Stefan Enderle

Miro - middleware for mobile robot applications

Developing software for mobile robot applications is a tedious and error-prone task. Modern mobile robot systems are distributed systems, and their designs exhibit large heterogeneity in terms of hardware, operating systems, communications protocols, and programming languages. Vendor-provided programming environments have not kept pace with recent developments in software technology. Also, standardized modules for certain robot functionalities are beginning to emerge. Furthermore, the seamless integration of mobile robot applications into enterprise information processing systems is mostly an open problem. We suggest the construction and use of object-oriented robot middleware to make the development of mobile robot applications easier and faster, and to foster portability and maintainability of robot software. With Miro, we present such a middleware, which meets the aforementioned requirements and has been ported to three different mobile platforms with little effort. Miro also provides generic abstract services like localization or behavior engines, which can be applied on different robot platforms with virtually no modifications.

Miro: Middleware for Autonomous Mobile Robots

Abstract Implementing software for autonomous mobile robots is a non-trivial task, because such robots incorporate several sensor systems and actuators that must be controlled simultaneously by a heterogeneous ensemble of networked computers and microcontrollers. Additionally, the use of modern software engineering technologies like object-oriented and distributed programming and client/server architectures is essential in order to maintain program code effectively. In this paper, we present Miro, a new CORBA-based robot programming framework which allows a rapid development of reliable and safe software on heterogeneous computer networks and supports the mixed use of several programming languages.

Vision-based localization for mobile robots

Abstract Robust self-localization and repositioning strategies are essential capabilities for robots operating in highly dynamic environments. Environments are considered highly dynamic, if objects of interest move continuously and quickly, and if chances of hitting or getting hit by other robots are quite significant. An outstanding example for such an environment is provided by RoboCup. Vision system designs for robots used in RoboCup are based on several approaches, aimed at fitting both the mechanical characteristics of the players and the strategies and operations that the different roles or playing situations may require. This paper reviews three approaches to vision-based self-localization used in the RoboCup middle-size league competition and describes the results they achieve in the robot soccer environment for which they have been designed.

Miro - Middleware for Cooperative Robotics

Developing software for mobile robot applications is a tedious and error-prone task. We suggest the use of object-oriented middleware to remedy the problem. After identifying crucial design goals, we present Miro, an object-oriented middleware for robots meeting the design goals. We discuss its implementation and demonstrate Miros role in the implementation of applications on different kinds of robots.

Vision-Based Localization in RoboCup Environments

Knowing its position in an environment is an essential capability for any useful mobile robot. Monte-Carlo Localization (MCL) has become a popular framework for solving the self-localization problem in mobile robots. The known methods exploit sensor data obtained from laser range finders or sonar rings to estimate robot positions and are quite reliable and robust against noise. An open question is whether comparable localization performance can be achieved using only camera images, especially if the camera images are used both for localization and object recognition. In this paper, we discuss the problems arising from these characteristics and show experimentally that MCL nevertheless works very well under these conditions.

Self-localization using sporadic features

Abstract Knowing its position in an environment is an essential capability for any useful mobile robot. Monte Carlo Localization (MCL) has become a popular framework for solving the self-localization problem in mobile robots. The known methods exploit sensor data obtained from laser range finders or sonar rings to estimate robot positions and are quite reliable and robust against noise. An open question is whether comparable localization performance can be achieved using only camera images, especially if the camera images are used both for localization and object recognition. In such a situation, it is both harder to obtain suitable models for predicting sensor readings and to correlate actual with predicted sensor data. Both problems can be easily solved if localization is based on features obtained by preprocessing images. In our image-based MCL approach, we combine visual distance features and visual landmark features, which have different characteristics. Distance features can always be computed, but have value-dependent and dramatically increasing margins for noise. Landmark features give good directional information, but are detected only sporadically. In our paper, we discuss the problems arising from these characteristics and show experimentally that MCL nevertheless works very well under these conditions.

Application of Neurosymbolic Integration for Environment Modelling in Mobile Robots

We present an architecture for representing spatial information on autonomous robots. This architecture integrates several kinds of representations each of which is tailored for different uses by the robot control software. We discuss various issues regarding neurosymbolic integration within this architecture. For one particular problem – extracting topological information from metric occupancy maps – various methods for their solution have been evaluated. Preliminary empirical results based on our current implementation are given.

The Ulm Sparrows 99

The Ulm Sparrows RoboCup team was initiated in early 1998. Among the goals of the team effort are to investigate methods for skill learning, adaptive spatial modeling, and emergent multiagent cooperation [1]. We develop both a middle-size robot league and a simulation league team. Based mostly on equipment and technology available in our robot lab, we implemented a first version of both teams for RoboCup-98 in order to gain practical experience in a major tournament. Based on the these experiences, we made significant progress in our team effort in several areas: we designed new robot hardware, extended our vision processing capabilities and implemented a revised and more complete version of our soccer agent software architecture. In particular, we added Monte Carlo localization techniques to our robots, enhanced environment modeling, and started to apply reinforcement learning techniques to improve basic playing skills.

The Ulm Sparrows: Research into Sensorimotor Integration, Agency Learning, and Multiagent Cooperation

We describe the motivations, research issues, current results, and future directions of THE ULM Sparrows, a project that aims at the design and implementation of a team of robotic soccer players.

Vision-Based Robot Localization Using Sporadic Features

Knowing its position in an environment is an essential capability for any useful mobile robot. Monte-Carlo Localization (MCL) has become a popular framework for solving the self-localization problem in mobile robots. The known methods exploit sensor data obtained from laser range finders or sonar rings to estimate robot positions and are quite reliable and robust against noise. An open question is whether comparable localization performance can be achieved using only camera images, especially if the camera images are used both for localization and object recognition. In this paper, we discuss the problems arising from these characteristics and showex perimentally that MCL nevertheless works very well under these conditions.