Inferring the Material Properties of Granular Media for Robotic Tasks

Matl Carolyn
Matl Carolyn
Ramos Fabio
Ramos Fabio

ICRA, pp. 2770-2777, 2020.

Cited by: 0|Bibtex|Views39|DOI:https://doi.org/10.1109/ICRA40945.2020.9197063
EI
Other Links: arxiv.org|dblp.uni-trier.de|academic.microsoft.com
Weibo:
Robotics demos showed that the inferred parameters generalized well to different pouring heights, and that a robot can effectively reason about granular material to pour desired granular formations and predict its behavior in dynamic scenarios

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 automati...More

Code:

Data:

0
Introduction
  • A granular material is a collection of discrete macroscopic particles that primarily experience inelastic collisions and are usually unaffected by temperature [17].
  • This definition spans a wide variety of materials, from sand and stones to powders and pills to seeds and cereals, making granular material one of the most manipulated substances in the construction, pharmaceutical, agriculture, and food industries [38].
  • While recent work has delivered promising advances in the formulation of continuum models for granular materials [18], [3], [15], [33], [20], [19], researchers frequently rely on numerical techniques and simulations to corroborate and extend their predictions
Highlights
  • A granular material is a collection of discrete macroscopic particles that primarily experience inelastic collisions and are usually unaffected by temperature [17]
  • The physics community has posed the following challenge: how can particle-scale parameters be determined from observations of macroscale behavior [1]? Answering this could lead to more efficient methods for refining simulations to match real macroscale behavior. This paper addresses this question by integrating a framework for likelihood-free Bayesian inference (BayesSim [37]) with a fast and efficient physics simulation platform capable of discrete element method simulations (NVIDIA’s Isaac Simulator [2]), as well as experimental observations using off-the-shelf depth cameras
  • The first objective was to test the accuracy of the trained BayesSim model on simulated depth images
  • The difference between the piles was evaluated via the L2norm error between T (Xs,i) and T (Xs,o), both standardized over the summary statistics of the training dataset
  • All 16 summary statistics defined in Section IV-D are used to calculate the L2-norm error
  • Robotics demos showed that the inferred parameters generalized well to different pouring heights, and that a robot can effectively reason about granular material to pour desired granular formations and predict its behavior in dynamic scenarios
Methods
  • The goal of this paper’s proposed framework is to estimate granular parameters θ = [μs, μr, e]T from summary statistics T (Xr) using BayesSim, which approximates the posterior p(θ |T (X) = T (Xr)) by sampling from a simulator g(θ ).
  • After the initial cost of running N simulations and training the model, BayesSim can quickly produce posterior approximations, making it a compelling method for granular material inference problems in robotic applications.
Results
  • The first objective was to test the accuracy of the trained BayesSim model on simulated depth images.
  • The difference between the piles was evaluated via the L2norm error between T (Xs,i) and T (Xs,o), both standardized over the summary statistics of the training dataset.
  • The authors avoid evaluating accuracy via direct comparisons of the downsampled depth images, as the computed error would be highly sensitive to misalignments of the scattered grains rather than reflect meaningful differences in spatial distributions
Conclusion
  • The material parameters of granular materials were inferred using a new framework combining likelihood-free Bayesian inference, efficient simulation, and simple experiments.
  • Simulation-to-simulation inference was highly accurate, and simulation-to-experiment inference trailed closely in performance.
  • More elaborate robotic manipulation tasks can be explored, such as moving the end effector along a trajectory to create an asymmetric grain trail, or scooping and pouring granular material into and out of assorted containers
Summary
  • Introduction:

    A granular material is a collection of discrete macroscopic particles that primarily experience inelastic collisions and are usually unaffected by temperature [17].
  • This definition spans a wide variety of materials, from sand and stones to powders and pills to seeds and cereals, making granular material one of the most manipulated substances in the construction, pharmaceutical, agriculture, and food industries [38].
  • While recent work has delivered promising advances in the formulation of continuum models for granular materials [18], [3], [15], [33], [20], [19], researchers frequently rely on numerical techniques and simulations to corroborate and extend their predictions
  • Methods:

    The goal of this paper’s proposed framework is to estimate granular parameters θ = [μs, μr, e]T from summary statistics T (Xr) using BayesSim, which approximates the posterior p(θ |T (X) = T (Xr)) by sampling from a simulator g(θ ).
  • After the initial cost of running N simulations and training the model, BayesSim can quickly produce posterior approximations, making it a compelling method for granular material inference problems in robotic applications.
  • Results:

