GPU Based Path Integral Control with Learned Dynamics

نویسندگان

  • Grady Williams
  • Eric Rombokas
  • Tom Daniel
چکیده

We present an algorithm which combines recent advances in model based path integral control with machine learning approaches to learning forward dynamics models. We take advantage of the parallel computing power of a GPU to quickly take a massive number of samples from a learned probabilistic dynamics model, which we use to approximate the path integral form of the optimal control. The resulting algorithm runs in a receding-horizon fashion in realtime, and is subject to no restrictive assumptions about costs, constraints, or dynamics. A simple change to the path integral control formulation allows the algorithm to take model uncertainty into account during planning, and we demonstrate its performance on a quadrotor navigation task. In addition to this novel adaptation of path integral control, this is the first time that a receding-horizon implementation of iterative path integral control has been run on a real system.

برای دانلود متن کامل این مقاله و بیش از 32 میلیون مقاله دیگر ابتدا ثبت نام کنید

ثبت نام

اگر عضو سایت هستید لطفا وارد حساب کاربری خود شوید

منابع مشابه

Sample Efficient Path Integral Control under Uncertainty

We present a data-driven stochastic optimal control framework that is derived using the path integral (PI) control approach. We find iterative control laws analytically without a priori policy parameterization based on probabilistic representation of the learned dynamics model. The proposed algorithm operates in a forward-backward sweep manner which differentiate it from other PI-related method...

متن کامل

Model Predictive Path Integral Control using Covariance Variable Importance Sampling

In this paper we present a Model Predictive Path Integral (MPPI) control algorithm that is derived from the path integral control framework and a generalized importance sampling scheme. In order to operate in real time we parallelize the sampling based component of the algorithm and achieve massive speed-up by using a Graphical Processor Unit (GPU). We compare MPPI against traditional model pre...

متن کامل

Dynamics modeling and stable gait planning of a quadruped robot in walking over uneven terrains

Quadruped robots have unique capabilities for motion over uneven natural environments. This article presents a stable gait for a quadruped robot in such motions and discusses the inverse-dynamics control scheme to follow the planned gait. First, an explicit dynamics model will be developed using a novel constraint elimination method for an 18-DOF quadruped robot. Thereafter, an inverse-dynamics...

متن کامل

Path Integral Networks: End-to-End Differentiable Optimal Control

In this paper, we introduce Path Integral Networks (PI-Net), a recurrent network representation of the Path Integral optimal control algorithm. The network includes both system dynamics and cost models, used for optimal control based planning. PI-Net is fully differentiable, learning both dynamics and cost models end-to-end by back-propagation and stochastic gradient descent. Because of this, P...

متن کامل

A New Control Strategy for Controlling Isolated Microgrid

Microgrid control in isolated mode is a highly important subject area. In the present paper, a new method is used for controlling the isolated microgrids. This method was used based on the classification of the microgrids into two groups, namely fast-dynamic (battery and flywheel) and slow-dynamic (diesel generator, electrolyzer, fuel cell). For the microgrid components with fast dynamics, a se...

متن کامل

ذخیره در منابع من


  با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید

برای دانلود متن کامل این مقاله و بیش از 32 میلیون مقاله دیگر ابتدا ثبت نام کنید

ثبت نام

اگر عضو سایت هستید لطفا وارد حساب کاربری خود شوید

عنوان ژورنال:
  • CoRR

دوره abs/1503.00330  شماره 

صفحات  -

تاریخ انتشار 2015