Inferring the Material Properties of Granular Media for Robotic Tasks

Abstract

Granular media (e.g., cereal grains, plastic resin pellets, and pills) are ubiquitous in robotics-integrated industries, such as agriculture, manufacturing, and pharmaceutical development. This prevalence mandates the accurate and efficient simulation of these materials. This work presents a software and hardware framework that automatically calibrates a fast physics simulator to accurately simulate granular materials by inferring material properties from real-world depth images of granular formations (i.e., piles and rings). Specifically, coefficients of sliding friction, rolling friction, and restitution of grains are estimated from summary statistics of grain formations using likelihood-free Bayesian inference. The calibrated simulator accurately predicts unseen granular formations in both simulation and experiment; furthermore, simulator predictions are shown to generalize to more complex tasks, including using a robot to pour grains into a bowl, as well as to create a desired pattern of piles and rings. Visualizations of the framework and experiments can be viewed at https://www.youtube.com/watch?v=X-5Sk2TUET4.

Playing with Food: Learning Food Item Representations through Interactive Exploration

“…Many recent works have utilized simulations in order to learn dynamics models and material properties of deformable objects [20,29]. For example, Matl et al [21] collect data on granular materials and compare the visual depth information with simulation results in order to infer their properties. Yan et al [32] learn latent dynamics models and visual representations of deformable objects by manipulating them in simulation and using contrastive estimation, which is similar to our approach.…”

Digger Finger: GelSight Tactile Sensor for Object Identification Inside Granular Media

“…Robotics research related to granular media has been fall primarily within the scope of automated operation of construction equipment such as scooping [6], legged locomotion [7,8], gripper design [9], manipulators [10], haptic displays [11,12] and in robotic pouring tasks [13,14], to name a few. In contrast, work on robotic manipulation of and within granular media has only recently begun receiving attention from the research community.…”