Alexander Kleiner's publications by topic

Also see:

Conference Papers

A New Algorithm for Learning Bayesian Classifiers from Data (Artificial Intelligence and Soft Computing, 2000)
We introduce a new algorithm for the induction of classifiers from data, based on Bayesian networks. Basically this problem has already been examined from two perspectives: first, the induction of classifiers by learning algorithms for Bayesian networks, second, the induction of classifiers based on the naive Bayesian classifier. Our approach is located between these two perspectives; it eliminates the disadvantages of both while exploiting their advantages. In contrast to recently appeared refinements of the naive Bayes classifier, which captures single correlations in the data, we have developed an approach which captures multiple correlations and furthermore does a trade-off between complexity and accuracy.
Self Organising Maps for Value Estimation to Solve Reinforcement Learning Tasks (Proc. of the 2nd International Conference on Enterprise Information Systems (ICEIS 2000), 2000)
Reinforcement learning has been applied recently more and more for the optimisation of agent behaviours. This approach became popular due to its adaptive and unsupervised learning process. One of the key ideas of this approach is to estimate the value of agent states. For huge state spaces however, it is difficult to implement this approach. As a result, various models were proposed which make use of function approximators, such as neural networks, to solve this problem. This paper focuses on an implementation of value estimation with a particular class of neural networks, known as self organizing maps.
CS Freiburg 2001 (RoboCup 2001 : Robot Soccer World Cup V, 2001)
The CS Freiburg team has become F2000 champion the third time in the history of RoboCup. The success of our team can probably be attributed to its robust sensor interpretation and its team play. In this paper, we will focus on new developments in our vision system, in our path planner, and in the cooperation component.
Towards a Life-Long Learning Soccer Agent (RoboCup 2002: Robot Soccer World Cup VI, 2002)
One problem in robotic soccer (and in robotics in general) is to adapt skills and the overall behavior to a changing environment and to hardware improvements. We applied hierarchical reinforcement learning in an SMDP framework learning on all levels simultaneously. As our experiments show, learning simultaneously on the skill level and on the skill selection level is advantageous since it allows for a smooth adaption to a changing environment.
Self-Localization in Dynamic Environments based on Laser and Vision Data (Proc. of the IEEE/RSJ Int. Conf. on Intelligent Robots & Systems (IROS), 2003)
For a robot situated in a dynamic real world environment the knowledge of its position and orientation is very advantageous and sometimes essential for carrying out a given task. Particularly, one would appreciate a robust, accurate and efficient selflocalization method which allows a global localization of the robot. In certain polygonal environments a laser based localization method is capable of combining all these properties by correlating observed lines with an a priori line model of the environment [5] . However, often line features can rather be detected by a vision system than by a laser range finder. For this reason we propose an extension of the laser based approach for the simultaneous use with lines detected by an omni-directional camera.
A Plugin-Based Architecture for Simulation in the F2000 League (RoboCup 2003: Robot Soccer World Cup VII, 2003)
Simulation has become an essential part in the development process of autonomous robotic systems. In the domain of robotics, developers often are confronted with problems like noisy sensor data, hardware malfunctions and scarce or temporarily inoperable hardware resources. A solution to most of the problems can be given by tools which allow the simulation of the application scenario in varying degrees of abstraction and the suppression of unwanted features of the domain (like e.g. sensor noise).
Approaching Urban Disaster Reality: The ResQ Firesimulator (RoboCup 2004: Robot Soccer World Cup VIII, 2004)
In this paper, we present a new fire simulator based on a realistic physical model of heat development and heat transport in urban fires. It allows to simulate three different ways of heat transport (radiation, convection, direct transport) and the influence of wind.
Successful Search and Rescue in Simulated Disaster Areas (Robocup 2005: Robot Soccer World Cup IX, 2005)
