Analysis of Theoretical and Numerical Properties of Sequential Convex Programming for Continuous-Time Optimal Control

09/10/2020
by   Riccardo Bonalli, et al.
0

Through the years, Sequential Convex Programming (SCP) has gained great interest as an efficient tool for non-convex optimal control. Despite the large number of existing algorithmic frameworks, only a few are accompanied by rigorous convergence analysis, which are often only tailored to discrete-time problem formulations. In this paper, we present a unifying theoretical analysis of a fairly general class of SCP procedures which is applied to the original continuous-time formulation. Besides the extension of classical convergence guarantees to continuous-time settings, our analysis reveals two new features inherited by SCP-type methods. First, we show how one can more easily account for manifold-type constraints, which play a key role in the optimal control of mechanical systems. Second, we demonstrate how the theoretical analysis may be leveraged to devise an accelerated implementation of SCP based on indirect methods. Detailed numerical experiments are provided to show the key benefits of a continuous-time analysis to improve performance.

READ FULL TEXT
research
03/01/2019

GuSTO: Guaranteed Sequential Trajectory Optimization via Sequential Convex Programming

Sequential Convex Programming (SCP) has recently seen a surge of interes...
research
10/11/2014

Q-learning for Optimal Control of Continuous-time Systems

In this paper, two Q-learning (QL) methods are proposed and their conver...
research
03/14/2016

A Variational Perspective on Accelerated Methods in Optimization

Accelerated gradient methods play a central role in optimization, achiev...
research
10/17/2022

Sufficient Exploration for Convex Q-learning

In recent years there has been a collective research effort to find new ...
research
06/15/2020

The Reflectron: Exploiting geometry for learning generalized linear models

Generalized linear models (GLMs) extend linear regression by generating ...
research
07/18/2023

Continuous-Time Reinforcement Learning: New Design Algorithms with Theoretical Insights and Performance Guarantees

Continuous-time nonlinear optimal control problems hold great promise in...
research
04/27/2022

Accelerated Continuous-Time Approximate Dynamic Programming via Data-Assisted Hybrid Control

We introduce a new closed-loop architecture for the online solution of a...

Please sign up or login with your details

Forgot password? Click here to reset