Showing papers on "Mobile robot navigation published in 1990"

Sonar-based real-world mapping and navigation

Abstract: A sonar-based mapping and navigation system developed for an autonomous mobile robot operating in unknown and unstructured environments is described. The system uses sonar range data to build a multileveled description of the robot's surroundings. Sonar readings are interpreted using probability profiles to determine empty and occupied areas. Range measurements from multiple points of view are integrated into a sensor-level sonar map, using a robust method that combines the sensor information in such a way as to cope with uncertainties and errors in the data. The resulting two-dimensional maps are used for path planning and navigation. From these sonar maps, multiple representations are developed for various kinds of problem-solving activities. Several dimensions of representation are defined: the abstraction axis, the geographical axis, and the resolution axis. The sonar mapping procedures have been implemented as part of an autonomous mobile robot navigation system called Dolphin. The major modules of this system are described and related to the various mapping representations used. Results from actual runs are presented, and further research is mentioned. The system is also situated within the wider context of developing an advanced software architecture for autonomous mobile robots.

Incorporating range sensing in the robot navigation function

Abstract: A model of mobile robot navigation is considered in which the robot is a point automaton operating in an environment with unknown obstacles of arbitrary shapes. The robot's input information includes its own and the target-points coordinates as well as local sensing information such as that from stereo vision or a range finder. These algorithmic issues are addressed: (1) Is it possible to combine sensing and planning functions to produce 'active sensing' guided by the needs of planning? (The answer is yes). (2) Can richer sensing (e.g., stereo vision versus tactile) guarantee better performance, that is, resulting in shorter paths? (The general answer is no). A paradigm for combining range data with motion planning is presented. It turns out that extensive modifications of simpler tactile algorithms are needed to take full advantage of additional sensing capabilities. Two algorithms that guarantee convergence and exhibit different styles of behavior are described, and their performance is demonstrated in simulated examples. >

Dynamic map building for autonomous mobile robot

Abstract: Presents an algorithm for autonomous map building and maintenance for a mobile robot. With each geometric target in the map the authors associate a validation measure to represent the belief in the validity of a target, in addition to the usual covariance matrix to represent spatial uncertainty. At each position update cycle, predicted features are generated for each target in the map and compared to features actually observed. Successful matches to targets with high validation measure are used for localization. Unpredicted observations are used to initialize target tracks for new environment features, while unobserved predictions result in a target's validation measure being decreased. They describe experimental results obtained with the algorithm that demonstrate successful map-building using real sonar data. >

A Distributed Model for Mobile Robot Environment-Learning and Navigation

Abstract: A distributed method for mobile robot navigation, spatial learning, and path planning is presented. It is implemented on a sonar-based physical robot, Toto, consisting of three competence layers: 1) Low-level navigation: a collection of reflex-like rules resulting in emergent boundary-tracing. 2) Landmark detection: dynamically extracts landmarks from the robot''s motion. 3) Map learning: constructs a distributed map of landmarks. The parallel implementation allows for localization in constant time. {\it Spreading of activation} computes both topological and physical shortest paths in linear time. The main issues addressed are: distributed, procedural, and qualitative representation and computation, emergent behaviors, dynamic landmarks, minimized communication.

Autonomous navigation in a manufacturing environment

Abstract: Current approaches towards achieving mobility in the workplace are reviewed. The role of automatic guided vehicles (AGVs) and some of the preliminary work of other groups in autonomous vehicles are described. An overview is presented of the autonomous robot architecture (AuRA), a general-purpose system designed for experimentation in the domain of intelligent mobility. The means by which navigation is accomplished within this framework is specifically addressed. A description is given of the changes made to AuRA to adapt it to a flexible manufacturing environment, the types of knowledge that need to be incorporated, and the new motor behaviors required for this domain. Simulations of both navigational planning and reactive/reflexive motor schema-based navigation in a flexible manufacturing systems environment, followed by actual navigational experiments using the mobile vehicle, are presented. >

An integrated navigation and motion control system for autonomous multisensory mobile robots

Abstract: Research on mobile robots began in the late sixties with the Stanford Research Institute’s pioneering work. Two versions of SHAKEY, an autonomous mobile robot, were built in 1968 and 1971. The main purpose of this project was “to study processes for the realtime control of a robot system that interacts with a complex environment” 〈NIL 69〉. Indeed, mobile robots were and still are a very convenient and powerful support for research on artificial intelligence oriented robotics. They possess the capacity to provide a variety of problems at different levels of generality and difficulty in a large domain including perception, decision making, communication, etc., which all have to be considered within the scope of the specific constraints of robotics: on-line computing, cost considerations, operating ability, and reliability.