    The first objective was to test the accuracy of the trained BayesSim model on simulated depth images.
  • The difference between the piles was evaluated via the L2norm error between T (Xs,i) and T (Xs,o), both standardized over the summary statistics of the training dataset.
  • The authors avoid evaluating accuracy via direct comparisons of the downsampled depth images, as the computed error would be highly sensitive to misalignments of the scattered grains rather than reflect meaningful differences in spatial distributions
  • Conclusion:

    The material parameters of granular materials were inferred using a new framework combining likelihood-free Bayesian inference, efficient simulation, and simple experiments.
  • Simulation-to-simulation inference was highly accurate, and simulation-to-experiment inference trailed closely in performance.
  • More elaborate robotic manipulation tasks can be explored, such as moving the end effector along a trajectory to create an asymmetric grain trail, or scooping and pouring granular material into and out of assorted containers
Related work
  • A. Granular Materials in Physics

    The mechanics of granular materials is an active area of research within the physics community. Recent advancements present new constitutive relations of granular media that relate flow behavior to particle-scale properties like grain size [19], geometry [30], and surface friction [21]. Throughout this body of work, DEM simulators are consistently used to evaluate and extend theoretical explanations [12], [42], [21], [18], [30]. This emphasis on simulation encourages the development of frameworks that can infer difficult-to-measure material parameters (e.g., frictional coefficients of a grain) from macroscale behavior of collections of grains (e.g., pile shape). This work proposes one such framework, designed primarily for robotic applications due to its speed, efficiency, and minimal hardware requirements.
Funding
  • The authors were supported in part by the National Science Foundation Graduate Research Fellowship
Reference
  • Granular material by design. https://jfi.uchicago.
    Findings
  • NVIDIA Isaac: Virtual simulator for robots. //www.nvidia.com/en-us/deep-learning-ai/
    Findings
  • industries/robotics/. Accessed: 2019-09-11.
    Google ScholarFindings
  • [3] L Anand and C Gu. Granular materials: constitutive equations and strain localization. Journal of the Mechanics and Physics of Solids, 48(8):1701–1733, 2000.
    Google ScholarLocate open access versionFindings
  • [4] L Benvenuti, C Kloss, and S Pirker. Identification of DEM simulation parameters by artificial neural networks and bulk experiments. Powder technology, 291:456–465, 2016.
    Google ScholarLocate open access versionFindings
  • [5] Eric Brown, Nicholas Rodenberg, John Amend, Annan Mozeika, Erik Steltz, Mitchell R Zakin, Hod Lipson, and Heinrich M Jaeger. Universal robotic gripper based on the jamming of granular material. Proceedings of the National Academy of Sciences, 107(44):18809–18814, 2010.
    Google ScholarLocate open access versionFindings
  • [6] Yevgen Chebotar, Ankur Handa, Viktor Makoviychuk, Miles Macklin, Jan Issac, Nathan Ratliff, and Dieter Fox. Closing the sim-to-real loop: Adapting simulation randomization with real world experience. In 2019 International Conference on Robotics and Automation (ICRA), pages 8973–8979. IEEE, 2019.
    Google ScholarLocate open access versionFindings
  • [7] Carolyn L Chen, Jeffrey O Snyder, and Peter J Ramadge. Learning to identify container contents through tactile vibration signatures. In 2016 IEEE International Conference on Simulation, Modeling, and
    Google ScholarLocate open access versionFindings
  • Programming for Autonomous Robots (SIMPAR), pages 43–48. IEEE, 2016.
    Google ScholarFindings
  • [8] Hongyang Cheng, Takayuki Shuku, Klaus Thoeni, Pamela Tempone, Stefan Luding, and Vanessa Magnanimo. An iterative Bayesian filtering framework for fast and automated calibration of DEM models.
    Google ScholarFindings
  • [9] Matteo Cianchetti, Tommaso Ranzani, Giada Gerboni, Thrishantha Nanayakkara, Kaspar Althoefer, Prokar Dasgupta, and Arianna Menciassi. Soft robotics technologies to address shortcomings in today’s minimally invasive surgery: the STIFF-FLOP approach. Soft Robotics, 1(2):122–131, 2014.
