Motion Planning and Control with Randomized Payloads Using Deep Reinforcement Learning

Ali Demir, Volkan Sezer

Araştırma sonucu: ???type-name???Konferans katkısıbilirkişi

5 Atıf (Scopus)

Özet

In this study, we present a unified motion planner with low-level controller for continuous control of a differential drive mobile robot under variable payload values. Our deep reinforcement agent takes 11 dimensional state vector as input and calculates each wheel's torque value as a 2 dimensional output vector. These torque values are fed into the dynamic model of the robot, and lastly steering commands are gathered. In previous studies, intersection navigation solutions that uses deep - RL methods, have not been considered with variable payloads. Our study is focused specifically on service robotic applications where payload is subject to change. To the best of our knowledge, this is the first study in the literature that investigates intersection - navigation problem under variable payloads using deep-RL. In this paper, deep-RL based motion planning is performed by considering both kinematic and dynamic constraints. According to the simulations in a dynamic environment, the agent succesfully navigates to target with 98.2% success rate in test time with unseen payload masses during training. Another agent is also trained without payload randomization for comparison. Results show that our agent outperforms the other agent, that is not aware of its own payload, with more than 40% gap.

Orijinal dilİngilizce
Ana bilgisayar yayını başlığıProceedings - 3rd IEEE International Conference on Robotic Computing, IRC 2019
YayınlayanInstitute of Electrical and Electronics Engineers Inc.
Sayfalar32-37
Sayfa sayısı6
ISBN (Elektronik)9781538692455
DOI'lar
Yayın durumuYayınlandı - 26 Mar 2019
Etkinlik3rd IEEE International Conference on Robotic Computing, IRC 2019 - Naples, Italy
Süre: 25 Şub 201927 Şub 2019

Yayın serisi

AdıProceedings - 3rd IEEE International Conference on Robotic Computing, IRC 2019

???event.eventtypes.event.conference???

???event.eventtypes.event.conference???3rd IEEE International Conference on Robotic Computing, IRC 2019
Ülke/BölgeItaly
ŞehirNaples
Periyot25/02/1927/02/19

Bibliyografik not

Publisher Copyright:
© 2019 IEEE.

Finansman

This work was supported by Research Fund of the Istanbul Technical University. Project Number: 41399.

FinansörlerFinansör numarası
Istanbul Teknik Üniversitesi41399

    Parmak izi

    Motion Planning and Control with Randomized Payloads Using Deep Reinforcement Learning' araştırma başlıklarına git. Birlikte benzersiz bir parmak izi oluştururlar.

    Alıntı Yap