Log In Sign Up

ContactNets: Learning of Discontinuous Contact Dynamics with Smooth, Implicit Representations

by   Samuel Pfrommer, et al.

Common methods for learning robot dynamics assume motion is continuous, causing unrealistic model predictions for systems undergoing discontinuous impact and stiction behavior. In this work, we resolve this conflict with a smooth, implicit encoding of the structure inherent to contact-induced discontinuities. Our method, ContactNets, learns parameterizations of inter-body signed distance and contact-frame Jacobians, a representation that is compatible with many simulation, control, and planning environments for robotics. We furthermore circumvent the need to differentiate through stiff or non-smooth dynamics with a novel loss function inspired by the principles of complementarity and maximum dissipation. Our method can predict realistic impact, non-penetration, and stiction when trained on 60 seconds of real-world data.


An Adaptive Framework for Reliable Trajectory Following in Changing-Contact Robot Manipulation Tasks

We describe a framework for changing-contact robot manipulation tasks th...

Towards a Framework for Changing-Contact Robot Manipulation

Many robot manipulation tasks require the robot to make and break contac...

Robotic Contact Juggling

We define "robotic contact juggling" to be the purposeful control of the...

ADD: Analytically Differentiable Dynamics for Multi-Body Systems with Frictional Contact

We present a differentiable dynamics solver that is able to handle frict...

Fundamental Challenges in Deep Learning for Stiff Contact Dynamics

Frictional contact has been extensively studied as the core underlying b...

Bundled Gradients through Contact via Randomized Smoothing

The empirical success of derivative-free methods in reinforcement learni...

A parallel-GPU code for asteroid aggregation problems with angular particles

The paper presents a numerical implementation of the gravitational N-bod...