Imitation Learning from Video by Leveraging Proprioception

被引:0
|
作者
Torabi, Faraz [1 ]
Warnell, Garrett [2 ]
Stone, Peter [1 ]
机构
[1] Univ Texas Austin, Austin, TX 78712 USA
[2] Army Res Lab, Austin, TX USA
基金
美国国家科学基金会;
关键词
D O I
暂无
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
Classically, imitation learning algorithms have been developed for idealized situations, e.g., the demonstrations are often required to be collected in the exact same environment and usually include the demonstrator's actions. Recently, however, the research community has begun to address some of these shortcomings by offering algorithmic solutions that enable imitation learning from observation (IfO), e.g., learning to perform a task from visual demonstrations that may be in a different environment and do not include actions. Motivated by the fact that agents often also have access to their own internal states (i.e., proprioception), we propose and study an IfO algorithm that leverages this information in the policy learning process. The proposed architecture learns policies over proprioceptive state representations and compares the resulting trajectories visually to the demonstration data. We experimentally test the proposed technique on several MuJoCo domains and show that it outperforms other imitation from observation algorithms by a large margin.
引用
收藏
页码:3585 / 3591
页数:7
相关论文
共 50 条
  • [1] Adversarial Imitation Learning from Video using a State Observer
    Karnan, Haresh
    Torabi, Faraz
    Warnell, Garrett
    Stone, Peter
    2022 IEEE INTERNATIONAL CONFERENCE ON ROBOTICS AND AUTOMATION (ICRA 2022), 2022, : 2452 - 2458
  • [2] Imitation Learning from a Single Demonstration Leveraging Vector Quantization for Robotic Harvesting
    Porichis, Antonios
    Inglezou, Myrto
    Kegkeroglou, Nikolaos
    Mohan, Vishwanathan
    Chatzakos, Panagiotis
    ROBOTICS, 2024, 13 (07)
  • [3] Leveraging Imitation Learning on Pose Regulation Problem of a Robotic Fish
    Zhang, Tianhao
    Yue, Lu
    Wang, Chen
    Sun, Jinan
    Zhang, Shikun
    Wei, Airong
    Xie, Guangming
    IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS, 2024, 35 (03) : 4232 - 4245
  • [4] Imitation from Observation: Learning to Imitate Behaviors from Raw Video via Context Translation
    Liu, YuXuan
    Gupta, Abhishek
    Abbeel, Pieter
    Levine, Sergey
    2018 IEEE INTERNATIONAL CONFERENCE ON ROBOTICS AND AUTOMATION (ICRA), 2018, : 1118 - 1125
  • [5] NAO Robot Learns to Interact with Humans through Imitation Learning from Video Observation
    Kolagar, Seyed Adel Alizadeh
    Taheri, Alireza
    Meghdari, Ali. F. F.
    JOURNAL OF INTELLIGENT & ROBOTIC SYSTEMS, 2023, 109 (01)
  • [6] NAO Robot Learns to Interact with Humans through Imitation Learning from Video Observation
    Seyed Adel Alizadeh Kolagar
    Alireza Taheri
    Ali F. Meghdari
    Journal of Intelligent & Robotic Systems, 2023, 109
  • [7] Intelligent Edge: Leveraging Deep Imitation Learning for Mobile Edge Computation Offloading
    Yu, Shuai
    Chen, Xu
    Yang, Lei
    Wu, Di
    Bennis, Mehdi
    Zhang, Junshan
    IEEE WIRELESS COMMUNICATIONS, 2020, 27 (01) : 92 - 99
  • [8] Imitation Learning from Observation
    Torabi, Faraz
    THIRTY-THIRD AAAI CONFERENCE ON ARTIFICIAL INTELLIGENCE / THIRTY-FIRST INNOVATIVE APPLICATIONS OF ARTIFICIAL INTELLIGENCE CONFERENCE / NINTH AAAI SYMPOSIUM ON EDUCATIONAL ADVANCES IN ARTIFICIAL INTELLIGENCE, 2019, : 9900 - 9901
  • [9] Human-Inspired Video Imitation Learning on Humanoid Model
    Lee, Chun Hei
    Yueh, Nicole Chee Lin
    Leung, Chun Yin
    Woo, Kam Tim
    INTERNATIONAL JOURNAL OF SEMANTIC COMPUTING, 2024, 18 (02) : 149 - 173
  • [10] Human-inspired Video Imitation Learning on Humanoid Model
    Lee, Chun Hei
    Yueh, Nicole Chee Lin
    Woo, Kam Tim
    2022 SIXTH IEEE INTERNATIONAL CONFERENCE ON ROBOTIC COMPUTING, IRC, 2022, : 345 - 352