GAP de Morais, LB Marcos, JNAD Bueno… - Control Engineering …, 2020 - Elsevier
… Thus, a hybrid architecture that combines a robust recursive regulator and a DRL algorithm is presented in this paper to enhance performance of the machinelearningmethod. During …
S Josef, A Degani - IEEE Robotics and Automation Letters, 2020 - ieeexplore.ieee.org
… vehicle orientation in positions within the range of the sensors. In this work, we present a deepreinforcementlearningapproach … or local motion planning search spaces methods. Our …
… DeepReinforcementLearning (DRL) is a novel method that combines DL and RL … of continuous deepreinforcementlearning for the autonomous navigation of four-wheeled vehicles in …
X Huang, H Deng, W Zhang, R Song… - IEEE Robotics and …, 2021 - ieeexplore.ieee.org
… Abstract—In this paper, we present a novel navigation system of unmanned groundvehicle (UGV) for local path planning based on deepreinforcementlearning. The navigation system …
… vehicles, we suppose that the maximum number of vehicles … range Rn of groundvehicles for vehicle-to-vehicle (V2V) … other embedded wireless interfaces in vehicles, such that 0 < (…
S Faryadi… - International journal of …, 2021 - Wiley Online Library
… a reinforcementlearning-based method (and in particular dyna-Q+) is presented for a team of unmanned groundvehicles (… the proposed method for simultaneous learning and planning …
S Aradi - IEEE Transactions on Intelligent Transportation …, 2020 - ieeexplore.ieee.org
… , modern control methods, artificial intelligence, and machine learn… focused on Deep ReinforcementLearning (DRL) approach. … used the ground truth information about the ego …
… vehicles using deepreinforcement in scenarios where human operators and traditional control methods … has not yet been applied to wheeled groundvehicles in rough terrain with high …
L Yu, X Shao, Y Wei, K Zhou - Sensors, 2018 - mdpi.com
… to-end model transfer trajectory planning method based on depthreinforcementlearning is proposed in this study. Furthermore, DDPG is a deepreinforcementlearningmethod, and it is …