Showing papers by "Sebastian Thrun published in 2003"

Fastslam: a factored solution to the simultaneous localization and mapping problem with unknown data association

Abstract: Simultaneous Localization and Mapping (SLAM) is an essential capability for mobile robots exploring unknown environments. The Extended Kalman Filter (EKF) has served as the de-facto approach to SLAM for the last fifteen years. However, EKF-based SLAM algorithms suffer from two well-known shortcomings that complicate their application to large, real-world environments: quadratic complexity and sensitivity to failures in data association. I will present an alternative approach to SLAM that specifically addresses these two areas. This approach, called FastSLAM, factors the full SLAM posterior exactly into a product of a robot path posterior, and N landmark posteriors conditioned on the robot path estimate. This factored posterior can be approximated efficiently using a particle filter. The time required to incorporate an observation into FastSLAM scales logarithmically with the number of landmarks in the map. In addition to sampling over robot paths, FastSLAM can sample over potential data associations. Sampling over data associations enables FastSLAM to be used in environments with highly ambiguous landmark identities. This dissertation will describe the FastSLAM algorithm given both known and unknown data association. The performance of FastSLAM will be compared against the EKF on simulated and real-world data sets. Results will show that FastSLAM can produce accurate maps in extremely large environments, and in environments with substantial data association ambiguity. Finally, a convergence proof for FastSLAM in linear-Gaussian worlds will be presented.

Robotic mapping: a survey

Abstract: This article provides a comprehensive introduction into the field of robotic mapping, with a focus on indoor mapping. It describes and compares various probabilistic techniques, as they are presently being applied to a vast array of mobile robot mapping problems. The history of robotic mapping is also detailed, along with an extensive list of open research problems.

Point-based value iteration: an anytime algorithm for POMDPs

Abstract: This paper introduces the Point-Based Value Iteration (PBVI) algorithm for POMDP planning. PBVI approximates an exact value iteration solution by selecting a small set of representative belief points and then tracking the value and its derivative for those points only. By using stochastic trajectories to choose belief points, and by maintaining only one value hyper-plane per point, PBVI successfully solves large problems: we present results on a robotic laser tag problem as well as three test domains from the literature.

FastSLAM 2.0: an improved particle filtering algorithm for simultaneous localization and mapping that provably converges

Abstract: Proceedings of IJCAI 2003 In [15], Montemerlo et al. proposed an algorithm called FastSLAM as an efficient and robust solution to the simultaneous localization and mapping problem. This paper describes a modified version of FastSLAM which overcomes important deficiencies of the original algorithm. We prove convergence of this new algorithm for linear SLAM problems and provide real-world experimental results that illustrate an order of magnitude improvement in accuracy over the original FastSLAM algorithm.

ARA*: Anytime A* with Provable Bounds on Sub-Optimality

Abstract: In real world planning problems, time for deliberation is often limited. Anytime planners are well suited for these problems: they find a feasible solution quickly and then continually work on improving it until time runs out. In this paper we propose an anytime heuristic search, ARA*, which tunes its performance bound based on available search time. It starts by finding a suboptimal solution quickly using a loose bound, then tightens the bound progressively as time allows. Given enough time it finds a provably optimal solution. While improving its bound, ARA* reuses previous search efforts and, as a result, is significantly more efficient than other anytime search methods. In addition to our theoretical analysis, we demonstrate the practical utility of ARA* with experiments on a simulated robot kinematic arm and a dynamic path planning problem for an outdoor rover.

An efficient fastSLAM algorithm for generating maps of large-scale cyclic environments from raw laser range measurements

Abstract: The ability to learn a consistent model of its environment is a prerequisite for autonomous mobile robots. A particularly challenging problem in acquiring environment maps is that of closing loops; loops in the environment create challenging data association problems [J.-S. Gutman et al., 1999]. This paper presents a novel algorithm that combines Rao-Blackwellized particle filtering and scan matching. In our approach scan matching is used for minimizing odometric errors during mapping. A probabilistic model of the residual errors of scan matching process is then used for the resampling steps. This way the number of samples required is seriously reduced. Simultaneously we reduce the particle depletion problem that typically prevents the robot from closing large loops. We present extensive experiments that illustrate the superior performance of our approach compared to previous approaches.

