Z Du, Q Miao, C Zong - International Journal of Automotive Technology, 2020 - Springer
… ABSTRACTDeep reinforcementlearning (DRL) has been … This paper proposes a DRL-based trajectoryplanner for … A simulation study is conducted to investigate the trajectoryplanning …
Y Qin, Z Zhang, X Li, W Huangfu… - IEEE Transactions on …, 2023 - ieeexplore.ieee.org
… formulate a joint user association, UAV trajectoryplanning and power allocation problem to … This paper exploits the centralized and the decentralized deep reinforcementlearning (DRL…
Y Li, AH Aghvami, D Dong - IEEE Wireless Communications …, 2021 - ieeexplore.ieee.org
… are evaluated for the considered UAV trajectoryplanning problem via the proposed QiRL solution. For comparison, two CRL methods (ie, Qlearning with ϵ-greedy and Boltzmann …
S Zhang, Q Xia, M Chen, S Cheng - Sensors, 2023 - mdpi.com
… planning methods become inapplicable when a space robot is in motion. A trajectory-planning strategy based on reinforcementlearning … Time-optimal trajectoryplanning has been …
… This work studies online learning-based trajectoryplanning for … The AUV trajectories for sampling are determined on an … The optimal trajectories of all the AUVs in the next epoch are …
… A flight trajectoryplanning optimization is formulated as a Partial Observable Markov … onboard deep reinforcementlearning algorithm to optimize the realtime trajectoryplanning of the …
Z Xi, D Wu, W Ni, X Ma - IEEE Access, 2022 - ieeexplore.ieee.org
… uses a reinforcementlearning (RL) method to train a neural network controller as an integrated aircraft navigation and guidance controller. It is used to optimize the flight trajectory and …
Q Luo, TH Luan, W Shi, P Fan - IEEE Journal on Selected …, 2022 - ieeexplore.ieee.org
… decisions and make optimal flying trajectories represent fundamental research challenges. In this … Thereafter, we propose a deep reinforcementlearning (DRL) technique to jointly make …
Z Zhu, N Li, R Sun, D Xu, H Zhao - 2020 IEEE intelligent …, 2020 - ieeexplore.ieee.org
… Behaviorbased methods learn cost functions that guide trajectoryplanning in compliance … and trajectoryplanning using Deep Maximum Entropy Inverse ReinforcementLearning. To …