Zobrazeno 1 - 9
of 9
pro vyhledávání: '"Shangding Gu"'
Publikováno v:
Frontiers in Neurorobotics, Vol 17 (2023)
Deployment of Reinforcement Learning (RL) algorithms for robotics applications in the real world requires ensuring the safety of the robot and its environment. Safe Robot RL (SRRL) is a crucial step toward achieving human-robot coexistence. In this p
Externí odkaz:
https://doaj.org/article/8b8fec242d784c4bbce59464e0dc748b
Publikováno v:
Robotics, Vol 11, Iss 4, p 81 (2022)
Rule-based traditional motion planning methods usually perform well with prior knowledge of the macro-scale environments but encounter challenges in unknown and uncertain environments. Deep reinforcement learning (DRL) is a solution that can effectiv
Externí odkaz:
https://doaj.org/article/3e25f54e533e44038868bf5a416f90e1
Publikováno v:
Journal of Marine Science and Engineering, Vol 10, Iss 3, p 420 (2022)
Aiming at the problem that unmanned surface vehicle (USV) motion planning is disturbed by effects of wind and current, a USV motion planning method based on regularization-trajectory cells is proposed. First, a USV motion mathematical model is establ
Externí odkaz:
https://doaj.org/article/74c472c6c9b84481849f225b2cc661c6
Autor:
Shangding Gu, Jakub Grudzien Kuba, Yuanpei Chen, Yali Du, Long Yang, Alois Knoll, Yaodong Yang
Publikováno v:
Gu, S, Grudzien Kuba, J, Chen, Y, Du, Y, Yang, L, Knoll, A & Yang, Y 2023, ' Safe multi-agent reinforcement learning for multi-robot control ', ARTIFICIAL INTELLIGENCE, vol. 319, 103905 . https://doi.org/10.1016/j.artint.2023.103905
A challenging problem in robotics is how to control multiple robots cooperatively and safely in real-world applications. Yet, developing multi-robot control methods from the perspective of safe multi-agent reinforcement learning (MARL) has merely bee
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::89988bc68de4276a36b0fcf66d3afb9c
https://kclpure.kcl.ac.uk/en/publications/4b6e2578-0b6d-455a-84f9-b317b80838cc
https://kclpure.kcl.ac.uk/en/publications/4b6e2578-0b6d-455a-84f9-b317b80838cc
Publikováno v:
IEEE Transactions on Artificial Intelligence. 3:207-217
2D LiDAR is an efficient alternative sensor for vehicle detection, which is one of the most critical tasks in autonomous driving. Compared to the fully-developed 3D LiDAR vehicle detection, 2D LiDAR vehicle detection has much room to improve. Most of
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::12a980fd8cac2cfbad624ebc35a5a71b
https://doi.org/10.1109/tai.2021.3112945
https://doi.org/10.1109/tai.2021.3112945
Publikováno v:
IEEE/ASME Transactions on Mechatronics. 26:1547-1557
With the process of urbanization, the problem of insufficient parking spaces has become prominent. Adopting a high-density parking lot with parking robots can greatly improve the land utilization rate of the parking lot. This article tackles the mult
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::6014da711226213684d526596e2f826d
https://doi.org/10.1109/tmech.2020.3023261
https://doi.org/10.1109/tmech.2020.3023261
Aiming at an obstacle avoidance problem with dynamic constraints for Unmanned Surface Vehicle (USV), a method based on Circle Grid Trajectory Cell (CGTC) is proposed. Firstly, the ship model and standardization rules are constructed to develop and co
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::b717affe0ddb6d0deb62b3287d184467
http://arxiv.org/abs/2202.04494
http://arxiv.org/abs/2202.04494
Pole-based Localization for Autonomous Vehicles in Urban Scenarios Using Local Grid Map-based Method
Publikováno v:
ICARM
Self-localization is a key component of autonomous vehicles in urban scenarios. In this work, we proposed a localization system which is based on pole-like objects such as trees and street lamps. Pole-like objects are extracted from 3D LiDAR point cl
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::de46b6c50f2dd0993dfedd7f08f8e1a5
https://mediatum.ub.tum.de/1550370
https://mediatum.ub.tum.de/1550370