Visual Rewards From Observation for Sequential Tasks: Autonomous Pile Loading.

Autor:	Strokina N; Computing Sciences, Tampere University, Tampere, Finland., Yang W; Computing Sciences, Tampere University, Tampere, Finland., Pajarinen J; Department of Electrical Engineering and Automation, Aalto University, Espoo, Finland., Serbenyuk N; Automation Technology and Mechanical Engineering, Tampere University, Tampere, Finland., Kämäräinen J; Computing Sciences, Tampere University, Tampere, Finland., Ghabcheloo R; Automation Technology and Mechanical Engineering, Tampere University, Tampere, Finland.
Jazyk:	angličtina
Zdroj:	Frontiers in robotics and AI [Front Robot AI] 2022 May 31; Vol. 9, pp. 838059. Date of Electronic Publication: 2022 May 31 (Print Publication: 2022).
DOI:	10.3389/frobt.2022.838059
Abstrakt:	One of the key challenges in implementing reinforcement learning methods for real-world robotic applications is the design of a suitable reward function. In field robotics, the absence of abundant datasets, limited training time, and high variation of environmental conditions complicate the task further. In this paper, we review reward learning techniques together with visual representations commonly used in current state-of-the-art works in robotics. We investigate a practical approach proposed in prior work to associate the reward with the stage of the progress in task completion based on visual observation. This approach was demonstrated in controlled laboratory conditions. We study its potential for a real-scale field application, autonomous pile loading, tested outdoors in three seasons: summer, autumn, and winter. In our framework, the cumulative reward combines the predictions about the process stage and the task completion (terminal stage). We use supervised classification methods to train prediction models and investigate the most common state-of-the-art visual representations. We use task-specific contrastive features for terminal stage prediction. Competing Interests: The authors declare that the research was conducted in the absence of any commercial or financial relationships that could be construed as a potential conflict of interest. (Copyright © 2022 Strokina, Yang, Pajarinen, Serbenyuk, Kämäräinen and Ghabcheloo.)
Databáze:	MEDLINE
Externí odkaz:	Zobrazit plný text záznamu