    Google ScholarLocate open access versionFindings
  • [10] Samuel Clarke, Travers Rhodes, Christopher G Atkeson, and Oliver Kroemer. Learning audio feedback for estimating amount and flow of granular material. In Conference on Robot Learning, pages 529–550, 2018.
    Google ScholarLocate open access versionFindings
  • [11] CJ Coetzee. Calibration of the discrete element method. Powder Technology, 310:104–142, 2017.
    Google ScholarLocate open access versionFindings
  • [12] Peter A Cundall and Otto DL Strack. A discrete numerical model for granular assemblies. geotechnique, 29(1):47–65, 1979.
    Google ScholarLocate open access versionFindings
  • [13] Karola Dierichs, Tobias Schwinn, and Achim Menges. Robotic pouring of aggregate structures. In Rob| Arch 2012, pages 196–205. Springer, 2013.
    Google ScholarLocate open access versionFindings
  • [14] Huy Q Do, Alejandro M Aragón, and Dingena L Schott. Automated discrete element method calibration using genetic and optimization algorithms. In EPJ Web of Conferences, volume 140, page 15011. EDP Sciences, 2017.
    Google ScholarLocate open access versionFindings
  • [15] Sachith Dunatunga and Ken Kamrin. Continuum modelling and simulation of granular flows through their many phases. Journal of Fluid Mechanics, 779:483–513, 2015.
    Google ScholarLocate open access versionFindings
  • [16] Yuanming Hu, Yu Fang, Ziheng Ge, Ziyin Qu, Yixin Zhu, Andre Pradhana, and Chenfanfu Jiang. A moving least squares material point method with displacement discontinuity and two-way rigid body coupling. ACM Transactions on Graphics (TOG), 37(4):150, 2018.
    Google ScholarLocate open access versionFindings
  • [17] Heinrich M Jaeger and Sidney R Nagel. Physics of the granular state. Science, 255(5051):1523–1531, 1992.
    Google ScholarLocate open access versionFindings
  • [18] Pierre Jop, Yoël Forterre, and Olivier Pouliquen. A constitutive law for dense granular flows. Nature, 441(7094):727, 2006.
    Google ScholarLocate open access versionFindings
  • [19] Ken Kamrin. Quantitative rheological model for granular materials: The importance of particle size. Handbook of Materials Modeling: Applications: Current and Emerging Materials, pages 1–24, 2018.
    Google ScholarLocate open access versionFindings
  • [20] Ken Kamrin. Non-locality in granular flow: Phenomenology and modeling approaches. Frontiers in Physics, 7:116, 2019.
    Google ScholarLocate open access versionFindings
  • [21] Ken Kamrin and Georg Koval. Effect of particle surface friction on nonlocal constitutive behavior of flowing granular media. Computational Particle Mechanics, 1(2):169–176, 2014.
    Google ScholarLocate open access versionFindings
  • [22] Margaret A Knuth, JB Johnson, MA Hopkins, RJ Sullivan, and JM Moore. Discrete element modeling of a Mars Exploration Rover wheel in granular material. Journal of Terramechanics, 49(1):27–36, 2012.
    Google ScholarLocate open access versionFindings
  • [23] Chen Li, Tingnan Zhang, and Daniel I Goldman. A terradynamics of legged locomotion on granular media. science, 339(6126):1408–1412, 2013.
    Google ScholarLocate open access versionFindings
  • [24] Jacky Liang, Viktor Makoviychuk, Ankur Handa, Nuttapong Chentanez, Miles Macklin, and Dieter Fox. GPU-accelerated robotic simulation for distributed reinforcement learning. arXiv preprint arXiv:1810.05762, 2018.
    Findings
  • [25] Andrea J Liu and Sidney R Nagel. Granular and jammed materials. Soft Matter, 6(13):2869–2870, 2010.
    Google ScholarLocate open access versionFindings
  • [26] Miles Macklin, Kenny Erleben, Matthias Müller, Nuttapong Chentanez, Stefan Jeschke, and Viktor Makoviychuk. Non-smooth Newton methods for deformable multi-body dynamics. ACM Transactions on Graphics (TOG), 38(5):1–20, 2019.
    Google ScholarLocate open access versionFindings
  • [27] Miles Macklin and Matthias Müller. Position based fluids. ACM Transactions on Graphics (TOG), 32(4):104, 2013.
    Google ScholarLocate open access versionFindings
  • [28] Miles Macklin, Matthias Müller, Nuttapong Chentanez, and Tae-Yong Kim. Unified particle physics for real-time applications. ACM Transactions on Graphics (TOG), 33(4):153, 2014.
    Google ScholarLocate open access versionFindings
