scispace - formally typeset
Search or ask a question

Showing papers by "Sebastian Thrun published in 1999"


Proceedings ArticleDOI
10 May 1999
TL;DR: The Monte Carlo localization method is introduced, where the probability density is represented by maintaining a set of samples that are randomly drawn from it, and it is shown that the resulting method is able to efficiently localize a mobile robot without knowledge of its starting location.
Abstract: To navigate reliably in indoor environments, a mobile robot must know where it is. Thus, reliable position estimation is a key problem in mobile robotics. We believe that probabilistic approaches are among the most promising candidates to providing a comprehensive and real-time solution to the robot localization problem. However, current methods still face considerable hurdles. In particular the problems encountered are closely related to the type of representation used to represent probability densities over the robot's state space. Earlier work on Bayesian filtering with particle-based density representations opened up a new approach for mobile robot localization based on these principles. We introduce the Monte Carlo localization method, where we represent the probability density involved by maintaining a set of samples that are randomly drawn from it. By using a sampling-based representation we obtain a localization method that can represent arbitrary distributions. We show experimentally that the resulting method is able to efficiently localize a mobile robot without knowledge of its starting location. It is faster, more accurate and less memory-intensive than earlier grid-based methods,.

1,629 citations


Proceedings Article
18 Jul 1999
TL;DR: Monte Carlo Localization is a version of Markov localization, a family of probabilistic approaches that have recently been applied with great practical success and yields improved accuracy while requiring an order of magnitude less computation when compared to previous approaches.
Abstract: This paper presents a new algorithm for mobile robot localization, called Monte Carlo Localization (MCL). MCL is a version of Markov localization, a family of probabilistic approaches that have recently been applied with great practical success. However, previous approaches were either computationally cumbersome (such as grid-based approaches that represent the state space by high-resolution 3D grids), or had to resort to extremely coarse-grained resolutions. Our approach is computationally efficient while retaining the ability to represent (almost) arbitrary distributions. MCL applies sampling-based methods for approximating probability distributions, in a way that places computation "where needed." The number of samples is adapted on-line, thereby invoking large sample sets only when necessary. Empirical results illustrate that MCL yields improved accuracy while requiring an order of magnitude less computation when compared to previous approaches. It is also much easier to implement.

1,206 citations


Journal ArticleDOI
TL;DR: A version of Markov localization which provides accurate position estimates and which is tailored towards dynamic environments, and includes a filtering technique which allows a mobile robot to reliably estimate its position even in densely populated environments in which crowds of people block the robot's sensors for extended periods of time.
Abstract: Localization, that is the estimation of a robot's location from sensor data, is a fundamental problem in mobile robotics. This papers presents a version of Markov localization which provides accurate position estimates and which is tailored towards dynamic environments. The key idea of Markov localization is to maintain a probability density over the space of all locations of a robot in its environment. Our approach represents this space metrically, using a fine-grained grid to approximate densities. It is able to globally localize the robot from scratch and to recover from localization failures. It is robust to approximate models of the environment (such as occupancy grid maps) and noisy sensors (such as ultrasound sensors). Our approach also includes a filtering technique which allows a mobile robot to reliably estimate its position even in densely populated environments in which crowds of people block the robot's sensors for extended periods of time. The method described here has been implemented and tested in several real-world applications of mobile robots, including the deployments of two mobile robots as interactive museum tour-guides.

1,011 citations


Journal ArticleDOI
TL;DR: The software architecture of an autonomous, interactive tour-guide robot is presented, which integrates localization, mapping, collision avoidance, planning, and various modules concerned with user interaction and Web-based telepresence and enables robots to operate safely, reliably, and at high speeds in highly dynamic environments.

889 citations


Proceedings ArticleDOI
10 May 1999
TL;DR: An interactive tour-guide robot is described, which was successfully exhibited in a Smithsonian museum, and uses learning pervasively at all levels of the software architecture to address issues such as safe navigation in unmodified and dynamic environments, and short-term human-robot interaction.
Abstract: This paper describes an interactive tour-guide robot, which was successfully exhibited in a Smithsonian museum. During its two weeks of operation, the robot interacted with thousands of people, traversing more than 44 km at speeds of up to 163 cm/sec. Our approach specifically addresses issues such as safe navigation in unmodified and dynamic environments, and short-term human-robot interaction. It uses learning pervasively at all levels of the software architecture.