This paper presents the comprehensive search and rescue approach of the ResQ Freiburg team, the winner in the RoboCupRescue Simulation league at RoboCup 2004. Specific contributions include the predictions of travel costs and civilian life-time, the efficient coordination of an active disaster space exploration, as well as an any-time rescue sequence optimization based on a genetic algorithm. We compare the performances of our team and others in terms of their capability of extinguishing fires, freeing roads from debris, disaster space exploration, and civilian rescue. The evaluation is carried out with information extracted from simulation log files gathered during RoboCup 2004.
RFID Technology-based Exploration and SLAM for Search And Rescue (Proc. of the IEEE/RSJ Int. Conf. on Intelligent Robots & Systems (IROS), 2006)
This paper proposes a novel method for real-time exploration and SLAM based on RFID tags that are autonomously distributed in the environment. We utilized the algorithm of Lu and Milios for calculating globally consistent maps from detected RFID tags. Furthermore we show how RFID tags can be used for coordinating the exploration of multiple robots.
Behavior maps for online planning of obstacle negotiation and climbing on rough terrain (Proc. of the IEEE/RSJ Int. Conf. on Intelligent Robots & Systems (IROS), 2007)
In this paper, we introduce a planning framework that extends ON to the general case, where different types of terrain classes directly map to specific robot skills, such as climbing stairs and ramps. This extension is based on a new concept called behavior maps, which is utilized for the planning and execution of complex skills. Behavior maps are directly generated from elevation maps, i.e. two-dimensional grids storing in each cell the corresponding height of the terrain surface, and a set of skill descriptions.
Cooperative Exploration for USAR Robots with Indirect Communication (Proc.of 6th IFAC Symposium on Intelligent Autonomous Vehicles (IAV'07), 2007)
To coordinate a team of robots for exploration is a challenging problem, particularly in unstructured areas, as for example post-disaster scenarios where direct communication is severely constrained. Furthermore, conventional methods of SLAM, e.g. those performing data association based on visual features, are doomed to fail due to bad visibility caused by smoke and fire. We use indirect communication (based on RFIDs), to share knowledge and use a gradient-like local search to direct robots towards interesting areas. To share a common frame of reference among robots we use a feature based SLAM approach (where features are RFIDs). The approach has been evaluated on a 3D simulation based on USARSim.
Decentralized SLAM for Pedestrians without direct Communication (Proc. of the IEEE/RSJ Int. Conf. on Intelligent Robots & Systems (IROS), 2007)
In this paper, we introduce a solution to this problem based on the non-selfish sharing of information between pedestrians for loop-closure. We introduce a novel DSLAM method which is based on data exchange and association via RFID technology, not requiring any radio communication.
Genetic MRF model optimization for real-time victim detection in Search and Rescue (Proc. of the IEEE/RSJ Int. Conf. on Intelligent Robots & Systems (IROS), 2007)
In this paper, we introduce a solution to this problem based on the non-selfish sharing of information between pedestrians for loop-closure. We introduce a novel DSLAM method which is based on data exchange and association via RFID technology, not requiring any radio communication.
RFID-Based Exploration for Large Robot Teams (Proc. of the IEEE Int. Conf. on Robotics & Automation (ICRA), 2007)
Coordination can generally be separated into a task assignment phase and a multi-robot path planning phase. In this paper, we address both problems jointly. This is possible because we reduce significantly the size of the search space by utilizing RFID tags as coordination points. The exploration approach consists of two parts: a stand-alone distributed local search and a global monitoring process which can be used to restart the local search in more convenient locations.
Multi-Robot Range-Only SLAM by Active Sensor Nodes for Urban Search and Rescue (Robocup 2008: Robot Soccer World Cup XII, 2008)
We consider the problem of multi-robot range-only SLAM for robot teams by solving the data association problem with wireless sensor nodes that we designed for this purpose. The memory of these nodes is utilized for the exchange of map data between multiple robots, facilitating loop-closures on jointly generated maps. We introduce RSLAM, which is a variant of FastSlam, extended for range-only measurements and the multi-robot case.
Towards automated online diagnosis of robot navigation software (Proc. of Int. Conf. on Simulation, Modeling and Programming for Autonomous Robots (SIMPAR 2008), 2008)
We present an approach which is able to automatically derive a model of the communication behavior within a component-orientated control software. The model can be used for online diagnosis in order to increase system robustness during runtime.