A fast line finder for vision-guided robot navigation

Abstract: There are two basic ways to improve the speed of a low-level vision algorithm: careful code optimization and selective processing. Reducing the computational effort expended on each pixel reduces the time required to process an image by a constant factor. Selective processing on a limited portion of an image using a focus of attention can decrease overall computation by orders of magnitude. A fast pixel-based algorithm is developed that uses these principles to achieve fast extraction of lines for use in vision-guided mobile robot navigation. It builds upon an algorithm for extracting lines by grouping pixels with similar gradient orientation. It allows parametric control of computational resources required to extract lines with particular characteristics. >

Cooperative control of a semi-autonomous mobile robot

Abstract: Multiagent control systems for robots are considered. A robot is described that is based on treating the existing behavioral agents as simply an enhanced effector command language and designing a higher-level control structure that switches them on and off. It is shown how supervisory control can be added to such a reactive multiagent system. >

Model-directed mobile robot navigation

Abstract: The authors report on the system and methods used by UMass Mobile Robot Project. Model-based processing of the visual sensory data is the primary mechanism used for controlling movement of an autonomous land vehicle through the environment, measuring progress towards a given goal, and avoiding obstacles. Goal-oriented navigation takes place through a partially modeled, unchanging environment that contains no unmodeled obstacles; this simplified environment provides a foundation for research in more complicated domains. The navigation system integrates perception, planning, and execution of actions. Of particular importance is that the planning processes are reactive and reason about landmarks that should be perceived at various stages of task execution. Correspondence between image features and expected landmark locations are used at several abstraction levels to ensure proper plan execution. The system and some experiments that demonstrate the performance of its components is described. >

Integrating execution, planning, and learning in soar for external environments

Abstract: Three key components of an autonomous intelligent system are planning, execution, and learning. This paper describes how the Soar architecture supports planning, execution, and learning in unpredictable and dynamic environments. The tight integration of these components provides reactive execution, hierarchical execution, interruption, on demand planning, and the conversion of deliberate planning to reaction. These capabilities are demonstrated on two robotic systems controlled by Soar, one using a Puma robot arm and an overhead camera, the second using a small mobile robot with an arm.

A Reactive Robot Navigation System Based on a Fluid Dynamics Metaphor

Abstract: Mobile robots need a powerful and flexible navigation system in order to move around autonomously in an incompletely known and changing environment In this paper we present a computational metaphor for path generation which is gleaned from fluid dynamics It is powerful because it can find optimal paths in a maze of arbitrary complexity and it is flexible because it readily adapts to any change in the topology of the maze Moreover, it can be proven that the path generator does not suffer from local minima, a defect which hampers some of the other metaphor based methods We show that the fluid dynamics metaphor also provides ample possibilities to solve more complicated navigation problems including navigation through weighted regions The paper discusses the natural parallelism of the metaphor and its implementation on the DAP computer, which is an SIMD machine

Environment learning using a distributed representation

Abstract: A method for robust mobile robot navigation and environmental learning is presented. It was implemented and tested on a physical robot. The method consists of a collection of simple, incrementally designed robot behaviors. The behaviors receive sonar and compass data which they use to dynamically detect landmarks and construct a distributed map of the environment. The map is represented as a graph in which each node is a collection of augmented finite state machines functioning in parallel. The distributed nature of the map allows for localization in constant time. The method utilizes a modified spreading of activation scheme to accomplish robust linear-time path planning. It is capable of generating both topologically and physically shortest paths to the goal. The method uses local information to achieve the global task without having to replan if the robot becomes lost or strays off the desired path. >

Application of multi-target tracking to sonar-based mobile robot navigation

Abstract: The authors describe an approach to mobile robot navigation that unifies the problems of obstacle avoidance, position estimation, and map building in a common multi-target tracking framework. Model-based navigation is viewed as a process of tracking naturally occurring geometric targets or beacons. Targets that have been predicted (expected) from the environment map are tracked to provide vehicle position estimates (localization). Targets that are observed, but not predicted, represent unknown environment features or obstacles and cause new tracks to be initiated, classified, and ultimately integrated into the map. A good sensor model is a crucial component of this approach, and is used both for predicting expected observations and classifying unexpected observations. This navigation framework is being implemented on a mobile robot that employs sonar as the principal navigation sensor. An implementation of model-based localization that achieves robust position estimation in a known environment is presented. Preliminary results in obstacle identification and map building are given that lead one to believe that a complete navigation system, encompassing localization, obstacle avoidance, and map building, can be implemented exclusively with sonar. >

Using a Genetic Algorithm to Learn Strategies for Collision Avoidance and Local Navigation.

