109 Hits in 4.9 sec

Adversarial Reinforcement Learning Framework for Benchmarking Collision Avoidance Mechanisms in Autonomous Vehicles [article]

Vahid Behzadan, Arslan Munir
2018 arXiv   pre-print
This work proposes a novel framework based on deep reinforcement learning for benchmarking the behavior of collision avoidance mechanisms under the worst-case scenario of dealing with an optimal adversarial  ...  With the rapidly growing interest in autonomous navigation, the body of research on motion planning and collision avoidance techniques has enjoyed an accelerating rate of novel proposals and developments  ...  adversarial deep reinforcement learning to measure the reliability of motion planning and collision avoidance mechanisms in autonomous vehicles.  ... 
arXiv:1806.01368v1 fatcat:pitfzjr2prbulfkw6b4fs2a66y

Exploring applications of deep reinforcement learning for real-world autonomous driving systems [article]

Victor Talpaert, Ibrahim Sobh, B Ravi Kiran, Patrick Mannion, Senthil Yogamani, Ahmad El-Sallab, Patrick Perez
2019 arXiv   pre-print
Deep Reinforcement Learning (DRL) has become increasingly powerful in recent years, with notable achievements such as Deepmind's AlphaGo.  ...  In general, DRL is still at its infancy in terms of usability in real-world applications.  ...  The authors (Djuric et al., 2018) , trained a deep convolutional neural network (CNN) to predict short-term vehicle trajectories, while accounting for inherent uncertainty of vehicle motion in road traffic  ... 
arXiv:1901.01536v3 fatcat:y3gck5rznjglvim4gem5dvb2ue

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.  ...  Index Terms-Deep learning in robotics and automation, autonomous agents, real world reinforcement learning, data-driven simulation. I.  ... 
arXiv:2105.14218v2 fatcat:27glt4i4lfhg3j4ozjrlsq6i3e

Deep Reinforcement Learning for Autonomous Driving: A Survey [article]

B Ravi Kiran, Ibrahim Sobh, Victor Talpaert, Patrick Mannion, Ahmad A. Al Sallab, Senthil Yogamani, Patrick Pérez
2021 arXiv   pre-print
With the development of deep representation learning, the domain of reinforcement learning (RL) has become a powerful learning framework now capable of learning complex policies in high dimensional environments  ...  This review summarises deep reinforcement learning (DRL) algorithms and provides a taxonomy of automated driving tasks where (D)RL methods have been employed, while addressing key computational challenges  ...  Index Terms-Deep reinforcement learning, Autonomous driving, Imitation learning, Inverse reinforcement learning, Controller learning, Trajectory optimisation, Motion planning, Safe reinforcement learning  ... 
arXiv:2002.00444v2 fatcat:axj3ohhjwzdrxp6dgpfqvctv2i

Motion Prediction on Self-driving Cars: A Review [article]

Shahrokh Paravarzar, Belqes Mohammad
2020 arXiv   pre-print
The state-of-the-art consists of classical and physical methods, deep learning networks, and reinforcement learning. prons and cons of the methods and gap of the research presented in this review.  ...  As a result, deep reinforcement learning is the best candidate to tackle self-driving cars.  ...  [5] reviewed the reinforcement learning approach for autonomous vehicle. In this review, our major focus will be on deep learning and reinforcement learning approach. A.  ... 
arXiv:2011.03635v1 fatcat:3452qcxglbeo5elkidc6pdb43u

Hybrid of Reinforcement and Imitation Learning for Human-Like Agents

Rousslan F. J. DOSSA, Xinyu LIAN, Hirokazu NOMOTO, Takashi MATSUBARA, Kuniaki UEHARA
2020 IEICE transactions on information and systems  
Reinforcement learning methods achieve performance superior to humans in a wide range of complex tasks and uncertain environments.  ...  However, high performance is not the sole metric for practical use such as in a game AI or autonomous driving.  ...  The double-blind sensitivity test conducted in this study was organized and held by EQUOS RESEARCH Co., and the participants were selected from its employees.  ... 
doi:10.1587/transinf.2019edp7298 fatcat:js3s735xcbfx7eae4w7wf734ly

A survey of deep learning techniques for autonomous driving

Sorin Grigorescu, Bogdan Trasnea, Tiberiu Cocias, Gigel Macesanu
2019 Journal of Field Robotics  
The objective of this paper is to survey the current state-of-the-art on deep learning technologies used in autonomous driving.  ...  We investigate both the modular perception-planning-action pipeline, where each module is built using deep learning methods, as well as End2End systems, which directly map sensory information to steering  ...  Over the next period, we expect deep learning to play a significant role in the area of local trajectory estimation and planning.  ... 
doi:10.1002/rob.21918 fatcat:pjyk4lwjavf63jz4pmc3mnuqe4

Autonomous Racing using a Hybrid Imitation-Reinforcement Learning Architecture [article]

Chinmay Vilas Samak, Tanmay Vilas Samak, Sivanathan Kandhasamy
2021 arXiv   pre-print
We adopted a hybrid imitation-reinforcement learning architecture and crafted a novel reward function to train a deep neural network policy to drive (using imitation learning) and race (using reinforcement  ...  This dominance could be justified in terms of better trajectory optimization and lower reaction time of the autonomous agent.  ...  These demonstrations were sub-optimal in terms of trajectory planning and were solely intended to impart fundamental driving ability to the autonomous agent.  ... 
arXiv:2110.05437v1 fatcat:dpo5kmv37ra77dm2aw57q5hmhq