Learning Occupancy Grid Maps with Forward Sensor Models

Abstract: This article describes a new algorithm for acquiring occupancy grid maps with mobile robots. Existing occupancy grid mapping algorithms decompose the high-dimensional mapping problem into a collection of one-dimensional problems, where the occupancy of each grid cell is estimated independently. This induces conflicts that may lead to inconsistent maps, even for noise-free sensors. This article shows how to solve the mapping problem in the original, high-dimensional space, thereby maintaining all dependencies between neighboring cells. As a result, maps generated by our approach are often more accurate than those generated using traditional techniques. Our approach relies on a statistical formulation of the mapping problem using forward models. It employs the expectation maximization algorithm for searching maps that maximize the likelihood of the sensor measurements.

Simultaneous localization and mapping with unknown data association using FastSLAM

Abstract: The extended Kalman filter (EKF) has been the de facto approach to the Simultaneous Localization and Mapping (SLAM) problem for nearly fifteen years. However, the EKF has two serious deficiencies that prevent it from being applied to large, real-world environments: quadratic complexity and sensitivity to failures in data association. FastSLAM, an alternative approach based on the Rao-Blackwellized Particle Filter, has been shown to scale logarithmically with the number of landmarks in the map. This efficiency enables FastSLAM to be applied to environments far larger than could be handled by the EKF. In this paper, we show that FastSLAM also substantially outperforms the EKF in environments with ambiguous data association. The performance of the two algorithms is compared on a real-world data set with various levels of odometric noise. In addition, we show how negative information can be incorporated into FastSLAM in order to improve the accuracy of the estimated map.

Perspectives on standardization in mobile robot programming: the Carnegie Mellon Navigation (CARMEN) Toolkit

Abstract: In this paper we describe our open-source robot control software, the Carnegie Mellon Navigation (CARMEN) Toolkit. The ultimate goals of CARMEN are to lower the barrier to implementing new algorithms on real and simulated robots and to facilitate sharing of research and algorithms between different institutions. In order for CARMEN to be as inclusive of various research approaches as possible, we have chosen not to adopt strict software standards, but to instead focus on good design practices. This paper outlines the lessons we have learned in developing these practices.

Online simultaneous localization and mapping with detection and tracking of moving objects: theory and results from a ground vehicle in crowded urban areas

Abstract: The simultaneous localization and mapping (SLAM) with detection and tracking of moving objects (DATMO) problem is not only to solve the SLAM problem in dynamic environments but also to detect and track these dynamic objects. In this paper, we derive the Bayesian formula of the SLAM with DATMO problem, which provides a solid basis for understanding and solving this problem. In addition, we provide a practical algorithm for performing DATMO from a moving platform equipped with range sensors. The probabilistic approach to solve the whole problem has been implemented with the Navlab11 vehicle. More than 100 miles of experiments in crowded urban areas indicated that SLAM with DATMO is indeed feasible.

Map building with mobile robots in dynamic environments

Abstract: The problem of generating maps with mobile robots has received considerable attention over the past years. Most of the techniques developed so far have been designed for situations in which the environment is static during the mapping process. Dynamic objects, however, can lead to serious errors in the resulting maps such as spurious objects or misalignments due to localization errors. In this paper we consider the problem of creating maps with mobile robots in dynamic environments. We present a new approach that interleaves mapping and localization with a probabilistic technique to identify spurious measurements. In several experiments we demonstrate that our algorithm generates accurate 2D and 3D in different kinds of dynamic indoor and outdoor environments. We also use our algorithm to isolate the dynamic objects and generate 3D representation of them.

