Robots must complete their tasks in spite of unreliable actuators and limited, noisy sensing. In this paper, we consider the information requirements of such tasks. What sensing and actuation abilities are needed to complete a given task? Are some robot systems provably “more powerful, ” in terms of the tasks they can complete, than others? Can we find meaningful equivalence classes of robot systems? This line of research is inspired by the theory of computation, which has produced similar results for abstract computing machines. The basic idea is a dominance relation over robot systems that formalizes the idea that some robots are stronger than others. This comparison, which is based on the how the robots progress through their information spaces, induces a partial order over the set of robot systems. We prove some basic properties of this partial order and show that it is directly related to the robots’ ability to complete tasks. We give examples to demonstrate the theory, including a detailed analysis of a limited-sensing global localization problem. 1

Navigating autonomously is one of the most important problems facing outdoor mobile robots. This task is extremely difficult if no prior information is available and is trivial if perfect prior information is available and the position of the robot is precisely known. Perfect prior maps are rare, but good-quality, high-resolution prior maps are increasingly available. Although the position of the robot is usually known through the use of the Global Position System (GPS), there are many scenarios in which GPS is not available, or its reliability is compromised by different types of interference such as mountains, buildings, foliage or jamming. If GPS is not available, the position estimate of the robot depends on dead-reckoning alone, which drifts with time and can accrue very large errors. Most existing approaches to path planning and navigation for outdoor environments are unable to use prior maps if the position of the robot is not precisely known. Often these approaches end up performing the much harder task of navigating without prior information. This thesis addresses the problem of planning paths with uncertainty in position for large outdoor environments. The objective is to be able to reliably navigate autonomously

Abstract — Localization is a fundamental problem for many kinds of mobile robots. Sensor systems of varying ability have been proposed and successfully used to solve the problem. This paper probes the lower limits of this range by describing three extremely simple robot models and addressing the active localization problem for each. The robot, whose configuration is composed of its position and orientation, moves in a fully known simply connected polygonal environment. We pose the localization task as a planning problem in the robot’s information space, which encapsulates the uncertainty in the robot’s configuration. We consider robots equipped with (1) angular and linear odometers, (2) a compass and contact sensor, and (3) an angular odometer and contact sensor. We present localization algorithms for models 1 and 2 and show that no algorithm exists for model 3. An implementation with simulation examples is presented. Index Terms — information spaces, mobile robot localization, robots, robot sensing systems I.

Introduction and Preliminaries For mobile robots, uncertainty is everywhere. Wheels slip. Sensors are a#ected by noise. Obstacles move unpredictably. Truly autonomous robots (and decision-makers or agents in general) must act in ways that are robust to these sorts of failures and unexpected events which we may think of in general as uncertainty. In this chapter, we attempt to meet uncertainty head-on by explicitly modeling it and reasoning about it. We use the term decision theoretic planning to refer to this broad class of planning methods characterized by explicit accounting for uncertainty. We will consider a number of formulations for the problem of planning under uncertainty and present algorithms for planning under these formulations. Uncertainty can take many forms, but for brevity and clarity we will restrict our attention to only two important types: . Prediction uncertainty occurs when the e#ects of actions are not fully predictable. This can be thought of as an uncertain