Abstract: : Navigation through obstacles such as mine fields is an important capability for autonomous underwater vehicles. One way to produce robust behavior is to perform projective planning. However, real-time performance is a critical requirement in navigation. What is needed for a truly autonomous vehicle are robust reactive rules that perform well in a wide variety of situations, and that also achieve real-time performance. In this work, SAMUEL, a learning system based on genetic algorithms, is used to learn high-performance reactive strategies for navigation and collision avoidance. (AN)

Situationally driven local navigation for mobile robots

Abstract: For mobile robots to autonomously accommodate dynamically changing navigation tasks in a goal-directed fashion, they must employ navigation plans. Any such plan must provide for the robot's immediate and continuous need for guidance while remaining highly flexible in order to avoid costly computation each time the robot's perception of the world changes. Due to the world's uncertainties, creation and maintenance of navigation plans cannot involve arbitrarily complex processes, as the robot's perception of the world will be in constant flux, requiring modifications to be made quickly if they are to be of any use. This work introduces Navigation Templates (or NaTs) which are building blocks for the construction and maintenance of rough navigation plans which capture the relationship that objects in the world have to the current navigation task. By encoding only the critical relationship between the objects in the world and the navigation task, a NaT-based navigation plan is highly flexible; allowing new constraints to be quickly incorporated into the plan and existing constraints to be updated or deleted from the plan. To satisfy the robot's need for immediate local guidance, the NaTs forming the current navigation plan are passed to a transformation function. The transformation function analyzes the plan with respect to the robot's current location to quickly determine (a few times a second) the locally preferred direction of travel. This dissertation presents NaTs and the transformation function as well as the needed support systems to demonstrate the usefulness of the technique for controlling the actions of a mobile robot operating in an uncertain world. ftn*This work was supported in part by a grant from the Jet Propulsion Laboratory under a contract from the National Aeronautics and Space Administration, and by a grant from the Naval Surface Weapons Center.

Motion planning for mobile robots in a dynamic environment with moving obstacles

Abstract: The objective of this study is to develop a method for mobile robot motion planning in the presence of moving obstacles. The concept of traversability vectors is used to analyze the spatial relationship between the robot and moving obstacles. Given a predefined path, the occupancy of the path by moving obstacles can be detected and registered on the constraint map. Obstacles on this map represent time constraints on the robot motion along the path. A search algorithm is then developed to coordinate the robot motion. Simulation results for this approach are discussed. >

Towards a real-time architecture for obstacle avoidance and path planning in mobile robots

Abstract: The design and partial implementation of a real-time architecture for a mobile robot, aimed particularly towards a vehicle developed for factory automation, is described. The authors develop a layered design to equip the robot with a number of behavioral competences. They examine sensing and a potential field algorithm especially to achieve modification of behavior at a speed close to the robot's operational speed. It is shown how the layered architecture interfaces to the original onboard architecture, which provided sophisticated localization but no ability to deal with environmental exceptions. >

Reactive and preplanned control in a mobile robot

Abstract: An architecture for robot navigation that combines reactive and preplanned control and has been demonstrated on an actual robot is presented. The system shares features of reactive control with other systems, but it is unique in its integration of planning with reactive control. It is believed that the organization could be effective for nonmobile robots as well. The result of this novel organization is robust, flexible, autonomous, real-time robot control; this organization has been demonstrated on a mobile robot that explores the peopled hallways of a large office building. >

Laser-radar based mapping and navigation for an autonomous mobile robot

Abstract: The environment mapping and navigation components of MOBOT-III are described. MOBOT-III is a laser-radar-based autonomous mobile robot designed to operate in an unknown indoor environment with moving obstacles. A simple environment representation that is continuously updated while MOBOT-III moves through the environment is used as the basis for the navigation method described. The environment representation is maintained by sensor data processing components, and a world model is built up successively as the system explores its environment. >

Building a 3D world model with a mobile robot: 3D line segment representation and integration

Abstract: A system whereby a mobile robot in an unknown environment can incrementally build a world model is described. The model discussed is segment-based. A trinocular system is used to build a local map of the environment. A global map is obtained by integrating a sequence of stereo frames taken while the robot navigates in the environment. Emphasis is on the representation of the uncertainty of 3D segments from stereo and on the integration of segments from multiple views. The representation is simple and very convenient for characterizing the uncertainty of segments. A Kalman filter is used to merge matched line segments. An important characteristic of the integration strategy is that a segment observed by the stereo system corresponds only to one part of the segment in space, so that the union of different observations gives a better estimate on the segment in space. The integration of 35 stereo frames taken in a robot room is described. >

