Identifying Mechanical Models through Differentiable Simulations
This addresses the challenge of robotic manipulation of heterogeneous objects in real-world settings, representing an incremental advance by extending differentiable physics to 3D forces.
The paper tackles the problem of manipulating unknown objects by identifying their mechanical properties through differentiable simulations, achieving on-the-fly identification of properties like inertia and friction using real robot data.
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.