CoCo: Online Mixed-Integer Control via Supervised Learning

07/16/2021
by   A. Cauligi, et al.
0

Many robotics problems, from robot motion planning to object manipulation, can be modeled as mixed-integer convex programs (MICPs). However, state-of-the-art algorithms are still unable to solve MICPs for control problems quickly enough for online use and existing heuristics can typically only find suboptimal solutions that might degrade robot performance. In this work, we turn to data-driven methods and present the Combinatorial Offline, Convex Online (CoCo) algorithm for quickly finding high quality solutions for MICPs. CoCo consists of a two-stage approach. In the offline phase, we train a neural network classifier that maps the problem parameters to a (logical strategy), which we define as the discrete arguments and relaxed big-M constraints associated with the optimal solution for that problem. Online, the classifier is applied to select a candidate logical strategy given new problem parameters; applying this logical strategy allows us to solve the original MICP as a convex optimization problem. We show through numerical experiments how CoCo finds near optimal solutions to MICPs arising in robot planning and control with 1 to 2 orders of magnitude solution speedup compared to other data-driven approaches and solvers.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
04/07/2020

Learning Mixed-Integer Convex Optimization Strategies for Robot Planning and Control

Mixed-integer convex programming (MICP) has seen significant algorithmic...
research
07/26/2021

The Holy Grail of Multi-Robot Planning: Learning to Generate Online-Scalable Solutions from Offline-Optimal Experts

Many multi-robot planning problems are burdened by the curse of dimensio...
research
07/04/2019

Online Mixed-Integer Optimization in Milliseconds

We propose a method to solve online mixed-integer optimization (MIO) pro...
research
08/28/2022

Benchmark Results for Bookshelf Organization Problem as Mixed Integer Nonlinear Program with Mode Switch and Collision Avoidance

Mixed integer convex and nonlinear programs, MICP and MINLP, are express...
research
04/21/2023

Surgery Scheduling in Flexible Operating Rooms by using a Convex Surrogate Model of Second-Stage Costs

We study the elective surgery planning problem in a hospital with operat...
research
03/31/2021

Generalized Conflict-directed Search for Optimal Ordering Problems

Solving planning and scheduling problems for multiple tasks with highly ...
research
10/29/2018

Fast, High-Quality Dual-Arm Rearrangement in Synchronous, Monotone Tabletop Setups

Rearranging objects on a planar surface arises in a variety of robotic a...

Please sign up or login with your details

Forgot password? Click here to reset