Author name cluster

Adam Milstein

Possible papers associated with this exact author name in Arrow. This page groups case-insensitive exact name matches and is not a full identity disambiguation profile.

3 papers

2 author rows

ICRA Conference 2011 Conference Paper

Occupancy voxel metric based iterative closest point for position tracking in 3D environments

Adam Milstein
Matthew McGill
Timothy Wiley
Rudino Salleh
Claude Sammut

Many applications for robotics require that the robot know its current position in the environment. While there exist several solutions for localizing a robot, even in a previously unknown environment, they often require an estimate of the robot's motion. However, in many situations, a robot may not have motion encoders, or its encoders may be highly inaccurate. We have developed an algorithm for tracking the position of a robot, based on a rangefinder device, that is robust to temporary errors in the range scan. By aligning each scan to an occupancy grid of prior scan data, we can find the robot's position more accurately than current techniques which only align to the previous scan. In addition, our solution can track the position of the robot based on three dimensional scan data, instead of requiring that the range sensor be fixed in a level plane.

Details

AAMAS Conference 2008 Conference Paper

Autonomous Geocaching: Navigation and Goal Finding in Outdoor Domains

James Neufeld
Michael Bowling
Jason Roberts
Stephen Walsh
Adam Milstein
Michael Sokolsky

This paper describes an autonomous robot system designed to solve the challenging task of geocaching. Geocaching involves locating a goal object in an outdoor environment given only its rough GPS position. No additional information about the environment such as road maps, waypoints, or obstacle descriptions is provided, nor is their often a simple straight line path to the object. This is in contrast to much of the research in robot navigation which often focuses on common structural features, e. g. , road following, curb avoidance, or indoor navigation. In addition, uncertainty in GPS positions requires a ﬁnal local search of the target area after completing the challenging navigation problem. We describe a relatively simple robotic system for completing this task. This system addresses three main issues: building a map from raw sensor readings, navigating to the target region, and searching for the target object. We demonstrate the eﬀectiveness of this system in a variety of complex outdoor environments and compare our system’s performance to that of a human expert teleoperating the robot.

PDF

AAAI Conference 2002 Conference Paper

Robust Global Localization Using Clustered Particle Filtering

Adam Milstein
and Evan Tang Williamson

Global mobile robot localization is the problem of determining a robot’s pose in an environment, using sensor data, when the starting position is unknown. A family of probabilistic algorithms known as Monte Carlo Localization (MCL) is currently among the most popular methods for solving this problem. MCL algorithms represent a robot’s belief by a set of weighted samples, which approximate the posterior probability of where the robot is located by using a Bayesian formulation of the localization problem. This article presents an extension to the MCL algorithm, which addresses its problems when localizing in highly symmetrical environments; a situation where MCL is often unable to correctly track equally probable poses for the robot. The problem arises from the fact that sample sets in MCL often become impoverished, when samples are generated according to their posterior likelihood. Our approach incorporates the idea of clusters of samples and modifies the proposal distribution considering the probability mass of those clusters. Experimental results are presented that show that this new extension to the MCL algorithm successfully localizes in symmetric environments where ordinary MCL often fails.

PDF Details