739 citations


01 Jan 1999
TL;DR: This paper gives a theoretical account of the phenomenon, deriving conditions under which one may expected it to cause learning to fail, and presents experimental results which support the theoretical findings.
Abstract: Reinforcement learning techniques address the problem of learning to select actions in unknown, dynamic environments. It is widely acknowledged that to be of use in complex domains, reinforcement learning techniques must be combined with generalizing function approximation methods such as artificial neural networks. Little, however, is understood about the theoretical properties of such combinations, and many researchers have encountered failures in practice. In this paper we identify a prime source of such failures—namely, a systematic overestimation of utility values. Using Watkins’ Q-Learning [18] as an example, we give a theoretical account of the phenomenon, deriving conditions under which one may expected it to cause learning to fail. Employing some of the most popular function approximators, we present experimental results which support the theoretical findings.

367 citations


Proceedings Article
29 Nov 1999
TL;DR: This work presents an efficient algorithm for learning Bayes networks from data by first identifying each node's Markov blankets, then connecting nodes in a maximally consistent way, and proves that under mild assumptions, the approach requires time polynomial in the size of the data and the number of nodes.
Abstract: In recent years, Bayesian networks have become highly successful tool for diagnosis, analysis, and decision making in real-world domains. We present an efficient algorithm for learning Bayes networks from data. Our approach constructs Bayesian networks by first identifying each node's Markov blankets, then connecting nodes in a maximally consistent way. In contrast to the majority of work, which typically uses hill-climbing approaches that may produce dense and causally incorrect nets, our approach yields much more compact causal networks by heeding independencies in the data. Compact causal networks facilitate fast inference and are also easier to understand. We prove that under mild assumptions, our approach requires time polynomial in the size of the data and the number of nodes. A randomized variant, also presented here, yields comparable results at much higher speeds.

347 citations


01 Jan 1999
TL;DR: The state-of-the art of a large-scale project, aimed towards the development of personal service robots for the elderly population, is described, which develops a first prototype robot that can provide information related to activities of daily living obtained from the Web.
Abstract: This paper describes the state-of-the art of a large-scale project, aimed towards the development of personal service robots for the elderly population. Taking care of elderly and chronically ill people is one of the major challenges currently faced by society. Needs range from increasing articulation to assisting those with dementia and cognitive impairment. To respond to this challenge, we have developed a first prototype robot. Using natural language, the robot can provide information related to activities of daily living obtained from the Web. It also enables remote care-givers to establish a “tele-presence” in people’s home, by relaying back video and audio stream through the Next Generation Internet. The paper describes this early prototype, and it lays out our research agenda towards building service robots for the elderly.

313 citations


Proceedings Article
29 Nov 1999
TL;DR: A Monte Carlo algorithm for learning to act in partially observable Markov decision processes (POMDPs) with real-valued state and action spaces using importance sampling for representing beliefs, and Monte Carlo approximation for belief propagation.
Abstract: We present a Monte Carlo algorithm for learning to act in partially observable Markov decision processes (POMDPs) with real-valued state and action spaces. Our approach uses importance sampling for representing beliefs, and Monte Carlo approximation for belief propagation. A reinforcement learning algorithm, value iteration, is employed to learn value functions over belief states. Finally, a sample-based version of nearest neighbor is used to generalize across states. Initial empirical results suggest that our approach works well in practical applications.

310 citations


Proceedings ArticleDOI
23 Jun 1999
TL;DR: This paper presents a novel, vision-based localization method based on the CONDENSATION algorithm, a Bayesian filtering method that uses a sampling-based density representation to track the position of the camera platform rather than tracking an object in the scene.
Abstract: To navigate reliably in indoor environments, a mobile robot must know where it is. This includes both the ability of globally localizing the robot from scratch, as well as tracking the robot's position once its location is known. Vision has long been advertised as providing a solution to these problems, but we still lack efficient solutions in unmodified environments. Many existing approaches require modification of the environment to function properly, and those that work within unmodified environments seldomly address the problem of global localization. In this paper we present a novel, vision-based localization method based on the CONDENSATION algorithm, a Bayesian filtering method that uses a sampling-based density representation. We show how the CONDENSATION algorithm can be rued in a novel way to track the position of the camera platform rather than tracking an object in the scene. In addition, it can also be used to globally localize the camera platform, given a visual map of the environment. Based on these two observations, we present a vision-based robot localization method that provides a solution to a difficult and open problem in the mobile robotics community. As evidence for the viability of our approach, we show both global localization and tracking results in the context of a state of the art robotics application.

