The Infona portal uses cookies, i.e. strings of text saved by a browser on the user's device. The portal can access those files and use them to remember the user's data, such as their chosen settings (screen view, interface language, etc.), or their login data. By using the Infona portal the user accepts automatic saving and using this information for portal operation purposes. More information on the subject can be found in the Privacy Policy and Terms of Service. By closing this window the user confirms that they have read the information on cookie usage, and they accept the privacy policy and the way cookies are used by the portal. You can change the cookie settings in your browser.
This paper concerns the application of techniques from estimation theory to the problem of navigation and perception for a mobile robot. After a brief introduction, a hierarchical architecture is presented for the design of a mobile robot navigation system. The control system for a mobile robot is found to decompose naturally into a set of layered control loops, where the layers are defined by the...
This paper provides an introduction to the field of reasoning with uncertainty in Artificial Intelligence (AI), with an emphasis on reasoning with numeric uncertainty. The considered formalisms are Probability Theory and some of its generalizations, the Certainty Factor Model, Dempster-Shafer Theory, and Probabilistic Networks.
This paper proposes an integrated approach to robot navigation that incorporates task-related information needs, perceptual capabilities, robot knowledge metrics and spatial characteristics of the environment into the motion planning process. Autonomous robots are modelled as discrete-time dynamic systems that implement optimal or suboptimal control policies in their choice of appropriate control...
Object recognition in digital images is a primary issue in robotics. We consider the model-based vision problem, where objects to be recognized come from a database of geometrically precise models. However, the modeling process involves uncertainties, and thus predicted collections of features will be subject to possible variations. Likewise, the image analysis problem using digital images must deal...
In this paper, we bring techniques from operations research to bear on the problem of choosing optimal actions in partially observable stochastic domains. In many cases, we have developed new ways of viewing the problem that are, perhaps, more consistent with the AI perspective. We begin by introducing the theory of Markov decision processes (MDPs) and partially observable Markov decision processes...
In this work we examine the problem of constructing and maintaining a map of an autonomous vehicle's environment for the purpose of navigation, using evidential reasoning. The inherent uncertainty in the origin of measurements of sensors demands a probabilistic approach to processing, or fusing, the new sensory information to build an accurate map. In this paper, the map is based on a two-dimensional...
The notion of uncertainty in robotics has to date largely involved the uncertainty, or variability, in the information the robot was receiving from its sensors, information about an outside world which itself is known, certain, unambiguous. For example, the uncertainty the robot may experience in answering the question “Is that object a cube?”. With the emergence of autonomous, ‘really useful robots’,...
Concepts of causal relevance and irrelevance are readily formulated in the context of Bayes nets, but these formulations have significant shortcomings. Most importantly, they do not allow for the great variety that can be observed in the temporal configuration of causally related entities. For example, they deal awkwardly with progressive causation, where continued action of a cause continues to enhance...
The effectiveness of robot-manipulators is determined to a great extent by the speed of making this or that movement needed for carrying out the task. According to this the problem of optimal robot control is often divided into two subproblems solved separately. In the autonomous regime the trajectory planning is fulfilled for providing the robot movement time close to the minimal. The problem...
In the robot navigation problem, noisy sensor data must be filtered to obtain the best estimate of the robot position. The discrete Kalman filter, commonly used for prediction and detection of signals in communication and control problems, has become a popular method to reduce the effect of uncertainty from the sensor data. However, in the domain of robot navigation, sensor readings are not only uncertain,...
This paper presents a method for planning the motions of a mobile robot navigating in a known environment with uncertainty in control and sensing. The robot is equipped with sensors which, if properly used, may provide information to overcome the uncertainty accumulated during the motions. The planner produces robust motion strategies composed of sensor-based motion commands which guarantee that the...
We develop a formal tool for representing and analyzing informational aspects of robotic tasks, based on the formal concept of ‘knowledge.’ Specifically, we adopt the notion of knowledge-based protocols from distributed systems, and define the notions of knowledge complexity of a robotic task and knowledge capability of a robot. The resulting formalism naturally captures previous work in the areas...
In this article, we propose a generic architecture for sensor data fusion and argue that the central issue in such an approach is the choice of a suitable representation of the robot's environment. We argue that for the navigation task a robot-centered discrete probabilistic representation (an occupancy grid) is a suitable choice. If such a representation is used, the two key problems are how to transform...
This paper presents structural extensions of Bayesian networks which improve their applicability for complex systems that are modeled by a large set of random variables with a lot of dependencies between them. A Hierarchical Bayesian network (HBN) architecture is developed where elementary random variables are successively combined to new ones, thus yielding compact summaries of the components information...
We have elaborated an autonomous mobile robot capable of exploring and navigating the entire accessible area in a closed a-priori unknown environment. In order to carry out this mission several modules execute in parallel as the robot evolves. The main modules developed are: the navigation strategy, the localisation system and the map building procedure. This paper shows the models and mechanisms...
In the context of map learning, a mobile robot must build and maintain a representation of the environment incrementally while locating itself. The robot is equipped with a set of sensors of limited precisions and may have an inexact model of the system evolution. The representation model is probabilistic in nature and the EKF (Extended Kalman Filtering) algorithm has been widely adopted to model...
Navigation methods for mobile robots need to take various sources of uncertainty into account in order to get robust performance. The ability to improve performance with experience and to adapt to new circumstances is equally important for long-term operation. Real-time constraints, limited computation and memory, as well as the cost of collecting training data also need to be accounted for. In this...
Set the date range to filter the displayed results. You can set a starting date, ending date or both. You can enter the dates manually or choose them from the calendar.