Trajectory Optimization Using Neural Network Gradients of Learned Dynamics

by   Nathanael Köhler, et al.

Trajectory optimization methods have achieved an exceptional level of performance on real-world robots in recent years. These methods heavily rely on accurate physics simulators, yet some aspects of the physical world, such as friction, can only be captured to a limited extent by most simulators. The goal of this paper is to leverage trajectory optimization for performing highly dynamic and complex tasks with robotic systems in absence of an accurate physics simulator. This is achieved by applying machine learning techniques to learn a differentiable dynamics model of the system from data. On the example of a RC car, we show that from data collected in only 15 minutes of human-operated interactions with the car, a neural network is able to model highly nonlinear behaviors such as loss of traction and drifting. Furthermore, we use the analytical gradients of the neural network to perform gradient-based trajectory optimization, both in an offline and online setting. We find that our learned model is able to represent complex physical behavior, like drifting and gives unprecedented performance in combination with trajectory optimization methods.


page 1

page 2

page 3

page 4

page 5

page 6

page 7

page 8


Leveraging Neural Network Gradients within Trajectory Optimization for Proactive Human-Robot Interactions

To achieve seamless human-robot interactions, robots need to intimately ...

Half-Inverse Gradients for Physical Deep Learning

Recent works in deep learning have shown that integrating differentiable...

Differentiable Physics Simulations with Contacts: Do They Have Correct Gradients w.r.t. Position, Velocity and Control?

In recent years, an increasing amount of work has focused on differentia...

Automatic Differentiation and Continuous Sensitivity Analysis of Rigid Body Dynamics

A key ingredient to achieving intelligent behavior is physical understan...

Contact-Implicit Trajectory Optimization using Orthogonal Collocation

In this paper we propose a method to improve the accuracy of trajectory ...

Graph networks as learnable physics engines for inference and control

Understanding and interacting with everyday physical scenes requires ric...

DiffCo: Auto-Differentiable Proxy Collision Detection with Multi-class Labels for Safety-Aware Trajectory Optimization

The objective of trajectory optimization algorithms is to achieve an opt...

Please sign up or login with your details

Forgot password? Click here to reset