smooth, safe, and efficient driving policy to make lane-change decisions (i.e. when and how) in a challenging situation such as dense traffic scenarios.  ...  CONCLUSIONS AND FUTURE WORK This paper proposed an automated mandatory lane change strategy by using proximal policy optimization (PPO) [17] based deep reinforcement learning, which features safety,  ... 
arXiv:2002.02667v2 fatcat:7beyqzig2remtnuczthjwosi7q

End-to-End Automated Lane-Change Maneuvering Considering Driving Style Using a Deep Deterministic Policy Gradient Algorithm

Hongyu Hu, Ziyang Lu, Qi Wang, Chengyuan Zheng
2020 Sensors  
on reinforcement learning.  ...  Thus, autonomous vehicles trained using the proposed method can learn an automated lane-changing policy while considering safety, comfort, and efficiency.  ...  Moreover, deep reinforcement learning combines the perception ability of deep learning with the decision-making ability of reinforcement learning, thus bringing complementary advantages and providing a  ... 
doi:10.3390/s20185443 pmid:32971987 pmcid:PMC7570521 fatcat:ohgssh2xyzc4ngwnjtnigmpx7a

Dueling Deep Q Network for Highway Decision Making in Autonomous Vehicles: A Case Study [article]

Teng Liu, Xingyu Mu, Xiaolin Tang, Bing Huang, Hong Wang, Dongpu Cao
2020 arXiv   pre-print
This work optimizes the highway decision making strategy of autonomous vehicles by using deep reinforcement learning (DRL).  ...  Then, the overtaking decision-making problem of the automated vehicle is formulated as an optimal control problem.  ...  They are formulated as the following expression: _, Maintain, _, , , e Left lane change to left lane keep speed and lane a Right lane change to left lane Acceleration driver fast Deceleration  ... 
arXiv:2007.08343v1 fatcat:pqvyrduhfzalfanimbdce6yyha

Decision-Making System for Lane Change Using Deep Reinforcement Learning in Connected and Automated Driving

HongIl An, Jae-il Jung
2019 Electronics  
In this paper, we propose a lane change system that combines deep reinforcement learning and vehicular communication.  ...  Lane changing systems have consistently received attention in the fields of vehicular communication and autonomous vehicles.  ...  Conclusions This paper presented a lane change system that uses deep reinforcement learning and vehicular communication.  ... 
doi:10.3390/electronics8050543 fatcat:pqubias5f5fr7bp4zl24qjttku

Decision-making Strategy on Highway for Autonomous Vehicles using Deep Reinforcement Learning [article]

Jiangdong Liao, Teng Liu, Xiaolin Tang, Xingyu Mu, Bing Huang, Dongpu Cao
2020 arXiv   pre-print
In this work, a deep reinforcement learning (DRL)-enabled decision-making policy is constructed for autonomous vehicles to address the overtaking behaviors on the highway.  ...  Then, the particular DRL method named dueling deep Q-network (DDQN) algorithm is applied to derive the highway decision-making strategy.  ...  For example, Duan et al. built a hierarchical structure to learn the decision-making policy via the reinforcement learning (RL) method [14] .  ... 
arXiv:2007.08691v1 fatcat:r5kr2px6rbehnonaxpwhwlp7dm

Automated Lane Change Decision Making using Deep Reinforcement Learning in Dynamic and Uncertain Highway Environment [article]

Ali Alizadeh, Majid Moghadam, Yunus Bicer, Nazim Kemal Ure, Ugur Yavas, Can Kurtulus
2019 arXiv   pre-print
In this work, we develop a novel simulation environment that emulates these challenges and train a deep reinforcement learning agent that yields consistent performance in a variety of dynamic and uncertain  ...  Autonomous lane changing is a critical feature for advanced autonomous driving systems, that involves several challenges such as uncertainty in other driver's behaviors and the trade-off between safety  ...  DRL is also used in [9] to automate the speed and lane change decision making, in which two different agents with different neural network architectures, 1-dimensional Convolution Neural Network (CNN  ... 
arXiv:1909.11538v1 fatcat:frgmz75pu5ah7ogqcbkt2kwuee

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

Fei Ye, Shen Zhang, Pin Wang, Ching-Yao Chan
2021 arXiv   pre-print
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.  ...  Finally, the remaining challenges applying deep RL algorithms on autonomous driving are summarized, and future research directions are also presented to tackle these challenges.  ...  DEEP REINFORCEMENT LEARNING FOR DECISION MAKING AND MOTION PLANNING In this section, we focus on recent advances in behavioral decision-making and motion planning for autonomous vehicles based on deep  ... 
arXiv:2105.14218v2 fatcat:27glt4i4lfhg3j4ozjrlsq6i3e

