Incremental Learning for Enhanced Personalization of Autocomplete Teleoperation

Hussein, Mohammad Haj; Ibrahim, Badaruddin; Elhajj, Imad H.; Asmar, Daniel

doi:10.1109/icra46639.2022.9812108

Cited by 4 publications

(1 citation statement)

References 22 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Existing studies can be categorized based on user intention recognition techniques, task performance metrics, and decision-making algorithms. User intention recognition is performed either by model based methods [3], [6], [11], data-driven methods [1], [2], [7]- [10] or combinations of both types of methods [4]. It is worth noting that user intention recognition accuracy varies between 20% and 95%, which was not considered in some references.…”

Section: Introductionmentioning

confidence: 99%

Wireless Control for Life‐Critical Actions

Kizilkaya¹,

Chang²,

Zhao³

et al. 2020

Engineering and Technology for Healthcare

View full text Add to dashboard Cite

Teleoperation can be very difficult due to limited perception, high communication latency, and limited degrees of freedom (DoFs) at the operator side. Autonomous teleoperation is proposed to overcome this difficulty by predicting user intentions and performing some parts of the task autonomously to decrease the demand on the operator and increase the task completion rate. However, decision-making for mode-switching is generally assumed to be done by the operator, which brings an extra DoF to be controlled by the operator and introduces extra mental demand. On the other hand, the communication perspective is not investigated in the current literature, although communication imperfections and resource limitations are the main bottlenecks for teleoperation. In this study, we propose an intelligent modeswitching framework by jointly considering mode-switching and communication systems. User intention recognition is done at the operator side. Based on user intention recognition, a deep reinforcement learning (DRL) agent is trained and deployed at the operator side to seamlessly switch between autonomous and teleoperation modes. A real-world data set is collected from our teleoperation testbed to train both user intention recognition and DRL algorithms. Our results show that the proposed framework can achieve up to 50% communication load reduction with improved task completion probability.

show abstract