Visual Geometric Skill Inference by Watching Human Demonstration

被引:0
|
作者
Jin, Jun [1 ]
Petrich, Laura [1 ]
Zhang, Zichen [1 ]
Dehghan, Masood [1 ]
Jagersand, Martin [1 ]
机构
[1] Univ Alberta, Dept Comp Sci, Edmonton, AB T6G 2E8, Canada
来源
2020 IEEE INTERNATIONAL CONFERENCE ON ROBOTICS AND AUTOMATION (ICRA) | 2020年
关键词
D O I
10.1109/icra40945.2020.9196570
中图分类号
TP [自动化技术、计算机技术];
学科分类号
0812 ;
摘要
We study the problem of learning manipulation skills from human demonstration video by inferring the association relationships between geometric features. Motivation for this work stems from the observation that humans perform eye-hand coordination tasks by using geometric primitives to define a task while a geometric control error drives the task through execution. We propose a graph based kernel regression method to directly infer the underlying association constraints from human demonstration video using Incremental Maximum Entropy Inverse Reinforcement Learning (InMaxEnt IRL). The learned skill inference provides human readable task definition and outputs control errors that can be directly plugged into traditional controllers. Our method removes the need for tedious feature selection and robust feature trackers required in traditional approaches (e.g. feature-based visual servoing). Experiments show our method infers correct geometric associations even with only one human demonstration video and can generalize well under variance.
引用
收藏
页码:8985 / 8991
页数:7
相关论文
共 50 条
  • [1] Inference making skill in children with visual impairments
    Sullivan, Susan
    Oakhill, Jane
    RESEARCH IN DEVELOPMENTAL DISABILITIES, 2020, 104
  • [2] THE INFLUENCE OF VISUAL DEMONSTRATION AND VERBAL INSTRUCTION ON LEARNING A COMPLEX MOTOR SKILL
    Baric, Renata
    Busko, Vesna
    5TH INTERNATIONAL SCIENTIFIC CONFERENCE ON KINESIOLOGY, PROCEEDINGS BOOK: KINESIOLOGY RESEARCH TRENDS AND APPLICATIONS, 2008, : 487 - +
  • [3] Automated Assembly Skill Acquisition through Human Demonstration
    Gu, Ye
    Sheng, Weihua
    Ou, Yongsheng
    2014 IEEE INTERNATIONAL CONFERENCE ON ROBOTICS AND AUTOMATION (ICRA), 2014, : 6313 - 6318
  • [4] Visual Inference of Human Emotion and Behaviour
    Gong, Shaogang
    Shan, Caifeng
    Xiang, Tao
    ICMI'07: PROCEEDINGS OF THE NINTH INTERNATIONAL CONFERENCE ON MULTIMODAL INTERFACES, 2007, : 22 - 29
  • [5] Quantitative evaluation for skill controller based on comparison with human demonstration
    Hirana, K
    Nozaki, T
    Suzuki, T
    Okuma, S
    Itabashi, K
    Fujiwara, F
    IEEE TRANSACTIONS ON CONTROL SYSTEMS TECHNOLOGY, 2004, 12 (04) : 609 - 619
  • [6] Automated assembly skill acquisition and implementation through human demonstration
    Gu, Ye
    Sheng, Weihua
    Crick, Christopher
    Ou, Yongsheng
    ROBOTICS AND AUTONOMOUS SYSTEMS, 2018, 99 : 1 - 16
  • [7] Augmented Visual Feedback for Complex Motor Skill Acquisition: A Demonstration with Healthy Young Adults
    Miyamoto, Wakako
    Kawahara, Yasuhiro
    Mori, Suguru
    Setsu, Katsuyoshi
    Hattori, Fumitada
    PERCEPTUAL AND MOTOR SKILLS, 2023, 130 (06) : 2685 - 2699
  • [8] VISUAL SCANNING OF GEOMETRIC FIGURES BY HUMAN NEWBORN
    SALAPATE.P
    JOURNAL OF COMPARATIVE AND PHYSIOLOGICAL PSYCHOLOGY, 1968, 66 (02): : 247 - &
  • [9] Skill acquisition from human demonstration using a hidden Markov model
    Hovland, GE
    Sikka, P
    McCarragher, BJ
    1996 IEEE INTERNATIONAL CONFERENCE ON ROBOTICS AND AUTOMATION, PROCEEDINGS, VOLS 1-4, 1996, : 2706 - 2711
  • [10] Human–robot skill transmission for mobile robot via learning by demonstration
    Jiehao Li
    Junzheng Wang
    Shoukun Wang
    Chenguang Yang
    Neural Computing and Applications, 2023, 35 : 23441 - 23451