Transfer Learning of Human Preferences for Proactive Robot Assistance in Assembly Tasks

Transfer Learning of Human Preferences for Proactive Robot Assistance in Assembly Tasks
复制标题

人类偏好的迁移学习,以主动协助机器人完成装配任务

DOI:
10.1145/3568162.3576965
复制
发表时间:
2023
期刊:
HRI '23: Proceedings of the 2023 ACM/IEEE International Conference on Human-Robot Interaction
影响因子:
--
通讯作者:
Nikolaidis, Stefanos
Nikolaidis, Stefanos
中科院分区:
--
文献类型:
--
作者:
Nemlekar, Heramb;Dhanaraj, Neel;Guan, Angelos;Gupta, Satyandra K.;Nikolaidis, Stefanos

文献摘要

参考文献

被引文献

相似文献

我们专注于使机器人能够主动协助人类的装配任务,通过适应他们的首选动作序列。机器人适应方面的许多工作都需要人类演示该任务。然而,真实世界装配的人工演示可能是乏味和耗时的。因此,我们建议在一个较短的,规范的任务,以预测用户在实际的组装任务的行动,从示范学习人类的喜好。所提出的系统使用的偏好模型从典型的任务作为先验知识,并更新模型时,预测是不准确的。我们评估所提出的系统在模拟装配任务,并在现实世界中的人-机器人装配研究,我们表明,无论是转移的偏好模型从规范的任务,以及更新的模型在线,有助于提高人类行动预测的准确性。这使得机器人能够主动协助用户,显著减少他们的空闲时间,并改善他们与机器人一起工作的体验。
We focus on enabling robots to proactively assist humans in assembly tasks by adapting to their preferred sequence of actions. Much work on robot adaptation requires human demonstrations of the task. However, human demonstrations of real-world assemblies can be tedious and time-consuming. Thus, we propose learning human preferences from demonstrations in a shorter, canonical task to predict user actions in the actual assembly task. The proposed system uses the preference model learned from the canonical task as a prior and updates the model through interaction when predictions are inaccurate. We evaluate the proposed system in simulated assembly tasks and in a real-world human-robot assembly study and we show that both transferring the preference model from the canonical task, as well as updating the model online, contribute to improved accuracy in human action prediction. This enables the robot to proactively assist users, significantly reduce their idle time, and improve their experience working with the robot, compared to a reactive robot.
DOI: --
发表时间: 2018
影响因子: 5.1
作者:
Min Chen;S. Nikolaidis;Harold Soh;David Hsu;S. Srinivasa
通讯作者: S. Srinivasa
DOI: 10.1109/icra.2014.6907165
发表时间: 2014-09
期刊: 2014 IEEE International Conference on Robotics and Automation (ICRA)
影响因子: --
作者:
Kelsey P. Hawkins;Shray Bansal;Nam N. Vo;A. Bobick
通讯作者: Kelsey P. Hawkins;Shray Bansal;Nam N. Vo;A. Bobick
DOI: 10.1109/ro-man53752.2022.9900872
发表时间: 2021-11
期刊: 2022 31st IEEE International Conference on Robot and Human Interactive Communication (RO-MAN)
影响因子: --
作者:
Heramb Nemlekar;Runyu Guan;Guanyang Luo;Satyandra K. Gupta;S. Nikolaidis
通讯作者: Heramb Nemlekar;Runyu Guan;Guanyang Luo;Satyandra K. Gupta;S. Nikolaidis
扩展奖励学习功能:重新思考人类输入
DOI: 10.1145/3434073.3444667
发表时间: 2020
期刊: 2021 16th ACM/IEEE International Conference on Human-Robot Interaction (HRI)
影响因子: --
作者:
Andreea Bobu;Marius Wiggert;C. Tomlin;A. Dragan
通讯作者: A. Dragan
DOI: --
发表时间: 2018
期刊: Auton. Robots
影响因子: --
作者:
Thibaut Munzer;Marc Toussaint;M. Lopes
通讯作者: M. Lopes