Particle Filters in Robotics (Invited Talk)

TL;DR

This paper introduces the use of particle filters, a sequential Monte Carlo method, in robotics, highlighting recent advances in high-dimensional spaces and practical implementation challenges.

Contribution

It presents new insights into applying particle filters to complex, high-dimensional robotic problems and discusses practical tricks and open challenges for real-world applications.

Findings

Particle filters have been successfully applied to high-dimensional robotic problems.

Structural properties of robotic domains can be exploited to improve particle filter performance.

Practical tricks are necessary for real-world implementation of particle filters.

Abstract

This presentation will introduce the audience to a new, emerging body of research on sequential Monte Carlo techniques in robotics. In recent years, particle filters have solved several hard perceptual robotic problems. Early successes were limited to low-dimensional problems, such as the problem of robot localization in environments with known maps. More recently, researchers have begun exploiting structural properties of robotic domains that have led to successful particle filter applications in spaces with as many as 100,000 dimensions. The presentation will discuss specific tricks necessary to make these techniques work in real - world domains,and also discuss open challenges for researchers IN the UAI community.