Estimating Mass Distribution of Articulated Objects through Non-prehensile Manipulation

We explore the problem of estimating the mass distribution of an articulated object by an interactive robotic agent. Our method predicts the mass distribution of an object by using limited sensing and actuating capabilities of a robotic agent during an interaction with the object. Inspired by the role of exploratory play in human infants, we take the combined approach of supervised and reinforcement learning to train an agent such that it learns to strategically interact with the object for estimating its mass distribution. Our method consists of two neural networks: (i) the policy network which decides how to interact with the object, and (ii) the predictor network that estimates the mass distribution given a history of observations and interactions. Using our method, we train a robotic arm to estimate the mass distribution of an object with moving parts (e.g. an articulated rigid body system) by pushing it on a surface with unknown friction properties. We show the robustness of our method across different physics simulators and robotic platforms. We further test our method on a real robot platform with 3D printed articulated chains with varying mass distributions. We present results that demonstrate that our method significantly outperforms the baseline agent that uses random pushes to interact with the object.

[1]  Oussama Khatib,et al.  A unified approach for motion and force control of robot manipulators: The operational space formulation , 1987, IEEE J. Robotics Autom..

[2]  Wolfram Burgard,et al.  Learning Kinematic Models for Articulated Objects , 2009, IJCAI.

[3]  James R. Kubricht,et al.  Intuitive Physics: Current Research and Controversies , 2017, Trends in Cognitive Sciences.

[4]  Jitendra Malik,et al.  Learning Visual Predictive Models of Physics for Playing Billiards , 2015, ICLR.

[5]  Daniel L. K. Yamins,et al.  Flexible Neural Representation for Physics Prediction , 2018, NeurIPS.

[6]  Jessica B. Hamrick,et al.  Inferring mass in complex scenes by mental simulation , 2016, Cognition.

[7]  Mario Fritz,et al.  Visual Stability Prediction and Its Application to Manipulation , 2016, AAAI Spring Symposia.

[8]  Oliver Brock,et al.  Interactive Perception of Articulated Objects , 2010, ISER.

[9]  Wenbin Li,et al.  Learning Manipulation under Physics Constraints with Visual Perception , 2019, ArXiv.

[10]  Dare A. Baldwin,et al.  Infants' ability to draw inferences about nonobvious object properties: evidence from exploratory play. , 1993, Child development.

[11]  Leslie Pack Kaelbling,et al.  Augmenting Physical Simulators with Stochastic Neural Networks: Case Study of Planar Pushing and Bouncing , 2018, 2018 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS).

[12]  Jiajun Wu,et al.  Learning to See Physics via Visual De-animation , 2017, NIPS.

[13]  Greg Turk,et al.  Preparing for the Unknown: Learning a Universal Policy with Online System Identification , 2017, Robotics: Science and Systems.

[14]  Abhinav Gupta,et al.  Interpretable Intuitive Physics Model , 2018, ECCV.

[15]  Jiajun Wu,et al.  DensePhysNet: Learning Dense Physical Object Representations via Multi-step Dynamic Interactions , 2019, Robotics: Science and Systems.

[16]  Jitendra Malik,et al.  Learning to Poke by Poking: Experiential Learning of Intuitive Physics , 2016, NIPS.

[17]  Abhinav Gupta,et al.  Bounce and Learn: Modeling Scene Dynamics with Real-World Bounces , 2019, ICLR.

[18]  Jessica B. Hamrick,et al.  Simulation as an engine of physical scene understanding , 2013, Proceedings of the National Academy of Sciences.

[19]  Niloy J. Mitra,et al.  Taking Visual Motion Prediction To New Heightfields , 2019, Comput. Vis. Image Underst..

[20]  Yong Yu,et al.  Estimation of object inertia parameters on robot pushing operation , 2004, 2004 International Conference on Intelligent Mechatronics and Automation, 2004. Proceedings..

[21]  Jürgen Schmidhuber,et al.  Solving Deep Memory POMDPs with Recurrent Policy Gradients , 2007, ICANN.

[22]  Abhinav Gupta,et al.  Environment Probing Interaction Policies , 2019, ICLR.

[23]  Laura Schulz,et al.  The Efficiency of Infants' Exploratory Play Is Related to Longer-Term Cognitive Development , 2018, Front. Psychol..

[24]  Jan Peters,et al.  Model learning for robot control: a survey , 2011, Cognitive Processing.

[25]  Sergey Levine,et al.  Deep visual foresight for planning robot motion , 2016, 2017 IEEE International Conference on Robotics and Automation (ICRA).

[26]  Oliver Brock,et al.  Learning to Manipulate Articulated Objects in Unstructured Environments Using a Grounded Relational Representation , 2008, Robotics: Science and Systems.

[27]  Jason J. Corso,et al.  Learning Kinematic Descriptions using SPARE: Simulated and Physical ARticulated Extendable dataset , 2018, ArXiv.

[28]  Razvan Pascanu,et al.  Interaction Networks for Learning about Objects, Relations and Physics , 2016, NIPS.

[29]  Jiajun Wu,et al.  Unsupervised Learning of Latent Physical Properties Using Perception-Prediction Networks , 2018, UAI.

[30]  Jiajun Wu,et al.  Galileo: Perceiving Physical Object Properties by Integrating a Physics Engine with Deep Learning , 2015, NIPS.

[31]  Joshua B. Tenenbaum,et al.  A Compositional Object-Based Approach to Learning Physical Dynamics , 2016, ICLR.

[32]  Siddhartha S. Srinivasa,et al.  DART: Dynamic Animation and Robotics Toolkit , 2018, J. Open Source Softw..

[33]  Karl J. Friston,et al.  Active Inference: A Process Theory , 2017, Neural Computation.

[34]  Oliver Brock,et al.  Interactive Perception: Leveraging Action in Perception and Perception in Action , 2016, IEEE Transactions on Robotics.

[35]  J. Andrew Bagnell,et al.  Interactive segmentation, tracking, and kinematic modeling of unknown 3D articulated objects , 2013, 2013 IEEE International Conference on Robotics and Automation.

[36]  Alec Radford,et al.  Proximal Policy Optimization Algorithms , 2017, ArXiv.

[37]  Hongyuan Zha,et al.  Single Episode Policy Transfer in Reinforcement Learning , 2019, ICLR.