282 citations


Proceedings ArticleDOI
10 May 1999
TL;DR: A technique for generating trajectories that take into account both the information content of the environment, and the density of the people in the environment to reduce the average positional certainty as the robot moves, reducing the likelihood the robot will become lost at any point.
Abstract: Ships often use the coasts of continents for navigation in the absence of better tools such as GPS, since being close to land allows sailors to determine with high accuracy where they are. Similarly for mobile robots, in many environments global and accurate localization is not always feasible. Environments can lack features, and dynamic obstacles such as people can confuse and block sensors. We demonstrate a technique for generating trajectories that take into account both the information content of the environment, and the density of the people in the environment. These trajectories reduce the average positional certainty as the robot moves, reducing the likelihood the robot will become lost at any point. Our method was successfully implemented and used by the mobile robot Minerva, a museum tourguide robot, for a 2 week period in the Smithsonian National Museum of American History.

Proceedings Article
29 Nov 1999
TL;DR: This paper explicitly models the uncertainty of the robot's position as a state variable, and generates trajectories through the augmented pose-uncertainty space, and demonstrates experimentally that coastal navigation reduces the uncertainty at the goal, especially with degraded localization.
Abstract: The problem that we address in this paper is how a mobile robot can plan in order to arrive at its goal with minimum uncertainty. Traditional motion planning algorithms often assume that a mobile robot can track its position reliably, however, in real world situations, reliable localization may not always be feasible. Partially Observable Markov Decision Processes (POMDPs) provide one way to maximize the certainty of reaching the goal state, but at the cost of computational intractability for large state spaces. The method we propose explicitly models the uncertainty of the robot's position as a state variable, and generates trajectories through the augmented pose-uncertainty space. By minimizing the positional uncertainty at the goal, the robot reduces the likelihood it becomes lost. We demonstrate experimentally that coastal navigation reduces the uncertainty at the goal, especially with degraded localization.

Proceedings ArticleDOI
10 May 1999
TL;DR: The algorithm proposed here uses the robot's sensors to automatically calibrate the robot as it operates, and an efficient, incremental maximum likelihood algorithm enables the robot to adapt to changes in its kinematics online, as they occur.
Abstract: This paper proposes a statistical method for calibrating the odometry of mobile robots. In contrast to previous approaches, which require explicit measurements of actual motion when calibrating a robot's odometry, the algorithm proposed here uses the robot's sensors to automatically calibrate the robot as it operates. An efficient, incremental maximum likelihood algorithm enables the robot to adapt to changes in its kinematics online, as they occur. The appropriateness of the approach is demonstrated in two large-scale environments, where the amount of odometric error is reduced by an order of magnitude.

Proceedings ArticleDOI
10 May 1999
TL;DR: The approach to spontaneous short-term interaction is described: a robot designed to be a believable social agent, implemented using a mobile robot with a motorized face as focal point for interaction, an architecture that suggests the robot has moods, and a method for learning how to interact with people.
Abstract: This paper considers a specific type of interaction: short-term and spontaneous interaction with crowds of people. Such patterns of interactions are found when service robots operate in public places, for example information kiosks, receptionists, and tour-guide robots applications. We describe our approach to spontaneous short-term interaction: a robot designed to be a believable social agent. The approach has been implemented using a mobile robot with a motorized face as focal point for interaction, an architecture that suggests the robot has moods, and a method for learning how to interact with people. Our system was recently deployed at a Smithsonian museum in Washington, DC. During a two week period it interacted with thousands of people. The robot's interactive capabilities were essential for its high on-task performance, and thus its practical success.


Book ChapterDOI
TL;DR: This paper uses a sample-based version of Markov localization, capable of localizing mobile robots in an any-time fashion, and illustrates drastic improvements in localization speed and accuracy when compared to conventional single-robot localization.
Abstract: This paper presents a probabilistic algorithm for collaborative mobile robot localization. Our approach uses a sample-based version of Markov localization, capable of localizing mobile robots in an any-time fashion. When teams of robots localize themselves in the same environment, probabilistic methods are employed to synchronize each robot's belief whenever one robot detects another. As a result, the robots localize themselves faster, maintain higher accuracy, and high-cost sensors are amortized across multiple robot platforms. The paper also describes experimental results obtained using two mobile robots. The robots detect each other and estimate their relative locations based on computer vision and laser range-finding. The results, obtained in an indoor office environment, illustrate drastic improvements in localization speed and accuracy when compared to conventional single-robot localization.

