Naslov
Biped Robot Walking based on Deep Reinforcement Learning

Autori
Tadić, Tomislav ; Ćurković, Petar

Vrsta, podvrsta i kategorija rada
Radovi u zbornicima skupova, cjeloviti rad (in extenso), znanstveni

Izvornik
2023 46th ICT and Electronics Convention / Skala, Karolj - Rijeka : Institute of Electrical and Electronics Engineers (IEEE), 2023, 344-349

ISBN
978-953-233-105-9

Skup
2023 46th ICT and Electronics Convention

Mjesto i datum
Opatija, Hrvatska, 22.05.2023. - 26.05.2023

Vrsta sudjelovanja
Predavanje

Vrsta recenzije
Međunarodna recenzija

Ključne riječi
Legged locomotion , Deep learning , Software packages , Humanoid robots , Reinforcement learning , 6-DOF , Oscillators

Sažetak
In this paper a 6 DOF biped robot model is designed, and deep reinforcement machine learning methods are implemented for the robot to learn efficient walking following a straight line. Detailed procedure of the robot design, development of a Simulink model and implementation of learning procedures is presented. Two approaches were compared for motion learning – Deep Deterministic Policy Gradient (DDPG), and Twin- Delayed Deep Deterministic Policy Gradient (TD3). The results show that both approaches are successful in generating a model with free continuous action learning and input to action mapping. Additionally, our results show that the TD3 algorithm outperforms the DDPG algorithm in the problem as formulated in this study.

Izvorni jezik
Engleski

Znanstvena područja
Strojarstvo, Temeljne tehničke znanosti

POVEZANOST RADA