A system for volumetric robotic mapping of abandoned mines

Abstract: This paper describes two robotic systems developed for acquiring accurate volumetric maps of underground mines. One system is based on a cart instrumented by laser range finders, pushed through a mine by people. Another is a remotely controlled mobile robot equipped with laser range finders. To build consistent maps of large mines with many cycles, we describe an algorithm for estimating global correspondences and aligning robot paths. This algorithm enables us to recover consistent maps several hundreds of meters in diameter, without odometric information. We report results obtained in two mines, a research mine in Bruceton, PA, and an abandoned coal mine in Burgettstown, PA.

Finding approximate pomdp solutions through belief compression

Abstract: Recent research in the field of robotics has demonstrated the utility of probabilistic models for perception and state tracking on deployed robot systems. For example, Kalman filters and Markov localisation have been used successfully in many robot applications (Leonard & Durrant-Whyte, 1991; Thrun et al., 2000). There has also been considerable research into control and decision making algorithms that are robust in the face of specific kinds of uncertainty (Bagnell & Schneider, 2001). Few control algorithms, however, make use of full probabilistic representations throughout planning. As a consequence, robot control can become increasingly brittle as the system's perceptual uncertainty, and state uncertainty, increase. This thesis addresses the problem of decision making under uncertainty. In particular, we use a planning model called the partially observable Markov decision process, or POMDP (Sondik, 1971). The POMDP model computes a policy that maximises the expected future reward based on the complete probabilistic state estimate, or belief. Unfortunately, finding an optimal policy exactly is computationally demanding and thus infeasible for most problems that represent real world scenarios. This thesis describes a scalable approach to POMDP planning which uses low-dimensional representations of the belief space. We demonstrate how to make use of a variant of Principal Components Analysis (PCA) called Exponential family PCA (Collins et al., 2002) in order to compress certain kinds of large real-world POMDPs, and find policies for these problems. By finding low-dimensional representations of POMDPS, we are able to find good policies for problems that are orders of magnitude larger than those solvable by conventional approaches.

A robotic walker that provides guidance

Abstract: This paper describes a robotic walker designed as an assistive device for frail elderly people with cognitive impairment. Locomotion is most often the primary form of exercise for the elderly, and devices that provide mobility assistance are critical for the health and well being of such individuals. Previous work on walkers focused primarily on safety but offered little or no assistance with navigation and global orientation. Our system provides these features in addition to the stability and support provided by conventional walkers. A software suite of robot localization and navigation combined with a shared-control haptic interface achieves this capability. The system has been tested in a retirement facility near Pittsburgh, PA, USA.

An extension of the ICP algorithm for modeling nonrigid objects with mobile robots

Abstract: The iterative closest point (ICP) algorithm [2] is a popular method for modeling 3D objects from range data. The classical ICP algorithm rests on a rigid surface assumption. Building on recent work on nonrigid object models [5; 16; 9], this paper presents an ICP algorithm capable of modeling nonrigid objects, where individual scans may be subject to local deformations. We describe an integrated mathematical framework for simultaneously registering scans and recovering the surface configuration. To tackle the resulting high-dimensional optimization problems, we introduce a hierarchical method that first matches a coarse skeleton of scan points, then adapts local scan patches. The approach is implemented for a mobile robot capable of acquiring 3D models of objects.

Real time data association for FastSLAM

Abstract: The ability to simultaneously localise a robot and accurately map its surroundings is considered by many to be a key prerequisite of truly autonomous robots. This paper presents a real-world implementation of FastSLAM, an algorithm that recursively estimates the full posterior distribution of both robot pose and landmark locations. In particular, we present an extension to FastSLAM that addresses the data association problem using a nearest neighbor technique. Building on this, we also present a novel multiple hypotheses tracking implementation (MHT) to handle uncertainty in the data association. Finally an extension to the multi-robot case is introduced. Our algorithm has been run successfully using a number of data sets obtained in outdoor environments. Experimental results are presented that demonstrate the performance of the algorithms when compared with standard Kalman filter-based approaches.

