A convex polynomial force-motion model for planar sliding: Identification and application

By Jiaji Zhou, Robert Paolini, J. Bagnell, Matthew Thomas Mason. 2016

102 citations recorded by the source corpus.

We propose a polynomial force-motion model for planar sliding. The set of generalized friction loads is the 1-sublevel set of a polynomial whose gradient directions correspond to generalized velocities. Additionally, the polynomial is confined to be convex even-degree homogeneous in order to obey the maximum work inequality, symmetry, shape invariance in scale, and fast invertibility. We present a simple and statistically-efficient model identification procedure using a sum-of-squares convex relaxation. Simulation and robotic experiments validate the accuracy and efficiency of our approach. We also show practical applications of our model including stable pushing of objects and free sliding dynamic simulations.

Subfields: Atomic and Molecular Physics, and Optics, Control and Systems Engineering

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Atomic and Molecular Physics, and Optics

In Control and Systems Engineering

Citations in the corpus

Learning Synergies Between Pushing and Grasping with Self-Supervised Deep Reinforcement Learning (2018, background): “While recent methods have explored data-driven algorithms for learning the dynamics of pushing [17], [18], [19], many of these works have largely focused on the execution of stable pushes for one object at a time.”
The Curious Robot: Learning Visual Representations via Physical Interactions (2016, background): “The origins of pushing as a manipulation task can be traced to the task of aligning objects to reduce pose uncertainty [25,26,27] and as a preceding realignment step before object manipulation [28,29,30].”
SE3-nets: Learning rigid body motion using deep neural networks (2016, background): “A shortcoming of such models is, however, that they rely on very accurate estimates of the state of the system [3].”
Learning to push by grasping: Using multiple tasks for effective learning (2016, background): “The origins of pushing as a manipulation task can be traced to the task of aligning objects to reduce pose uncertainty [14], [15], [16] and as a preceding realignment step before object manipulation [17], [18], [19].”
Model Identification via Physics Engines for Improved Policy Search (2017, background): “There is also work on identifying sliding models of objects using white-box optimization [17], [20], [26].”
Learning to Singulate Objects using a Push Proposal Network (2017, background): “However, estimating the location of objects and other properties of the physical environment in order to plan push actions can be subject to errors, especially for unknown objects and cluttered scenes [21, 30, 31].”
ContactNets: Learning of Discontinuous Contact Dynamics with Smooth, Implicit Representations (2020, methodology): “[25] learn a set-valued representation of frictional forces via convex optimization and Bauza and Rodriguez [6] learn a pusher-slider system’s dynamics via Gaussian processes regression.”
A probabilistic data-driven model for planar pushing (2017, background): “Over the years, several works have applied data-driven techniques to the problem of planar pushing [12, 13, 14, 15, 16].”
Policy transfer via modularity (2017, background): “Some previous efforts have been made to deal with the uncertainties in friction by learning how to push objects [19], [20], [21], [22], [23], [18].”
Learning Visual Affordances for Robotic Manipulation (2019, background): “While recent methods have explored data-driven algorithms for learning the dynamics of pushing [100, 73, 128], many of these works have largely focused on the execution of stable”
Policy transfer via modularity and reward guiding (2017, background): “Some previous efforts have been made to deal with the uncertainties in friction by learning how to push objects [24], [25], [26], [27], [28], [20], [29].”
Fast Model Identification via Physics Engines for Data-Efficient Policy Search (2017, methodology): “Variants have been applied in robotics [Dogar et al. , 2012; Lynch and Mason, 1996; Scholz et al. , 2014; Zhou et al. , 2016], where using inaccurate models can still allow a policy to steer an RC car [ Abbeel et al. , 2006].”