Identifying Mechanical Models through Differentiable Simulations

05/11/2020
by   Changkyu Song, et al.
0

This paper proposes a new method for manipulating unknown objects through a sequence of non-prehensile actions that displace an object from its initial configuration to a given goal configuration on a flat surface. The proposed method leverages recent progress in differentiable physics models to identify unknown mechanical properties of manipulated objects, such as inertia matrix, friction coefficients and external forces acting on the object. To this end, a recently proposed differentiable physics engine for two-dimensional objects is adopted in this work and extended to deal forces in the three-dimensional space. The proposed model identification technique analytically computes the gradient of the distance between forecasted poses of objects and their actual observed poses and utilizes that gradient to search for values of the mechanical properties that reduce the reality gap. Experiments with real objects using a real robot to gather data show that the proposed approach can identify the mechanical properties of heterogeneous objects on the fly.

READ FULL TEXT

page 2

page 8

research
05/11/2020

Learning to Slide Unknown Objects with Differentiable Physics Simulations

We propose a new technique for pushing an unknown object from an initial...
research
08/05/2020

A Probabilistic Model for Planar Sliding of Objects with Unknown Material Properties: Identification and Robust Planning

This paper introduces a new technique for learning probabilistic models ...
research
03/13/2019

Inferring 3D Shapes of Unknown Rigid Objects in Clutter through Inverse Physics Reasoning

We present a probabilistic approach for building, on the fly, 3-D models...
research
10/14/2022

Mechanical features based object recognition

Current robotic haptic object recognition relies on statistical measures...
research
04/12/2018

Efficient Model Identification for Tensegrity Locomotion

This paper aims to identify in a practical manner unknown physical param...
research
10/24/2017

Model Identification via Physics Engines for Improved Policy Search

This paper presents a practical approach for identifying unknown mechani...
research
11/03/2020

Predicting Terrain Mechanical Properties in Sight for Planetary Rovers with Semantic Clues

Non-geometric mobility hazards such as rover slippage and sinkage posing...

Please sign up or login with your details

Forgot password? Click here to reset