An End-to-End Human Simulator for Task-Oriented Multimodal Human-Robot Collaboration

被引:1
|
作者
Shervedani, Afagh Mehri [1 ]
Li, Siyu [1 ]
Monaikul, Natawut [2 ]
Abbasi, Bahareh [3 ]
Di Eugenio, Barbara [2 ]
Zefran, Milos [1 ]
机构
[1] Univ Illinois, Dept Elect & Comp Engn, Robot Lab, Chicago, IL 60607 USA
[2] Univ Illinois, Dept Comp Sci, Nat Language Proc Lab, Chicago, IL 60607 USA
[3] Calif State Univ Channel Islands, Dept Comp Sci, Camarillo, CA 93012 USA
基金
美国国家科学基金会;
关键词
D O I
10.1109/RO-MAN57019.2023.10309444
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
This paper proposes a neural network-based user simulator that can provide a multimodal interactive environment for training Reinforcement Learning (RL) agents in collaborative tasks involving multiple modes of communication. The simulator is trained on the existing ELDERLY-AT-HOME corpus and accommodates multiple modalities such as language, pointing gestures, and haptic-ostensive actions. The paper also presents a novel multimodal data augmentation approach, which addresses the challenge of using a limited dataset due to the expensive and time-consuming nature of collecting human demonstrations. Overall, the study highlights the potential for using RL and multimodal user simulators in developing and improving domestic assistive robots.
引用
收藏
页码:614 / 620
页数:7
相关论文
共 50 条
  • [41] An End-to-End Trainable Neural Network Model with Belief Tracking for Task-Oriented Dialog
    Liu, Bing
    Lane, Ian
    18TH ANNUAL CONFERENCE OF THE INTERNATIONAL SPEECH COMMUNICATION ASSOCIATION (INTERSPEECH 2017), VOLS 1-6: SITUATED INTERACTION, 2017, : 2506 - 2510
  • [42] Building End-to-End Task-oriented Dialogue Systems Via CNNs And Attention Mechanisms
    Song, Meina
    Chen, Chongfu
    Niu, Peiqing
    Haihong, E.
    PROCEEDINGS OF THE 11TH INTERNATIONAL CONFERENCE ON ELECTRONICS, COMPUTERS AND ARTIFICIAL INTELLIGENCE (ECAI-2019), 2019,
  • [43] End-to-End Task-oriented Dialog System through Template Slot Value Generation
    Hong, Teakgyu
    Kwon, Oh-Woog
    Kim, Young-Kil
    INTERSPEECH 2020, 2020, : 3900 - 3904
  • [44] End-to-End Task-Oriented Dialog Modeling with Semi-Structured Knowledge Management
    Gao, Silin
    Takanobu, Ryuichi
    Bosselut, Antoine
    Huang, Minlie
    IEEE/ACM Transactions on Audio Speech and Language Processing, 2022, 30 : 2173 - 2187
  • [45] A multimodal teleoperation interface for human-robot collaboration
    Si, Weiyong
    Zhong, Tianjian
    Wang, Ning
    Yang, Chenguang
    2023 IEEE INTERNATIONAL CONFERENCE ON MECHATRONICS, ICM, 2023,
  • [46] Safe Multimodal Communication in Human-Robot Collaboration
    Ferrari, Davide
    Pupa, Andrea
    Signoretti, Alberto
    Secchi, Cristian
    HUMAN-FRIENDLY ROBOTICS 2023, HFR 2023, 2024, 29 : 151 - 163
  • [47] Dynamic Task Scheduling for Human-Robot Collaboration
    Alirezazadeh, Saeid
    Alexandre, Luis A.
    IEEE ROBOTICS AND AUTOMATION LETTERS, 2022, 7 (04) : 8699 - 8704
  • [48] Visual Coordination Task for Human-Robot Collaboration
    Khatib, Maram
    Al Khudir, Khaled
    De Luca, Alessandro
    2017 IEEE/RSJ INTERNATIONAL CONFERENCE ON INTELLIGENT ROBOTS AND SYSTEMS (IROS), 2017, : 3762 - 3768
  • [49] Task-oriented human-robot interaction control of a robotic glove utilizing forearm electromyography
    Wang, Xianhe
    Zhang, Haotian
    Teng, Long
    Tang, Chak Yin
    JOURNAL OF THE FRANKLIN INSTITUTE-ENGINEERING AND APPLIED MATHEMATICS, 2023, 360 (16): : 11351 - 11370
  • [50] Timing of Multimodal Robot Behaviors during Human-Robot Collaboration
    Jensen, Lars Christian
    Fischer, Kerstin
    Suvei, Stefan-Daniel
    Bodenhagen, Leon
    2017 26TH IEEE INTERNATIONAL SYMPOSIUM ON ROBOT AND HUMAN INTERACTIVE COMMUNICATION (RO-MAN), 2017, : 1061 - 1066