Inferring the Material Properties of Granular Media for Robotic Tasks

Matl, Carolyn; Narang, Yashraj; Bajcsy, Růžena; Ramos, Fábio; Fox, Dieter

doi:10.1109/icra40945.2020.9197063

Cited by 31 publications

(19 citation statements)

References 36 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…BayesSim-MDRFF extracts RFF features from trajectories before passing the data to the mixture density network for training. This variant has been used in experiments with inferring material properties of granular media [34] and showed strong performance on that challenging task. One key aspect to note is that [34] domain-specific features, as we described in the background in Section II.…”

Section: Hardware Results For Real-to-simmentioning

confidence: 99%

“…BayesSim [7] is a likelihood-free method that has been applied to a variety of robotics problems [32], [8], [33], [34], [35]. It offers a principled way of obtaining posteriors over simulation parameters, and does not place restrictions on simulator type of properties, i.e.…”

Section: B Probabilistic Parameter Inferencementioning

confidence: 99%

“…robot joint angles, object poses and velocities) used these states directly. [34] applied BayesSim to scenarios with granular media and developed domainspecific summary statistics of depth images of granular formations, such as dispersion and statistical dependence of the grain locations (mean, standard deviation, interquartile range, kurtosis, and distance correlation). In this work, we present a novel methodology to perform inference using state trajectories directly from images, without the need to first extract sufficient statistics from trajectories.…”

Section: B Probabilistic Parameter Inferencementioning

confidence: 99%

See 2 more Smart Citations

A Bayesian Treatment of Real-to-Sim for Deformable Object Manipulation

Antonova¹,

Yang²,

Sundaresan³

et al. 2021

Preprint

Self Cite

View full text Add to dashboard Cite

Deformable object manipulation remains a challenging task in robotics research. Conventional techniques for parameter inference and state estimation typically rely on a precise definition of the state space and its dynamics. While this is appropriate for rigid objects and robot states, it is challenging to define the state space of a deformable object and how it evolves in time. In this work, we pose the problem of inferring physical parameters of deformable objects as a probabilistic inference task defined with a simulator. We propose a novel methodology for extracting state information from image sequences via a technique to represent the state of a deformable object as a distribution embedding. This allows to incorporate noisy state observations directly into modern Bayesian simulation-based inference tools in a principled manner. Our experiments confirm that we can estimate posterior distributions of physical properties, such as elasticity, friction and scale of highly deformable objects, such as cloth and ropes. Overall, our method addresses the real-to-sim problem probabilistically and helps to better represent the evolution of the state of deformable objects.

show abstract

Section: Hardware Results For Real-to-simmentioning

confidence: 99%

Section: B Probabilistic Parameter Inferencementioning

confidence: 99%

Section: B Probabilistic Parameter Inferencementioning

confidence: 99%

See 1 more Smart Citation

A Bayesian Treatment of Real-to-Sim for Deformable Object Manipulation

Antonova¹,

Yang²,

Sundaresan³

et al. 2021

Preprint

Self Cite

View full text Add to dashboard Cite

show abstract

“…Prior work has looked at the grasping of a fixed target mass of food, which would be difficult to generalize to an arbitrary target mass [4]. There has been some research and development on target-mass grasping of granular foods [5] including our study [3], manipulation for desired shape [6], and estimation of food properties [7]. Entangled foods behave differently than granular foods, in that they are likely to pull along neighbouring pieces when grasped, and predicting the degree of entanglement is difficult.…”

Section: A Manipulation Of Small Pieces Of Foodmentioning

confidence: 99%

Target-mass Grasping of Entangled Food using Pre-grasping & Post-grasping

Takahashi,

Fukaya,

Ummadisingu

2022

Preprint

View full text Add to dashboard Cite

Food packing industries typically use seasonal ingredients with immense variety that factory workers manually pack. For small pieces of food picked by volume or weight that tend to get entangled, stick or clump together, it is difficult to predict how intertwined they are from a visual examination, making it a challenge to grasp the requisite target mass accurately. Workers rely on a combination of weighing scales and a sequence of complex maneuvers to separate out the food and reach the target mass. This makes automation of the process a non-trivial affair. In this study, we propose methods that combines 1) pre-grasping to reduce the degree of the entanglement, 2) post-grasping to adjust the grasped mass using a novel gripper mechanism to carefully discard excess food when the grasped amount is larger than the target mass, and 3) selecting the grasping point to grasp an amount likely to be reasonably higher than target grasping mass with confidence. We evaluate the methods on a variety of foods that entangle, stick and clump, each of which has a different size, shape, and material properties such as volumetric mass density. We show significant improvement in grasp accuracy of userspecified target masses using our proposed methods.

show abstract

“…Probabilistic inference techniques, on the other hand, seek to infer a distribution of simulation parameters that allows downstream applications to evaluate the uncertainty of the estimates. Such methods have been applied to learn conditional densities of simulation parameters given trajectories from the simulator and the real system [27,52,53,68,73,80].…”

Section: Parameter Inference For Simulatorsmentioning

confidence: 99%

DiSECt: A Differentiable Simulation Engine for Autonomous Robotic Cutting

Heiden

Macklin

Narang

et al. 2021

Robotics: Science and Systems XVII

Self Cite

View full text Add to dashboard Cite

Robotic cutting of soft materials is critical for applications such as food processing, household automation, and surgical manipulation. As in other areas of robotics, simulators can facilitate controller verification, policy learning, and dataset generation. Moreover, differentiable simulators can enable gradient-based optimization, which is invaluable for calibrating simulation parameters and optimizing controllers. In this work, we present DiSECt: the first differentiable simulator for cutting soft materials. The simulator augments the finite element method (FEM) with a continuous contact model based on signed distance fields (SDF), as well as a continuous damage model that inserts springs on opposite sides of the cutting plane and allows them to weaken until zero stiffness, enabling crack formation. Through various experiments, we evaluate the performance of the simulator. We first show that the simulator can be calibrated to match resultant forces and deformation fields from a state-of-the-art commercial solver and real-world cutting datasets, with generality across cutting velocities and object instances. We then show that Bayesian inference can be performed efficiently by leveraging the differentiability of the simulator, estimating posteriors over hundreds of parameters in a fraction of the time of derivativefree methods. Finally, we illustrate that control parameters in the simulation can be optimized to minimize cutting forces via lateral slicing motions. We publish videos and additional results on our project website at https://diff-cutting-sim.github.io.

show abstract

Inferring the Material Properties of Granular Media for Robotic Tasks

Cited by 31 publications

References 36 publications

A Bayesian Treatment of Real-to-Sim for Deformable Object Manipulation

A Bayesian Treatment of Real-to-Sim for Deformable Object Manipulation

Target-mass Grasping of Entangled Food using Pre-grasping & Post-grasping

DiSECt: A Differentiable Simulation Engine for Autonomous Robotic Cutting

Contact Info

Product

Resources

About