Abstract
This paper is concerned with learning transferable forward models for push manipulation that can be applying to novel contexts and how to improve the quality of prediction when critical information is available. We propose to learn a parametric internal model for push interactions that, similar for humans, enables a robot to predict the outcome of a physical interaction even in novel contexts. Given a desired push action, humans are capable to identify where to place their finger on a new object so to produce a predictable motion of the object. We achieve the same behaviour by factorising the learning into two parts. First, we learn a set of local contact models to represent the geometrical relations between the robot pusher, the object, and the environment. Then we learn a set of parametric local motion models to predict how these contacts change throughout a push. The set of contact and motion models represent our internal model. By adjusting the shapes of the distributions over the physical parameters, we modify the internal model's response. Uniform distributions yield to coarse estimates when no information is available about the novel context. We call this an unbiased predictor. A more accurate predictor can be learned for a specific environment/object pair (e.g., low friction/high mass), called a biased predictor. The effectiveness of our approach is demonstrated in a simulated environment in which a Pioneer 3-DX robot equipped with a bumper needs to predict a push outcome for an object in a novel context, and we support those results with a proof of concept on a real robot. We train on two objects (a cube and a cylinder) for a total of 24,000 pushes in various conditions, and test on six objects encompassing a variety of shapes, sizes, and physical parameters for a total of 14,400 predicted push outcomes. Our experimental results show that both biased and unbiased predictors can reliably produce predictions in line with the outcomes of a carefully tuned physics simulator.
Highlights
Modelling push manipulation so that the outcome of a push can be accurately predicted remains largely an open question, especially in novel situations, e.g., previously unseen objects or same objects in different environments
First we evaluate the ability of our framework to select the correct contact and motion models at prediction time
We demonstrate that the unbiased predictors can make reliable predictions of how the object behaves under push operations, and that biased predictors can provide a better accuracy for specific environment/object pairs
Summary
Modelling push manipulation so that the outcome of a push can be accurately predicted remains largely an open question, especially in novel situations, e.g., previously unseen objects or same objects in different environments (i.e., a cube on a carpet or on an icy surface). As robot make their way out of factories into human environments, outer space, and beyond, they require the skill to manipulate their environment in unforeseeable circumstances. Humans possess an internal model of physical interactions (Johansson and Cole, 1992; Witney et al, 2000; Berthoz, 2002; Mehta and Schaal, 2002; Flanagan et al, 2003, 2006) that allows for them to predict the outcome of a physical interaction such as grasping, lifting, pulling, or pushing. All poses denoted by v are specified relative to a frame at the world origin WO
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
