In this paper, we present a novel methodology to obtain imitative and innovative postural movements in a humanoid based on human demonstrations in a different kinematic scale. We collected motion data from a group of human participants standing up from a chair. Modeling the human as an actuated 3-link kinematic chain, and by defining a multi-objective reward function of zero moment point and joint torques to represent the stability and effort, we computed reward profiles for each demonstration. Since individual reward profiles show variability across demonstrating trials, the underlying state transition probabilities were modeled using a Markov chain. Based on the argument that the reward profiles of the robot should show the same temporal structure of those of the human, we used differential evolution to compute a trajectory that fits all humanoid constraints and minimizes the difference between the robot reward profile and the predicted profile if the robot imitates the human. Therefore, robotic imitation involves developing a policy that results in a temporal reward structure, matching that of a group of human demonstrators across an array of demonstrations. Skill innovation was achieved by optimizing a signed reward error after imitation was achieved. Experimental results using the humanoid HOAP-3 are shown. ; The research leading to these results has received funding from the ARCADIA project DPI2010-21047-C02-01, funded by CICYT project grant on behalf of Spanish Ministry of Economy and Competitiveness and from the RoboCity2030-II-CM project (S2009/DPI-1559), funded by Programas de Actividades I+D en la Comunidad de Madrid and co-funded by Structural Funds of the EU. ; Publicado


    Zugriff

    Download


    Exportieren, teilen und zitieren



    Titel :

    Full-Body Postural Control of a Humanoid Robot with Both Imitation Learning and Skill Innovation



    Erscheinungsdatum :

    01.04.2014


    Anmerkungen:

    AR/0000015524



    Medientyp :

    Aufsatz (Zeitschrift)


    Format :

    Elektronische Ressource


    Sprache :

    Englisch



    Klassifikation :

    DDC:    629



    Bidirectional Human-Robot Learning: Imitation and Skill Improvement

    Sousa Ewerton, Marco Antônio | TIBKAT | 2020


    Modular Real-Time System for Upper-Body Motion Imitation on Humanoid Robot Talos

    Savevska, Kristina / Simonic, Mihael / Ude, Aleš | TIBKAT | 2021


    Study of similar motion imitation of stepping upstairs for humanoid robot

    Ke, Wen-De / Peng, Zhi-Ping / Chen, Ke et al. | British Library Online Contents | 2013


    Study on similarity imitation constraints of biped walking for humanoid robot

    Ke, W.-d. / Hong, B.-r. / Cui, G. et al. | British Library Online Contents | 2013


    On the imitation of goal directed movements of a humanoid robot

    Bao, Y. / Cuijpers, R.H. | BASE | 2017

    Freier Zugriff