Zobrazeno 1 - 10
of 120
pro vyhledávání: '"trajectory rollout"'
Autor:
RAVNIKAR, ROBI
Zaradi vse večjega vključevanja ljudi v delovni prostor je narasla potreba po zanesljivem algoritmu, ki je sposoben detekcije in izogibanja ovir. V ta namen so se razvili prediktivni algoritmi vodenja, ki vnaprej predvidevajo trk z objektom in robo
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=od______3505::b222e6d69611c7c2880a42918cc9a4de
https://hdl.handle.net/20.500.12556/RUL-131087
https://hdl.handle.net/20.500.12556/RUL-131087
Autor:
Moysiadis, Vasileios1,2,3 (AUTHOR) gkarras@uth.gr, Benos, Lefteris1 (AUTHOR) e.benos@certh.gr, Karras, George2 (AUTHOR), Kateris, Dimitrios1 (AUTHOR) d.kateris@certh.gr, Peruzzi, Andrea4 (AUTHOR) andrea.peruzzi@unipi.it, Berruto, Remigio5 (AUTHOR) remigio.berruto@unito.it, Papageorgiou, Elpiniki6 (AUTHOR) elpinikipapageorgiou@uth.gr, Bochtis, Dionysis1,3 (AUTHOR) d.bochtis@certh.gr
Publikováno v:
AgriEngineering. Sep2024, Vol. 6 Issue 3, p2494-2512. 19p.
Curriculum learning is a training mechanism in reinforcement learning (RL) that facilitates the achievement of complex policies by progressively increasing the task difficulty during training. However, designing effective curricula for a specific tas
Externí odkaz:
http://arxiv.org/abs/2409.18382
Autor:
Karwowski, Jarosław1 (AUTHOR) jaroslaw.karwowski.dokt@pw.edu.pl, Szynkiewicz, Wojciech1 (AUTHOR), Niewiadomska-Szynkiewicz, Ewa1 (AUTHOR) ewa.szynkiewicz@pw.edu.pl
Publikováno v:
Sensors (14248220). May2024, Vol. 24 Issue 9, p2794. 61p.
Autor:
Zhao, Shengmin1 (AUTHOR) shengmin.zhao@dgu.ac.kr, Hwang, Seung-Hoon1 (AUTHOR) shwang@dongguk.edu
Publikováno v:
Sensors (14248220). Apr2023, Vol. 23 Issue 7, p3648. 19p.
Autor:
Hossain, Ramij Raja, Yin, Tianzhixi, Du, Yan, Huang, Renke, Tan, Jie, Yu, Wenhao, Liu, Yuan, Huang, Qiuhua
Publikováno v:
Machine Learning; May2024, Vol. 113 Issue 5, p2675-2700, 26p
Autor:
Soegiarto, Duddy1, Trilaksono, Bambang Riyanto1,2 briyanto@lskk.ee.itb.ac.id, Adiprawita, Widyawardana1,2, Idris Hidayat, Egi Muhammad1,2, Prabowo, Yaqub Aris1
Publikováno v:
International Journal on Electrical Engineering & Informatics. Sep2022, Vol. 14 Issue 3, p514-551. 38p.
Both pedestrian and robot comfort are of the highest priority whenever a robot is placed in an environment containing human beings. In the case of pedestrian-unaware mobile robots this desire for safety leads to the freezing robot problem, where a ro
Externí odkaz:
http://arxiv.org/abs/2206.00705
Reinforcement learning (RL) is capable of sophisticated motion planning and control for robots in uncertain environments. However, state-of-the-art deep RL approaches typically lack safety guarantees, especially when the robot and environment models
Externí odkaz:
http://arxiv.org/abs/2204.07417
Publikováno v:
Machines; Apr2024, Vol. 12 Issue 4, p256, 25p