Andrea Censi and Richard M. Murray. Learning diffeomorphism models of robotic sensorimotor cascades. In Proceedings of the IEEE International Conference on Robotics and Automation (ICRA). Saint Paul, MN, May 2012. pdfdoi supp. material slides

bibtex

    @inproceedings{censi12diffeo,
        author = "Censi, Andrea and Murray, Richard M.",
        doi = "10.1109/ICRA.2012.6225318",
        title = "Learning diffeomorphism models of robotic sensorimotor cascades",
        url = "http://purl.org/censi/2011/diffeo",
        timestamp = "2011.09.13",
        booktitle = "Proceedings of the {IEEE} International Conference on Robotics and Automation ({ICRA})",
        year = "2012",
        month = "May",
        slides = "http://purl.org/censi/research/2012-diffeo-slides.pdf",
        address = "Saint Paul, MN",
        pdf = "http://purl.org/censi/research/2012-diffeo.pdf"
    }
    

paper

slides

Abstract: The problem of bootstrapping consists in designing agents that can learn from scratch the model of their sensorimotor cascade (the series of robot actuators, the external world, and the robot sensors) and use it to achieve useful tasks. In principle, we would want to design agents that can work for any robot dynamics and any robot sensor(s). One of the difficulties of this problem is the fact that the observations are very high dimensional, the dynamics is nonlinear, and there is a wide range of "representation nuisances" to which we would want the agent to be robust. In this paper, we model the dynamics of sensorimotor cascades using diffeomorphisms of the sensel space. We show that this model captures the dynamics of camera and range-finder data, that it can be used for long-term predictions, and that it can capture nonlinear phenomena such as a limited field of view. Moreover, by analyzing the learned diffeomorphisms it is possible to recover the "linear structure" of the dynamics in a manner which is independent of the commands representation.

Supplemental materials:

• Log files