Abstract. This paper addresses the problem of perception and localisation for a mobile robot in an unknown environment. It describes a modelling of the environment based on two certainty grids: one local model and the other one a global model. Localisation of the robot is reduced to nding the best alignment of the local certainty grid onto the global certainty grid. Four localisation procedures to correct the robot position are introduced. First experimental results show the capacity of the method. 1

This paper introduces histogramic in-motion mapping(HIMM), a new method for real-time map building with a mobile robot in motion. HIMM represents data in a two-dimensional array, called a histogram grid, that is updated through rapid in-motion sampling of onboard range sensors. Rapid in-motion sampling results in a map representation that is well-suited to modeling inaccurate and noisy range-sensor data, such as that produced by ultrasonic sensors, and requires minimal computational overhead. Fast map-building allows the robot to immediately use the mapped information in real-time obstacle-avoidance algorithms. The benefits of this integrated approach are twofold: (1) quick, accurate mapping; and (2) safe navigation of the robot toward a given target. HIMM has been implemented and tested on a mobile robot. Its dual functionality was demonstrated through numerous tests in which maps of unknown obstacle courses were created, while the robot simultaneously performed real-time obstacle avoidance maneuvers at speeds of up to 0.78 m/sec.

This paper addresses the reactive collision avoidance for vehicles that move in very dense, cluttered, and complex scenarios. First, we describe the design of a reactive navigation method that uses a "divide and conquer" strategy based on situations to simplify the difficulty of the navigation. Many techniques could be used to implement this design (since it is described at symbolic level), leading to new reactive methods that must be able to navigate in arduous environments (as the difficulty of the navigation is simplified). We also propose a geometry-based implementation of our design called the nearness diagram navigation. The advantage of this reactive method is to successfully move robots in troublesome scenarios, where other methods present a high degree of difficulty in navigating. We show experimental results on a real vehicle to validate this research, and a discussion about the advantages and limitations of this new approach.

Office delivery robots have to perform many tasks. They have to determine the order in which to visit ofces, plan paths to those offices, follow paths reliably, and avoid static and dynamic obstacles in the process. Reliability and efficiency are key issues in the design of such autonomous robot systems. They must deal reliably with noisy sensors and actuators and with incomplete knowledge of the environment. They must also act efficiently, in real time, to deal with dynamic situations. Our architecture is composed of four abstraction layers: obstacle avoidance, navigation, path planning, and task scheduling. The layers are independent, communicating processes that are always active, processing sensory data and status information to update their decisions and actions. A version of our robot architecture has been in nearly daily use in our building since December 1995. As of July 1996, the robot has traveled more than 75 kilometers in service of over 1800 navigation requests that were specified using our World Wide Web interface.

Gesture recognition is an important skill for robots that work closely with humans. Gestures help to clarify spoken commands and are a compact means of relaying geometric information. We have developed a real-time, three-dimensional gesture recognition system that resides on-board a mobile robot. Using a coarse three-dimensional model of a human to guide stereo measurements of body parts, the system is capable of recognizing six distinct gestures made by an unadorned human in an unaltered environment. An active vision approach focuses the vision system's attention on small, moving areas of space to allow for frame rate processing even when the person and/or the robot are moving. This paper describes the gesture recognition system, including the coarse model and the active vision approach. This paper also describes how the gesture recognition system is integrated with an intelligent control architecture to allow for complex gesture interpretation and complex robot action. Results from e...

Abstract not found

We present a general theory of topological maps whereby sensory input, topological and local metrical information are combined to define the topological maps explaining such information. Topological maps correspond to the minimal models of an axiomatic theory describing the relationships between the different sources of information explained by a map. We use a circumscriptive theory to specify the minimal models associated with this representation.

Based on evolutionary computation (EC) concepts, we developed an adaptive Evolutionary Planner/Navigator �EP/N � as a novel approach to path planning and navigation. The EP/N is characterized by generality, flexibility � and adaptability. It unifies offline planning and on�line planning/navigation processes in the same general and flexible evolutionary algorithm which (1) accommodates different optimization criteria and changes in these criteria, (2) incorporates various types of problem�specific domain knowledge, (3) enables good trade�offs among near�optimality of paths � high planning efficiency � and effective handling of unknown obstacles. More importantly � the EP/N can self-tune its performance for different task environments and changes in such environments � mostly through adapting probabilities of its operators and adjusting paths constantly even during a robot�s motion towards the goal.

To coordinate with other agents in its an environment, an agent needs models of what the other agents are trying to do. When communication is impossible or expensive, this information must be acquired indirectly via plan recognition. Typical approaches to plan recognition start with specification of the possible plans the other agents may be following and develop special techniques for discriminating among the possibilities. These structures are not the direct nor derived output of a planning system. Prior work has not yet addressed the problem of how the plan recognition structures are (or could be) derived from executable plans as generated by planning systems. Furthermore, concerns about building models of agents ’ actions in all possible worlds lead to a desire for dynamically constructing belief network models for situation-specific plan recognition activities. As a step in this direction, we have developed and implemented methods that take plans, as generated by a planning system, and creates a belief network model in support of the plan recognition task. We start from a language designed for plan specification, PRS (Ingrand, Georgeff, & Rao 1992).l From a PRS plan, we generate a belief network model that directly serves plan recognition by relating potential observations to the candidate plans. Our methods handle a large variety of plan structures such as conditional branching, subgoaling, and alternative goals. Furthermore, our application domain is coordinated autonomous robotic teams, where sensor-based observations are inherently uncertain. The methodology we have developed handles this uncertainty through explicit modeling, something not necessary in other plan recognition domains (Charniak & Goldman 1993; Goodman & Litman 1990) where observations are certain. An example of a belief network generated by the mapping methods from a set of simple plans for performing a “bounding-overwatch ” surveillance task

The problem of concurrent mapping and localization has received considerable attention in the mobile robotics community. Existing approaches can largely be grouped into two distinct paradigms: topological and metric. This paper proposes a method that integrates both. It poses the mapping problem as a statistical maximum likelihood problem, and devises an efficient algorithm for search in likelihood space. It presents an novel mapping algorithm that integrates two phases: a topological and a metric mapping phase. The topological mapping phase solves a global position alignment problem between potentially indistinguishable, significant places. The subsequent metric mapping phase produces a fine-grained metric map of the environment in floating-point resolution. The approach is demonstrated empirically to scale up to large, cyclic, and highly ambiguous environments.