15 Sep 1999
TL;DR: This approach uses a sample-based version of Markov localization, capable of localizing mobile robots in an any-time fashion, to achieve drastic improvements in localization speed and accuracy when compared to conventional single-robot localization.
Abstract: This paper presents a probabilistic algorithm for collaborative mobile robot localization. Our approach uses a sample-based version of Markov localization, capable of localizing mobile robots in an any-time fashion. When teams of robots localize themselves in the same environment, probabilistic methods are employed to synchronize each robot's belief whenever one robot detects another. As a result, the robots localize themselves faster, maintain higher accuracy, and high-cost sensors are amortized across multiple robot platforms. The paper also describes experimental results obtained using two mobile robots. The robots detect each other and estimate their relative locations based on computer vision and laser range-finding. The results, obtained in an indoor office environment, illustrate drastic improvements in localization speed and accuracy when compared to conventional single-robot localization.

Book ChapterDOI
TL;DR: An interactive tour-guide robot which was successfully exhibited in a Smithsonian museum and employed a collection of learning techniques, some of which were necessary to cope with the challenges arising from its extremely large and crowded environment, whereas others were used to aid the robot's interactive capabilities.
Abstract: This paper describes an interactive tour-guide robot which was successfully exhibited in a Smithsonian museum. Minerva employed a collection of learning techniques, some of which were necessary to cope with the challenges arising from its extremely large and crowded environment, whereas others were used to aid the robot's interactive capabilities. During two weeks of highly successful operation, the robot interacted with thousands of people, traversing more than 44km at speeds of up to 163 cm/sec in the un-modified museum.

Proceedings Article
27 Jun 1999
TL;DR: It is proved that under mild assumptions, Monte Carlo Hidden Markov Models converge to a local maximum in likelihood space, just like conventional HMMs.
Abstract: We present a learning algorithm for non-parametric hidden Markov models with continuous state and observation spaces. All necessary probability densities are approximated using samples, along with density trees generated from such samples. A Monte Carlo version of Baum-Welch (EM) is employed to learn models from data. Regularization during learning is achieved using an exponential shrinking technique. The shrinkage factor, which determines the effective capacity of the learning algorithm, is annealed down over multiple iterations of Baum-Welch, and early stopping is applied to select the right model. Once trained, Monte Carlo HMMs can be run in an any-time fashion. We prove that under mild assumptions, Monte Carlo Hidden Markov Models converge to a local maximum in likelihood space, just like conventional HMMs. In addition, we provide empirical results obtained in a gesture recognition domain.

01 Jan 1999
TL;DR: This paper describes and compares two pioneering mobile robot systems, which were recently deployed as interactive tour-guides in two museums, and demonstrates safe and reliable navigation in proximity of people.
Abstract: This paper describes and compares two pioneering mobile robot systems, which were recently deployed as interactive tour-guides in two museums. Both robots demonstrated safe and reliable navigation in proximity of people. They also interacted with museum visitor through various means, including the Web. Probabilistic algorithms and learning are pervasive in their software architectures. This article sketches the basic software, summarizes results, compares the robots, and discusses open problems.

Journal ArticleDOI
TL;DR: This report summarizes the CONALD meeting, which took place June 11-13, 1998, at Carnegie Mellon University, and summarizes the results obtained in the individual workshops, discussing in depth promising research topics.
Abstract: This report summarizes the CONALD meeting, which took place June 11-13, 1998, at Carnegie Mellon University. CONALD brought together an interdisciplinary group of scientists, concerned with decision making based on data. This report is organized in two parts. The first part (pages 1-6) summarizes the CONALD meeting and highlights its main outcomes, beyond the individual workshop level. The second part (pages 7-30) summarize the results obtained in the individual workshops, discussing in depth promising research topics. This report is available through the Web at http://www.cs.cmu.edu/ conald.