Survey of Deep Reinforcement Learning for Motion Planning of Autonomous Vehicles [article]

Szilárd Aradi
2020 arXiv   pre-print
A wide range of techniques in Machine Learning itself have been developed, and this article describes one of these fields, Deep Reinforcement Learning (DRL).  ...  Another part of research focuses on different layers of Motion Planning, such as strategic decisions, trajectory planning, and control.  ...  ACKNOWLEDGMENT The research reported in this paper was supported by the Higher Education Excellence Program of the Ministry of Human Capacities in the frame of Artificial Intelligence research area of  ... 
arXiv:2001.11231v1 fatcat:l6l2ptyyxjc3dhseza5bsleoje

Survey of Deep Reinforcement Learning for Motion Planning of Autonomous Vehicles

Szilard Aradi
2020 IEEE transactions on intelligent transportation systems (Print)  
A wide range of techniques in Machine Learning itself have been developed, and this article describes one of these fields, Deep Reinforcement Learning (DRL).  ...  Index Terms-Machine learning, motion planning, autonomous vehicles, artificial intelligence, reinforcement learning. Szilárd Aradi (Member, IEEE) received the M.Sc.  ...  Research Development and Innovation Office in the field of Artificial Intelligence (BME IE-MI-FM TKP2020).  ... 
doi:10.1109/tits.2020.3024655 fatcat:wk4c2ked3jho3jtqdn4o5ys4zu

InfoGAIL: Interpretable Imitation Learning from Visual Demonstrations [article]

Yunzhu Li, Jiaming Song, Stefano Ermon
2017 arXiv   pre-print
In the driving domain, we show that a model learned from human demonstrations is able to both accurately reproduce a variety of behaviors and accurately anticipate human actions using raw visual inputs  ...  In this paper, we propose a new algorithm that can infer the latent structure of expert demonstrations in an unsupervised way.  ...  deep neural network to achieve better performance in imitation learning with relatively few demonstrations.  ... 
arXiv:1703.08840v2 fatcat:pnvgdi5syvc4djno32b2gnhjoa

A Method of Personalized Driving Decision for Smart Car Based on Deep Reinforcement Learning

Xinpeng Wang, Chaozhong Wu, Jie Xue, Zhijun Chen
2020 Information  
Finally, compare the proposed method with classic Deep Reinforcement Learning algorithms.  ...  To date, automatic driving technology has become a hotspot in academia. It is necessary to provide a personalization of automatic driving decision for each passenger.  ...  Reinforcement learning has shown good learning performance in strategy learning. At present, deep reinforcement learning is widely used in the simulation, industrial control and gaming [14] .  ... 
doi:10.3390/info11060295 fatcat:6h7r4ibvqbagnee2vqzpx3wnii

Solving Deep Memory POMDPs with Recurrent Policy Gradients [chapter]

Daan Wierstra, Alexander Foerster, Jan Peters, Jürgen Schmidhuber
2007 Lecture Notes in Computer Science  
Using a "Long Short-Term Memory" architecture, we are able to outperform other RL methods on two important benchmark tasks.  ...  This paper presents Recurrent Policy Gradients, a modelfree reinforcement learning (RL) method creating limited-memory stochastic policies for partially observable Markov decision problems (POMDPs) that  ...  Next, we describe the particular type of recurrent neural network architecture used in this paper, Long Short-Term Memory.  ... 
doi:10.1007/978-3-540-74690-4_71 fatcat:xvmxbfb4obcsrdf4ytjqkk7yze

Target-driven Visual Navigation in Indoor Scenes using Deep Reinforcement Learning [article]

Yuke Zhu, Roozbeh Mottaghi, Eric Kolve, Joseph J. Lim, Abhinav Gupta, Li Fei-Fei, Ali Farhadi
2016 arXiv   pre-print
Two less addressed issues of deep reinforcement learning are (1) lack of generalization capability to new target goals, and (2) data inefficiency i.e., the model requires several (and often costly) episodes  ...  We show that our proposed method (1) converges faster than the state-of-the-art deep reinforcement learning methods, (2) generalizes across targets and across scenes, (3) generalizes to a real robot scenario  ...  ACKNOWLEDGEMENTS We would like to thank Dieter Fox for his helpful comments, Andrzej Pronobis and Yu Xiang for helping us with the robot experiments, and Noah Siegel for his help with creating the video  ... 
arXiv:1609.05143v1 fatcat:ri2vgvyrlvae3i7iknsc6emubq

Recent Advances in Deep Reinforcement Learning Applications for Solving Partially Observable Markov Decision Processes (POMDP) Problems: Part 1—Fundamentals and Applications in Games, Robotics and Natural Language Processing

Xuanchen Xiang, Simon Foo
2021 Machine Learning and Knowledge Extraction  
The first part of a two-part series of papers provides a survey on recent advances in Deep Reinforcement Learning (DRL) applications for solving partially observable Markov decision processes (POMDP) problems  ...  In this overview, we introduce Markov Decision Processes (MDP) problems and Reinforcement Learning and applications of DRL for solving POMDP problems in games, robotics, and natural language processing  ...  Acknowledgments: The authors would like to express their appreciation to friends and colleagues who had assisted in the preparation of this paper.  ... 
doi:10.3390/make3030029 fatcat:u3y7bqkoljac5not2eq5konnnm
« Previous Showing results 1 — 15 out of 109 results