Terrain aided navigation: current status, techniques for flat terrain and reference data requirements

Abstract: It is pointed out that terrain referenced navigation (TRN) techniques are now well established as effective position-fixing systems suitable for use in manned and unmanned vehicles. The SPARTAN TRN technique, which has been selected for the UK Tornado GR4 update, provides accurate navigation with rapid initial capture without recourse to an initialization mode. An overview of the SPARTAN technique is provided, and techniques for improving navigation performance over very flat terrain are described. The benefits of the terrain characteristic matching techniques are outlined, and a summary of integrated navigation system performance is given. Terrain-aided systems require appropriate reference databases. The availability of the data and its suitability are discussed. The need for careful consideration of database quality and registration when terrain aided systems are being designed is indicated. >

The Navlab system for mobile robot navigation

Abstract: Mobile robots are useful for a broad range of tasks including factory automation, hazardous waste removal, planetary exploration, defense, and construction Navigation is an important component in these applications in order to transport materials and position sensors for data acquisition The robot's software must coordinate the sensing and robot control to recognize landmarks, detect and avoid obstacles, and guide the robot along navigable passageways The system must be organized in such a way that high-level, symbolic instructions can be systematically converted into low-level control signals to move the robot about In this thesis, we address the architectural and planning issues involved in building a mobile robot system We begin with CODGER, a software engineering tool for building complex robot systems for execution in a distributed programming environment It employs a common data representation with information hiding, synchronization primitives for the exchange of data between parallel modules, and a central geometric reasoning system to assimilate data taken at different times and places into a consistent form We describe a hierarchical architecture for navigation implemented atop CODGER that separates high-level route planning from low-level sensing, trajectory generation, and driving operations We illustrate a control scheme known as the driving pipeline that employs parallelism to maximize the velocity of the robot We illustrate how parameters of this control scheme such as the aiming of sensors and adjustment of robot speed affect parallelism, continuous motion, and robot behavior We extensively address the problem of trajectory planning in local navigation Our system is capable of planning trajectories while taking into account the visibility of landmarks, kinematic constraints such as a minimum turning radius, robot safety, and uncertainly in the robot's control and the environment Multi-resolution techniques are employed to reduce the number of states needed in the search space and thus the planning time Furthermore, we establish a framework for reasoning about a broad class of constraints to allow this work to be extended to other classes of robots, environments, and goal specifications Many of the ideas in this thesis were implemented and tested on the NAVLAB (NAVigational LABoratory), an outdoor mobile robot

A mobile robot: sensing, planning, and locomotion

Abstract: A mobile robot architecture must include sensing, planning, and locomotion which are tied together by a model or map of the world based on sensor information, apriori knowledge and generic models. The architecture of a Stanford's autonomous mobile robot is described including its distributed computing system, locomotion, and sensing. Additionally, some of the issues in the representation of a world model are explored. Sensor models are used to update the world model in a uniform manner, and uncertainty reduction is discussed.

Open architecture design and inter-task/inter module communication for an autonomous mobile robot

Abstract: Introduces the new experimental robot HILARE II. In order to build a mobile robot that will be an experimental testbed for several years, and to study and evaluate several approaches for organizing a robot system, basic architectural concepts have been derived and implemented. The robot system is composed of modules, the structure of which is described, as well as the communication tools they need to interact. These tools enable one to implement and evaluate several control schemes and mobile robot architecture approaches. >

Hierarchical Evidence Accumulation in the Pseiki System and Experiments in Model-Driven Mobile Robot Navigation

Abstract: In this paper, we will review the process of evidence accumulation in the PSEIKI system for expectation-driven interpretation of images of 3-D scenes. Expectations are presented to PSEIKI as a geometrical hierarchy of abstractions. PSEIKI's job is then to construct abstraction hierarchies in the perceived image taking cues from the abstraction hierarchies in the expectations. The Dempster-Shafer formalism is used for associating belief values with the different possible labels for the constructed abstractions in the perceived image. This system has been used successfully for autonomous navigation of a mobile robot in indoor environments.

Real-time autonomous robot navigation using VLSI neural networks

Abstract: We describe a real time robot navigation system based on three VLSI neural network modules. These are a resistive grid for path planning, a nearest-neighbour classifier for localization using range data from a time-of-flight infra-red sensor and a sensory-motor associative network for dynamic obstacle avoidance.