  • [29] Ryan D Maladen, Yang Ding, Paul B Umbanhowar, and Daniel I Goldman. Undulatory swimming in sand: experimental and simulation studies of a robotic sandfish. The International Journal of Robotics Research, 30(7):793–805, 2011.
    Google ScholarLocate open access versionFindings
  • [30] Hammad Mazhar, Jonas Bollmann, Endrina Forti, Andreas Praeger, Tim Osswald, and Dan Negrut. Studying the effect of powder geometry on the selective laser sintering process. Society of Plastics Engineers (SPE) ANTEC, 2014.
    Google ScholarLocate open access versionFindings
  • [31] Matthias Müller, Bruno Heidelberger, Marcus Hennix, and John Ratcliff. Position based dynamics. Journal of Visual Communication and Image Representation, 18(2):109–118, 2007.
    Google ScholarLocate open access versionFindings
  • [32] Dan Negrut, Daniel Melanz, Hammad Mazhar, David Lamb, Paramsothy Jayakumar, and Michael Letherwood. Investigating through simulation the mobility of light tracked vehicles operating on discrete granular terrain. SAE International Journal of Passenger CarsMechanical Systems, 6(2013-01-1191):369–381, 2013.
    Google ScholarLocate open access versionFindings
  • [33] Sia Nemat-Nasser and Juhua Zhang. Constitutive relations for cohesionless frictional granular materials. International Journal of Plasticity, 18(4):531–547, 2002.
    Google ScholarLocate open access versionFindings
  • [34] George Papamakarios and Iain Murray. Fast ε-free inference of simulation models with Bayesian conditional density estimation. In Advances in Neural Information Processing Systems, pages 1028–1036, 2016.
    Google ScholarLocate open access versionFindings
  • [35] Alexander Podlozhnyuk, Stefan Pirker, and Christoph Kloss. Efficient implementation of superquadric particles in discrete element method within an open-source framework. Computational Particle Mechanics, 4(1):101–118, 2017.
    Google ScholarLocate open access versionFindings
  • [36] Ali Rahimi and Benjamin Recht. Random features for large-scale kernel machines. In Advances in Neural Information Processing Systems, pages 1177–1184, 2008.
    Google ScholarLocate open access versionFindings
  • [37] Fabio Ramos, Rafael Carvalhaes Possas, and Dieter Fox. BayesSim: adaptive domain randomization via probabilistic inference for robotics simulators. arXiv preprint arXiv:1906.01728, 2019.
    Findings
  • [38] Patrick Richard, Mario Nicodemi, Renaud Delannay, Philippe Ribiere, and Daniel Bideau. Slow relaxation and compaction of granular systems. Nature materials, 4(2):121, 2005.
    Google ScholarLocate open access versionFindings
  • [39] Connor Schenck, Jonathan Tompson, Dieter Fox, and Sergey Levine. Learning robotic manipulation of granular media. arXiv preprint arXiv:1709.02833, 2017.
    Findings
  • [40] Jivko Sinapov, Connor Schenck, and Alexander Stoytchev. Learning relational object categories using behavioral exploration and multimodal perception. In 2014 IEEE International Conference on Robotics and Automation (ICRA), pages 5691–5698. IEEE, 2014.
    Google ScholarLocate open access versionFindings
  • [41] Elliot Thompson-Bean, Oliver Steiner, and Andrew McDaid. A soft robotic exoskeleton utilizing granular jamming. In 2015 IEEE International Conference On Advanced Intelligent Mechatronics (AIM), pages 165–170. IEEE, 2015.
    Google ScholarLocate open access versionFindings
  • [42] Qiong Zhang and Ken Kamrin. Microscopic description of the granular fluidity field in nonlocal flow modeling. Physical review letters, 118(5):058001, 2017.
    Google ScholarLocate open access versionFindings
  • [43] Tingnan Zhang, Feifei Qian, Chen Li, Pierangelo Masarati, Aaron M Hoover, Paul Birkmeyer, Andrew Pullin, Ronald S Fearing, and Daniel I Goldman. Ground fluidization promotes rapid running of a lightweight robot. The International Journal of Robotics Research, 32(7):859–869, 2013.
    Google ScholarLocate open access versionFindings
  • [44] Yifan Zhu, Laith Abdulmajeid, and Kris Hauser. A data-driven approach for fast simulation of robot locomotion on granular media. In 2019 International Conference on Robotics and Automation (ICRA), pages 7653–7659. IEEE, 2019.
    Google ScholarLocate open access versionFindings
Full Text
Your rating :
0

 

Tags
Comments