An Object-Centric Paradigm for Robot Programming by Demonstration

被引：5
|
作者：
Huang, Di-Wei [1 ]
Katz, Garrett E. [1 ]
Langsfeld, Joshua D. [2 ]
Oh, Hyuk [3 ]
Gentili, Rodolphe J. [4 ]
Reggia, James A. [1 ]
机构：
[1] Univ Maryland, Dept Comp Sci, UMIACS, College Pk, MD 20742 USA
[2] Univ Maryland, Dept Mech Engn, College Pk, MD 20742 USA
[3] Univ Maryland, Neurosci & Cognit Sci Program, College Pk, MD 20742 USA
[4] Univ Maryland, Dept Kinesiol, Grad Program Neurosci & Cognit Sci, Maryland Robot Ctr, College Pk, MD 20742 USA
来源：
FOUNDATIONS OF AUGMENTED COGNITION, AC 2015 | 2015年 / 9183卷
关键词：
Programming by demonstration; Imitation learning; Human-robot interactions; IMITATION;
D O I：
10.1007/978-3-319-20816-9_71
中图分类号：
TP18 [人工智能理论];
学科分类号：
081104 ; 0812 ; 0835 ; 1405 ;
摘要：
In robot programming by demonstration, we hypothesize that in a class of procedural tasks where the end goal primarily consists of the states of objects that are external to a task performer, one can significantly reduce complexity of a robot learner by not processing a human demonstrator's motions at all. In this class of tasks, object behaviors are far more critical than human behaviors. Based on this virtual demonstrator hypothesis, this paper presents a paradigm where a human demonstrates an object manipulation task in a simulated world without any of the human demonstrator's body parts being sensed by a robot learner. Based on the object movements alone, the robot learns to perform the same task in the physical world. These results provide strong support for the virtual demonstrator hypothesis.
引用
下载
收藏
页码：745 / 756
页数：12
相关论文
共 50 条
  • [41] Deep convolution neural network with scene-centric and object-centric information for object detection
    Shen, Zong-Ying
    Han, Shiang-Yu
    Fu, Li-Chen
    Hsiao, Pei-Yung
    Lau, Yo-Chung
    Chang, Sheng-Jen
    IMAGE AND VISION COMPUTING, 2019, 85 : 14 - 25
  • [42] OBJECT-CENTRIC VIDEO PREDICTION VIA DECOUPLING OF OBJECT DYNAMICS AND INTERACTIONS
    Villar-Corrales, Angel
    Wahdan, Ismail
    Behnke, Sven
    2023 IEEE INTERNATIONAL CONFERENCE ON IMAGE PROCESSING, ICIP, 2023, : 570 - 574
  • [43] Predicting Coupling of Object-Centric Business Process Implementations
    Wahler, Ksenia
    Kuester, Jochen M.
    BUSINESS PROCESS MANAGEMENT, 2008, 5240 : 148 - 163
  • [44] Compositional scene modeling with global object-centric representations
    Tonglin Chen
    Zhimeng Shen
    Bin Li
    Xiangyang Xue
    Machine Learning, 2024, 113 : 3505 - 3524
  • [45] Object-centric Representation Learning for Video Scene Understanding
    Zhou Y.
    Zhang H.
    Park S.
    Yoo B.
    Qi X.
    IEEE Transactions on Pattern Analysis and Machine Intelligence, 2024, 46 (12) : 1 - 13
  • [46] Object-Centric Approach to Prediction and Labeling of Manipulation Tasks
    Chen, Ee Heng
    Burschka, Darius
    2018 IEEE INTERNATIONAL CONFERENCE ON ROBOTICS AND AUTOMATION (ICRA), 2018, : 6931 - 6938
  • [47] Object-Centric Scene Representations Using Active Inference
    Van de Maele, Toon
    Verbelen, Tim
    Mazzaglia, Pietro
    Ferraro, Stefano
    Dhoedt, Bart
    NEURAL COMPUTATION, 2024, 36 (04) : 677 - 704
  • [48] Self-supervised Object-Centric Learning for Videos
    Aydemir, Gorkay
    Xie, Weidi
    Guney, Fatma
    ADVANCES IN NEURAL INFORMATION PROCESSING SYSTEMS 36 (NEURIPS 2023), 2023,
  • [49] Quantized Disentangled Representations for Object-Centric Visual Tasks
    Kirilenko, Daniil
    Korchemnyi, Alexandr
    Smirnov, Konstantin
    Kovalev, Alexey K.
    Panov, Aleksandr I.
    PATTERN RECOGNITION AND MACHINE INTELLIGENCE, PREMI 2023, 2023, 14301 : 514 - 522
  • [50] Efficient Evaluation of Object-Centric Exploration Queries for Visualization
    Wu, You
    Harb, Boulos
    Yang, Jun
    Yu, Cong
    PROCEEDINGS OF THE VLDB ENDOWMENT, 2015, 8 (12): : 1752 - 1763
12345