Results for outdoor-SLAM using sparse extended information filters

Abstract: In [Thrun, S., et al., 2001], we proposed the sparse extended information filter for efficiently solving the simultaneous localization and mapping (SLAM) problem. In this paper, we extend this algorithm to handle data association problems and report real-world results, obtained with an outdoor vehicle. We find that our approach performs favorably when compared to the extended Kalman filter solution from which it is derived.

EM, MCMC, and chain flipping for structure from motion with unknown correspondence

Abstract: Learning spatial models from sensor data raises the challenging data association problem of relating model parameters to individual measurements This paper proposes an EM-based algorithm, which solves the model learning and the data association problem in parallel The algorithm is developed in the context of the the structure from motion problem, which is the problem of estimating a 3D scene model from a collection of image data To accommodate the spatial constraints in this domain, we compute virtual measurements as sufficient statistics to be used in the M-step We develop an efficient Markov chain Monte Carlo sampling method called chain flipping, to calculate these statistics in the E-step Experimental results show that we can solve hard data association problems when learning models of 3D scenes, and that we can do so efficiently We conjecture that this approach can be applied to a broad range of model learning problems from sensor data, such as the robot mapping problem

A Bayesian Algorithm for Simultaneous Localisation and Map Building

Abstract: This paper describes a full probabilistic solution to the Simultaneous Localisation and Mapping (SLAM) problem. Previously, the SLAM problem could only be solved in real time through the use of the Kalman Filter. This generally restricts the application of SLAM methods to domains with straight-forward (analytic) environment and sensor models. In this paper the Sum-of-Gaussian (SOG) method is used to approximate more general (arbitrary) probability distributions. This representation permits the generalizations made possible by particle filter or Monte-Carlo methods, while inheriting the real-time computational advantages of the Kalman filter. The method is demonstrated by its application to sub-sea field data consisting of both sonar and visual observation of near-field landmarks.

Scan Alignment and 3-D Surface Modeling with a Helicopter Platform

Abstract: This paper describes initial results for a laser-based aerial mapping system. Our approach applies a real-time laser scan matching algorithm to 2-D range data acquired by a remotely controlled helicopter. Results obtain for urban and natural terrain exhibit an unprecedented level of spatial detail in the resulting 3-D maps.

Decentralised SLAM with Low-Bandwidth Communication for Teams of Vehicles.

Abstract: This paper addresses the problem of simultaneous localization and mapping (SLAM) for teams of collaborating vehicles where the communication bandwidth is limited. We present a novel SLAM algorithm that enables multiple vehicles to acquire a joint map, but which can cope with arbitrary latency and bandwidth limitations such as typically found in airborne vehicle applications. The key idea is to represent maps in information form (negative log-likelihood), and to selectively communicate subsets of the information tailored to the available communication resources. We show that our communication scheme preserves the consistency, which has important ramifications for data association problems. We also provide experimental results that illustrate the effectiveness of our approach in comparison with previous

Auction Mechanism Design for Multi-Robot Coordination

Abstract: The design of cooperative multi-robot systems is a highly active research area in robotics. Two lines of research in particular have generated interest: the solution of large, weakly coupled MDPs, and the design and implementation of market architectures. We propose a new algorithm which joins together these two lines of research. For a class of coupled MDPs, our algorithm automatically designs a market architecture which causes a decentralized multi-robot system to converge to a consistent policy. We can show that this policy is the same as the one which would be produced by a particular centralized planning algorithm. We demonstrate the new algorithm on three simulation examples: multi-robot towing, multi-robot path planning with a limited fuel resource, and coordinating behaviors in a game of paint ball.

