7,856 Hits in 9.1 sec

Tactical Decision-Making in Autonomous Driving by Reinforcement Learning with Uncertainty Estimation [article]

Carl-Johan Hoel, Krister Wolff, Leo Laine
2020 arXiv   pre-print
Reinforcement learning (RL) can be used to create a tactical decision-making agent for autonomous driving.  ...  This paper investigates how a Bayesian RL technique, based on an ensemble of neural networks with additional randomized prior functions (RPF), can be used to estimate the uncertainty of decisions in autonomous  ...  In contrast to the related work, this paper investigates an RL method for tactical decision-making in autonomous driving that can estimate the uncertainty of its decision, based arXiv:2004.10439v1 [cs.RO  ... 
arXiv:2004.10439v1 fatcat:xlqp2jupvrg4lnwjzp5phzedza

Reinforcement Learning with Uncertainty Estimation for Tactical Decision-Making in Intersections [article]

Carl-Johan Hoel, Tommy Tram, Jonas Sjöberg
2020 arXiv   pre-print
This paper investigates how a Bayesian reinforcement learning method can be used to create a tactical decision-making agent for autonomous driving in an intersection scenario, where the agent can estimate  ...  The coefficient of variation in the estimated Q-values of the ensemble members is used to approximate the uncertainty, and a criterion that determines if the agent is sufficiently confident to make a particular  ...  McAllister et al. further discuss the importance of estimating the uncertainty of decisions in autonomous driving [11] .  ... 
arXiv:2006.09786v1 fatcat:g5krdbp335gvja25gd4y7vaxga

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
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  ...  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  ...  Deep RL is efficient in learning arbitrary policies defining specific goals. In [8] , a tactical decision making for lane changing in highway driving scenarios is being performed using deep RL.  ... 
arXiv:1909.11538v1 fatcat:frgmz75pu5ah7ogqcbkt2kwuee

Decision-Making Technology for Autonomous Vehicles Learning-Based Methods, Applications and Future Outlook [article]

Qi Liu, Xueyuan Li, Shihua Yuan, Zirui Li
2021 arXiv   pre-print
Secondly, related works about learning-based decision-making methods for autonomous vehicles are mainly reviewed with the comparison to classical decision-making methods.  ...  In addition, applications of decision-making methods in existing autonomous vehicles are summarized.  ...  review mainly on learning-based decision-making methods that have emerged in recent years with the summarization of applications in existing autonomous vehicles.  ... 
arXiv:2107.01110v1 fatcat:ohffatmrmfbzdlihgvywryzupa

A Decision-Making Model for Autonomous Vehicles at Urban Intersections Based on Conflict Resolution

Zi-jia Wang, Xue-mei Chen, Pin Wang, Meng-xi Li, Yang-jia-xin Ou, Han Zhang, Wenqing Wu
2021 Journal of Advanced Transportation  
The reliability and effectiveness of the tactical decision-making model was verified by simulations.  ...  The decision-making models that are able to deal with complex and dynamic urban intersections are critical for the development of autonomous vehicles.  ...  To address this problem, this paper will focus on developing a tactical decisionmaking model for autonomous vehicles in intersection crossing scenarios. e problems of robust tactical decision-making for  ... 
doi:10.1155/2021/8894563 fatcat:vkvrhgljlrezte256fevb5wfka

Hierarchical Decision Making [chapter]

2009 Handbook of Learning and Approximate Dynamic Programming  
Decision making must be made within an appropriate context; we contend that such context is best represented by a hierarchy of states.  ...  Once learned, the resulting mathematical models may be combined with the techniques of reinforcement learning to predict behavior and anticipate the needs of the user, delivering appropriate data, visualizations  ...  Moving Forward Although Reinforcement Learning methods have been successfully integrated with probabilistic graphical networks, which allow us to build autonomous decision making systems that learn and  ... 
doi:10.1109/9780470544785.ch8 fatcat:kffb3eyh5bbgnc7otfnflgv5me

Combining Planning and Deep Reinforcement Learning in Tactical Decision Making for Autonomous Driving [article]

Carl-Johan Hoel, Katherine Driggs-Campbell, Krister Wolff, Leo Laine, Mykel J. Kochenderfer
2019 arXiv   pre-print
Tactical decision making for autonomous driving is challenging due to the diversity of environments, the uncertainty in the sensor information, and the complex interaction with other road users.  ...  This paper introduces a general framework for tactical decision making, which combines the concepts of planning and learning, in the form of Monte Carlo tree search and deep reinforcement learning.  ...  TACTICAL DECISION MAKING FRAMEWORK This paper introduces a framework that combines planning and learning for tactical decision making in the autonomous driving domain.  ... 
arXiv:1905.02680v1 fatcat:rbfhjw3k7jd73kpgcdw2uv7lbi

Front Matter: Volume 11021

Charles M. Shoemaker, Paul L. Muench, Hoa G. Nguyen
2019 Unmanned Systems Technology XXI  
These two-number sets start with 00, 01, 02, 03, 04,  ...  Publication of record for individual papers is online in the SPIE Digital Library. Paper Numbering: Proceedings of SPIE follow an e-First publication model.  ...  to decision making under uncertainty [11021-30] 11021 0T Stochastic functional laws of the iterated logarithm with applications to learning and control [11021-31] Proc. of SPIE Vol. 11021 1102101-4 [11021  ... 
doi:10.1117/12.2536312 fatcat:2beoa75kr5dvjb7qzhhxhilrim