Proceedings Article
01 Jan 1999

Journal Article
TL;DR: In this paper, the authors present Markov localization as a technique for estimating the position of a mobile robot, which is based on a fine-grained, metric discretization of the state space.
Abstract: Localization is one of the fundamental problems in mobile robotics. Without knowledge about their position mobile robots cannot efficiently carry out their tasks. In this paper we present Markov localization as a technique for estimating the position of a mobile robot. The key idea of this technique is to maintain a probability density over the whole state space of the robot within its environment. This way our technique is able to globally localize the robot from scratch and even to recover from localization failures, a property which is essential for truly autonomous robots. The probabilistic framework makes this approach robust against approximate models of the environment as well as noisy sensors. Based on a fine-grained, metric discretization of the state space, Markov localization is able to incorporate raw sensor readings and does not require predefined landmarks. It also includes a filtering technique which allows to reliably estimate the position of a mobile robot even in densely populated environments. We furthermore describe, how the explicit representation of the density can be exploited in a reactive collision avoidance system to increase the robustness and reliability of the robot even in situations in which it is uncertain about its position. The method described here has been implemented and tested in several real-world applications of mobile robots including the deployments of two mobile robots as interactive museum tour-guides.

ReportDOI
01 Mar 1999
TL;DR: This approach uses a sample-based version of Markov localization, capable of localizing mobile robots in an any-time fashion, to achieve drastic improvements in localization speed and accuracy when compared to conventional single-robot localization.
Abstract: : This paper presents a statistical algorithm for collaborative mobile robot localization. Our approach uses a sample-based version of Markov localization, capable of localizing mobile robots in an any-time fashion. When teams of robots localize themselves in the same environment, probabilistic methods are employed to synchronize each robot's belief whenever one robot detects another. As a result, the robots localize themselves faster, maintain higher accuracy, and high-cost sensors are amortized across multiple robot platforms. The paper also describes experimental results obtained using two mobile robots, using computer vision and laser range finding for detecting each other and estimating each other's relative location. The results, obtained in an indoor office environment, illustrate drastic improvements in localization speed and accuracy when compared to conventional single-robot localization.

01 Jan 1999
TL;DR: In this paper, the authors installed a mobile tourguide robot in a branch of the Deutsches Museum to guide visitors through the museum, explaining to them a subset of the museum's exhibits.
Abstract: Recent research in the field of mobile robotics has led to significant progress along various dimensions. Applications such as robots that guide blind or mentally handicapped people, robots that clean large office buildings and department stores, robots that assist people in recreational activities, etc., are clearly in reach, and for many of those target domains prototypes are readily available. This recent, ongoing revolution has been triggered by advances along various dimensions. Robotic hardware has steadily become cheaper and more reliable. Robotic software has matured, reaching critical levels of reliability, robustness, and flexibility. Mobile robots have an enormous potential to change our everyday lives. It is worth noting that an increasing fraction of these robots rely on methods developed in artificial intelligence. Together with researchers at the University of Bonn (W. Burgard, A.B. Cremers, D. Fox, D. Hahnel, G. Lakemeyer, D. Schultz and W. Steiner), and motivated in part by the work of Horswill [3], the author recently installed a mobile tourguide robot in a branch of the Deutsches Museum [1, 4]. The robot’s task was to guide visitors through the museum, explaining to them a subset of the museum’s exhibits. The major challenges that arose in this project can be grouped into two categories: navigation and human robot interaction.

01 Jan 1999
TL;DR: This chapter discusses probabilistic methods, which emphasis on frameworks that enable systems to represent and handle uncertainty and have probably been analyzed most thoroughly and applied most successfully in a variety of problem domains.
Abstract: The eld of Arti cial Intelligence (AI) is currently undergoing a transition. While in the eighties, rule-based and logical representations were the representation of choice in the majority of AI systems, in recent years various researchers have explored alternative representational frameworks, which emphasis on frameworks that enable systems to represent and handle uncertainty. Out of those, probabilistic methods (and speci cally Bayesian methods) have probably been analyzed most thoroughly and applied most successfully in a variety of problem domains.

01 Jan 1999
TL;DR: In this paper, the authors consider the question of what constitutes an appropriate general-purpose learning mechanism for a cognitive architecture such as Soar, and propose a set of mechanisms that might explain and reproduce the rich variety of learning capabilities of humans, ranging from learning perceptual-motor skills such as how to ride a bicycle, to learning highly cognitive tasks such as playing chess.
Abstract: Learning is a fundamental component of intelligence, and a key consideration in designing cognitive architectures such as Soar [Laird et al., 1986]. This chapter considers the question of what constitutes an appropriate general-purpose learning mechanism. We are interested in mechanisms that might explain and reproduce the rich variety of learning capabilities of humans, ranging from learning perceptual-motor skills such as how to ride a bicycle, to learning highly cognitive tasks such as how to play chess.