Learning Task Agnostic Sufficiently Accurate Models

02/19/2019
by   Clark Zhang, et al.
10

For complex real-world systems, designing controllers are a difficult task. With the advent of neural networks as a proxy for complex function approximators, it has become popular to learn the controller directly. However, these controllers are specific to a given task and need to be relearned for a new task. Alternatively, one can learn just the model of the dynamical system and compose it with external controllers. Such a model is task (and controller) agnostic and must generalize well across the state space. This paper proposes learning a "sufficiently accurate" model of the dynamics that explicitly enforces small residual error on pre-defined parts of the state-space. We formulate task agnostic controller design for this learned model as an optimization problem with state and control constraints that is solved in an online fashion. We validate this approach in simulation using a challenging contact-based Ball-Paddle system.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
11/07/2020

Leveraging Forward Model Prediction Error for Learning Control

Learning for model based control can be sample-efficient and generalize ...
research
07/10/2018

On Controller Design for Systems on Manifolds in Euclidean Space

A new method is developed to design controllers in Euclidean space for s...
research
09/26/2018

Adding Neural Network Controllers to Behavior Trees without Destroying Performance Guarantees

In this paper, we show how controllers created using data driven designs...
research
04/18/2019

Learning a Controller Fusion Network by Online Trajectory Filtering for Vision-based UAV Racing

Autonomous UAV racing has recently emerged as an interesting research pr...
research
01/04/2021

Control of Stochastic Quantum Dynamics with Differentiable Programming

Controlling stochastic dynamics of a quantum system is an indispensable ...
research
05/09/2022

FC^3: Feasibility-Based Control Chain Coordination

Hierarchical coordination of controllers often uses symbolic state repre...
research
02/17/2022

Morse Graphs: Topological Tools for Analyzing the Global Dynamics of Robot Controllers

Understanding the global dynamics of a robot controller, such as identif...

Please sign up or login with your details

Forgot password? Click here to reset