Learning Robotic Manipulation of Granular Media
This work addresses robotic manipulation challenges for granular media, which is incremental as it builds on existing methods with domain-specific optimizations.
The paper tackled the problem of robotic manipulation of granular media by evaluating predictive models for scooping and dumping actions to deform it into a desired shape, and found that a tailored convolutional network with explicit physical mechanics prediction outperformed hand-crafted and value-network baselines.
In this paper, we examine the problem of robotic manipulation of granular media. We evaluate multiple predictive models used to infer the dynamics of scooping and dumping actions. These models are evaluated on a task that involves manipulating the media in order to deform it into a desired shape. Our best performing model is based on a highly-tailored convolutional network architecture with domain-specific optimizations, which we show accurately models the physical interaction of the robotic scoop with the underlying media. We empirically demonstrate that explicitly predicting physical mechanics results in a policy that out-performs both a hand-crafted dynamics baseline, and a "value-network", which must otherwise implicitly predict the same mechanics in order to produce accurate value estimates.