Variable resolution particle filter

Abstract: Particle filters are used extensively for tracking the state of non-linear dynamic systems. This paper presents a new particle filter that maintains samples in the state space at dynamically varying resolution for computational efficiency. Resolution within siatespace varies by region, depending on the belief that the true state lies within each region. Where belief is strong, resolution is fine. Where belief is low, resolution is coarse, abstracting multiple similar states together. The resolution of the statespace is dynamically updated as the belief changes. The proposed algorithm makes an explicit bias-variance tradeoff to select between maintaining samples in a biased generalization of a region of state space versus in a high variance specialization at fine resolution. Samples are maintained at a coarser resolution when the bias introduced by the generalization to a coarse resolution is outweighed by the gain in terms of reduction in variance, and at a finer resolution when it is not. Maintaining samples in abstraction prevents potential hypotheses from being eliminated prematurely for lack of a sufficient number of particles. Empirical results show that our variable resolution particle filter requires significantly lower computation for performance comparable to a classical particle filter.

Locating moving entities in indoor environments with teams of mobile robots

Abstract: This article presents an implemented multi-robot system for playing the popular game of laser tag. The object of the game is to search for and tag opponents that can move freely about the environment. The main contribution of this paper is a new particle filter algorithm for tracking the location of many opponents in the presence of pervasive occlusion. We achieve efficient tracking principally through a clever factorization of our posterior into roles that can be dynamically added and merged. When searching for opponents, the individual agents greedily maximize their information gain, using a negotiation technique for coordinating their search efforts. Experimental results are provided, obtained with a physical robot system in large-scale indoor environments and through simulation.

Planning under Uncertainty for Reliable Health Care Robotics

Abstract: We describe a mobile robot system, designed to assist residents of an retirement facility. This system is being developed to respond to an aging population and a predicted shortage of nursing professionals. In this paper, we discuss the task of finding and escorting people from place to place in the facility, a task containing uncertainty throughout the problem. Planning algorithms that model uncertainty well such as Partially Observable Markov Decision Processes (POMDPs) do not scale tractably to most real world problems. We demonstrate an algorithm for representing real world POMDP problems compactly, which allows us to find good policies in reasonable amounts of time. We show that our algorithm is able to find moving people in close to optimal time, where the optimal policy would start with knowledge of the person’s location.

An Autonomous Robotic System for Mapping Abandoned Mines

Abstract: We present the software architecture of a robotic system for mapping abandoned mines. The software is capable of acquiring consistent 2D maps of large mines with many cycles, represented as Markov random fields. 3D C-space maps are acquired from local 3D range scans, which are used to identify navigable paths using A* search. Our system has been deployed in three abandoned mines, two of which inaccessible to people, where it has acquired maps of unprecedented detail and accuracy.

Adapting navigation strategies using motions patterns of people

Abstract: As people move through their environments, they do not move randomly. Instead, they are often engaged in typical motion patterns, related to specific locations they might be interested in approaching. In this paper we propose a method for adapting the behavior of a mobile robot according to the activities of the people in its surrounding. Our approach uses learned models of people's motion behaviors. Whenever the robot detects a person it computes a probabilistic estimate about which motion pattern the person might be engaged in. During the path planning it then uses this belief to improve its navigation behavior. In different practical experiments carried out on a real robot we demonstrate that our approach allows a robot to quickly adapt its navigation plans according to the activities of the persons in its surrounding. We also present experiments illustrating that our approach provides a better behavior than a standard reactive collision avoidance system.

A learning algorithm for localizing people based on wireless signal strength that uses labeled and unlabeled data

Abstract: This paper summarizes a probabilistic approach for localizing people through the signal strengths of a wireless IEEE 802.1 lb network. Our approach uses data labeled by ground truth position to learn a probabilistic mapping from locations to wireless signals, represented by piecewise linear Gaussians. It then uses sequences of wireless signal data (without position labels) to acquire motion models of individual people, which further improves the localization accuracy. The approach has been implemented and evaluated in an office environment.