Development of A Stochastic Traffic Environment with Generative Time-Series Models for Improving Generalization Capabilities of Autonomous Driving Agents [article]

Anil Ozturk, Mustafa Burak Gunel, Melih Dal, Ugur Yavas, Nazim Kemal Ure
2020 arXiv   pre-print
In recent years, reinforcement learning (RL) algorithms trained on traffic simulators yielded successful results in computing lane changing policies that strike a balance between safety, agility and compensating  ...  Automated lane changing is a critical feature for advanced autonomous driving systems.  ...  Reinforcement Learning We formulate the lane change decision making problem as a Markov Decision Process and use Q-learning to compute policies that yield lane changing decisions while optimizing safety  ... 
arXiv:2006.05821v1 fatcat:webvydr2kjb7vowjkptbvobrxu

Facilitating Connected Autonomous Vehicle Operations Using Space-weighted Information Fusion and Deep Reinforcement Learning Based Control [article]

Jiqian Dong, Sikai Chen, Yujie Li, Runjia Du, Aaron Steinfeld, Samuel Labi
2020 arXiv   pre-print
in the short-term (local decisions including lane change) and long-term (route choice).  ...  the CAV and from those located further downstream, and we use the fused data to guide lane changing, a specific context of CAV operations.  ...  Acknowledgements This study is based on research supported by the Center for Connected and Automated Transportation (CCAT), Region V University Transportation Center funded by the U.S.  ... 
arXiv:2009.14665v1 fatcat:ie5esur4srgqbh7sz474aarsju

A New Approach for Tactical Decision Making in Lane Changing: Sample Efficient Deep Q Learning with a Safety Feedback Reward [article]

M. Ugur Yavas, N. Kemal Ure, Tufan Kumbasar
2020 arXiv   pre-print
Automated lane change is one of the most challenging task to be solved of highly automated vehicles due to its safety-critical, uncertain and multi-agent nature.  ...  This paper presents the novel deployment of the state of art Q learning method, namely Rainbow DQN, that uses a new safety driven rewarding scheme to tackle the issues in an dynamic and uncertain simulation  ...  Recently, applications of Deep Reinforcement Learning (DRL) to the lane change problem have been investigated by using Q-masking to integrate high-level knowledge [7] , combining with the safety layer  ... 
arXiv:2009.11905v1 fatcat:i6gkddp22vew3bbkgsrxhyhh6a

Decision-making Strategy on Highway for Autonomous Vehicles using Deep Reinforcement Learning

Jiangdong Liao, Teng Liu, Xiaolin Tang, Xingyu Mu, Bing Huang, Dongpu Cao
2020 IEEE Access  
[14] , Nie et al. discussed the lane-changing decision-making strategy for connected automated cars.  ...  For example, Duan et al. built a hierarchical structure to learn the decision-making policy via the reinforcement learning (RL) method [17] .  ...  CONCLUSION This paper discusses the highway decision-making problem using the DRL technique.  ... 
doi:10.1109/access.2020.3022755 fatcat:kkimzfkwdbc2zogivbjtso7nsm

Automated vehicle's behavior decision making using deep reinforcement learning and high-fidelity simulation environment [article]

Yingjun Ye, Xiaohui Zhang, Jian Sun
2018 arXiv   pre-print
In addition, theoretical analysis and experiments were conducted on setting reward function for accelerating training using deep reinforcement learning.  ...  Later on, on a more complex three-lane section, we trained the integrated model combines both car-following and lane-changing behavior, the average speed further grows 2.4%.  ...  Acknowledgments The authors would like to thank the Natural Science Foundation of China (51422812), and the Shanghai Science and technology project of international cooperation (16510711400) for supporting  ... 
arXiv:1804.06264v1 fatcat:zf3uso7kv5e57i4lboa2l3sshi

Decision-making for Autonomous Vehicles on Highway: Deep Reinforcement Learning with Continuous Action Horizon [article]

Teng Liu, Hong Wang, Bing Lu, Jun Li, Dongpu Cao
2020 arXiv   pre-print
This paper utilizes the deep reinforcement learning (DRL) method to address the continuous-horizon decision-making problem on the highway.  ...  Finally, the PPO-DRL-based decision-making strategy is estimated from multiple perspectives, including the optimality, learning efficiency, and adaptability.  ...  Reinforcement learning (RL), especially deep reinforcement learning (DRL) methods, exhibit powerful potentials to dispose of the decision-making problems in AD [10] .  ... 
arXiv:2008.11852v1 fatcat:ozyiffczh5fyzbh3s6d3cq5vje
« Previous Showing results 1 — 15 out of 3,397 results