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
Decision-making strategy for autonomous vehicles de-scribes a sequence of driving maneuvers to achieve a certain navigational mission.  ...  This paper utilizes the deep reinforcement learning (DRL) method to address the continuous-horizon decision-making problem on the highway.  ...  Decision-making for Autonomous Vehicles on Highway: Deep Reinforcement Learning with Continuous Action Horizon Fig. 1.  ... 
arXiv:2008.11852v1 fatcat:ozyiffczh5fyzbh3s6d3cq5vje

Autonomous Driving in Roundabout Maneuvers Using Reinforcement Learning with Q-Learning

Laura García Cuenca, Enrique Puertas, Javier Fernandez Andrés, Nourdine Aliane
2019 Electronics  
Several simulations are performed to train the algorithm in two scenarios: navigating a roundabout with and without surrounding traffic.  ...  Navigating roundabouts is a complex driving scenario for both manual and autonomous vehicles.  ...  For example, in [11, 26, 27] various RL methods are proposed in which autonomous vehicles learn to make decisions while interacting with simulated traffic.  ... 
doi:10.3390/electronics8121536 fatcat:a7dod2evqbddnlvazefknzqrry

Lane-Change Initiation and Planning Approach for Highly Automated Driving on Freeways [article]

Salar Arbabi, Shilp Dixit, Ziyao Zheng, David Oxtoby, Alexandros Mouzakitis, Saber Fallah
2020 arXiv   pre-print
Quantifying and encoding occupants' preferences as an objective function for the tactical decision making of autonomous vehicles is a challenging task.  ...  It is shown that the decision model can replicate human drivers' discretionary lane-change decisions with up to 92% accuracy.  ...  Recently, deep reinforcement learning has been proposed for tactical decision-making [4] .  ... 
arXiv:2007.14032v2 fatcat:53idpayfxrgttnbxgp7djcrbqm

Recent Advances in Deep Reinforcement Learning Applications for Solving Partially Observable Markov Decision Processes (POMDP) Problems Part 2—Applications in Transportation, Industries, Communications and Networking and More Topics

Xuanchen Xiang, Simon Foo, Huanyu Zang
2021 Machine Learning and Knowledge Extraction  
Reinforcement Learning (RL) is an approach to simulate the human's natural learning process, whose key is to let the agent learn by interacting with the stochastic environment.  ...  The two-part series of papers provides a survey on recent advances in Deep Reinforcement Learning (DRL) for solving partially observable Markov decision processes (POMDP) problems.  ...  This makes DL unpractical in many domains. Reinforcement Learning imitates the learning process of humans. It is trained by making and then avoiding mistakes.  ... 
doi:10.3390/make3040043 doaj:45bf00de595c44d186fa3d200589c1c5 fatcat:qx4srh7qabgjvd5l6lj6nulhxa

Reinforcement Learning based Negotiation-aware Motion Planning of Autonomous Vehicles [article]

Zhitao Wang, Yuzheng Zhuang, Qiang Gu, Dong Chen, Hongbo Zhang, Wulong Liu
2021 arXiv   pre-print
For autonomous vehicles integrating onto roadways with human traffic participants, it requires understanding and adapting to the participants' intention and driving styles by responding in predictable  ...  This paper proposes a reinforcement learning based negotiation-aware motion planning framework, which adopts RL to adjust the driving style of the planner by dynamically modifying the prediction horizon  ...  For tactical decision making, Hoel et al. introduced a general framework, which combines planning and learning in the form of Monte Carlo tree search and RL [27] .  ... 
arXiv:2107.03600v1 fatcat:tebaof5anzcd7dv6jp7eugznqu


2020 IEEE Transactions on Intelligent Vehicles  
We propose a new method that makes full use of the advantages of traditional methods and deep learning methods via incorporating human domain knowledge into the neural network model to reduce the demand  ...  Quantitative experiments show that the pretrained model achieves better performance than random initialization in almost all cases; furthermore, our method can achieve similar performance with fewer manual  ...  Tactical Tactical decision making for autonomous driving is challenging due to the diversity of environments, the uncertainty in the sensor information, and the complex interaction with other road users  ... 
doi:10.1109/tiv.2020.2973018 fatcat:qgsawvfx6rgfpgknnwdmfixrme

Managing Uncertainty in AI-Enabled Decision Making and Achieving Sustainability

Junyi Wu, Shari Shang
2020 Sustainability  
By referring to studies on uncertainty in decision making, this research describes three dimensions of uncertainty, namely informational, environmental and intentional.  ...  To understand how to manage uncertainty in AI-enabled decision-making applications, the authors conduct a literature review using content analysis with practical approaches.  ...  As an example, the autonomous vehicle is a novel AI application that provides humans with convenient transport services by autonomously analyzing road conditions and making driving decisions.  ... 
doi:10.3390/su12218758 fatcat:54jbxassl5cohfjn4pmsfvjtyq
« Previous Showing results 1 — 15 out of 7,856 results