Dissertation

Mapping and Exploration for Search and Rescue with Humans and Mobile Robots (Ph.D. dissertation, 2008)
In this thesis a unified approach joining human and robot resources for solving these problems is contributed. Following the vision of combined multi-robot and multi-human teamwork, core problems, such as position tracking on rough terrain, mapping by mixed teams, and decentralized team coordination with limited radio communication, are directly addressed. More specific, RFID-SLAM, a novel method for robust and efficient loop closure in large-scale environments that utilizes RFID technology for data association, is contributed. The method is capable of jointly improving multiple maps from humans and robots in a centralized and decentralized manner without requiring team members to perform loops on their routes. Thereby positions of humans are tracked by PDR (Pedestrian Dead Reckoning), and robot positions by slippage- sensitive odometry, respectively. The joint-graph emerging from these trajectories serves as an input for an iterative map optimization procedure. The introduced map representation is further utilized for solving the centralized and decentralized coordination of large rescue teams. On the one hand, a deliberate method for combined task assignment and multi-agent path planning, and on the other hand, a local search method using the memory of RFIDs for coordination, are proposed.

Journal Papers

CS Freiburg: Coordinating Robots for Successful Soccer Playing (IEEE Transactions on Robotics and Automation, 2002)
This paper presents the CS Freiburg team, the winner in the middle size league at RoboCup 1998, 2000 and 2001. The paper focuses on multi-agent coordination for both perception and action. The contributions of this work are new methods for tracking ball and players observed by multiple robots, team coordination methods for strategic team formation and dynamic role assignment, a rich set of basic skills allowing to respond to large range of situations in an appropriate way, an action selection method based on behavior networks as well as a method to learn the skills and their selection.
Game AI: The shrinking gap between computer games and AI systems (Ambient Intelligence: The evolution of technology, communication and cognition towards the future of human-computer interaction, 2005)
We sketch some methods currently utilized in RoboCup and relates them to methods found in commercial computer games. We show how methods from RoboCup might contribute to game AI and improve both the performance and plausibility of its digital characters. Furthermore, we describe state-of-the-art game engines and discuss the challenge but also opportunity they are offering to AI research.
Real-time Localization and Elevation Mapping within Urban Search and Rescue Scenarios (Journal of Field Robotics, 2007)
In this paper we propose real-time solutions for localization and mapping, which all have been extensively evaluated within the test arenas of the National Institute of Standards and Technology (NIST). We specifically deal with the problems of vision-based pose tracking on tracked vehicles, the building of globally consistent maps based on a network of RFID tags, and the building of elevation maps from readings of a tilted Laser Range Finder (LRF). Our results show that these methods lead under modest computational requirements to good results within the utilized testing arenas.
Towards heterogeneous robot teams for disaster mitigation: Results and Performance Metrics from Robocup Rescue (Journal of Field Robotics, 2007)
Urban Search And Rescue is a growing area of robotic research. The RoboCup Federation has recognized this, and has created the new Virtual Robots competition to complement its existing physical robot and agent competitions. In order to successfully compete in this competition, teams need to field multi-robot solutions that cooperatively explore and map an environment while searching for victims. This paper presents the results of the first annual RoboCup Rescue Virtual competition. It provides details on the metrics used to judge the contestants as well as summaries of the algorithms used by the top four teams. This allows readers to compare and contrast these effective approaches. Furthermore, the simulation engine itself is examined and real-world validation results on the engine and algorithms are offered.

Team Description Papers

ResQ Freiburg: Team Description and Evaluation (RoboCup 2004 (CDROM Proceedings), Team Description Paper, Rescue Simulation League, 2004)
RoboCupRescue is a large-scale multi-agent simulation of urban disasters where, in order to save lives and minimize damage, rescue teams must effectively cooperate despite sensing and communication limitations. To accomplish this, ResQ Freiburg introduced new methods for hierarchical path planning, death-time prediction of civilians, coordination of multi-agent city exploration, as well as an any-time rescue sequence optimization based on genetic algorithms.
RoboCupRescue - Robot League Team RescueRobots Freiburg (Germany) (RoboCup 2005 (CDROM Proceedings), Team Description Paper, Rescue Robot League, 2005)
This paper describes the approach of the RescueRobots Freiburg team. RescueRobots Freiburg is a team of students from the university of Freiburg, that originates from the former CS Freiburg team (RoboCupSoccer) and the ResQ Freiburg team (RoboCupRescue Simulation).
RoboCupRescue - Robot League Team RescueRobots Freiburg (Germany) (RoboCup 2006 (CDROM Proceedings), Team Description Paper, Rescue Robot League, 2006)
This paper describes the approach of the RescueRobots Freiburg team, which is a team of students from the University of Freiburg that originates from the former CS Freiburg team (RoboCupSoccer) and the ResQ Freiburg team (RoboCupRescue Simulation). Furthermore we introduce linkMAV, a micro aerial vehicle platform. Our approach covers RFID-based SLAM and exploration, autonomous detection of relevant 3D structures, visual odometry, and autonomous victim identification. Furthermore, we introduce a custom made 3D Laser Range Finder (LRF) and a novel mechanism for the active distribution of RFID tags.
RoboCupRescue - Simulation League Team RescueRobots Freiburg (Germany) (RoboCup 2006 (CDROM Proceedings), Team Description Paper, Rescue Simulation League, 2006)
This paper describes the approach of the RescueRobots Freiburg Virtual League team. Our simulated robots are based on the two real robot types Lurker, a robot capable of climbing stairs and random stepfield, and Zerg, a lightweight and agile robot, capable of autonomously distributing RFID tags. Our approach covers a novel method for RFID-Technology based SLAM and exploration, allowing the fast and efficient coordination of a team of robots. Furthermore we utilize Petri nets for team coordination.

Technical Reports

Rescue3D: Making rescue simulation attractive to the public (TR, 2004)
The annually increasing number of teams participating in the Rescue Simulation league shows clearly that there is a high demand on research in this field. However, from our experience of participating at RoboCup as a team, but also from organizing RoboCupRescue as a public event, we learned about two strong limitations that arise practically during the competition: First, the current system offers only limited methods for comparing specific abilities of rescue teams. Second, the current presentation of the competition is only limited understandable for spectators. Within our effort in developing a new visualization of the rescue domain, we want to focus on these two limitations. We introduce a system for visualization that covers the demands of both developers and spectators.
ResQ Freiburg: Team Description and Evaluation (TR, 2005)
RoboCupRescue is a large-scale multi-agent simulation of urban disasters where, in order to save lives and minimize damage, rescue teams must effectively cooperate despite sensing and communication limitations. To accomplish this, ResQ Freiburg introduced new methods for hierarchical path planning, death-time prediction of civilians, coordination of multi-agent city exploration, as well as an any-time rescue sequence optimization based on genetic algorithms. To evaluate the usefulness of these techniques we performed an extensive evaluation of the log files of the best participating teams in the competition.

Video Proceedings

Behavior maps for online planning of obstacle negotiation and climbing on rough terrain (Video Proc. of the IEEE/RSJ Int. Conf. on Intelligent Robots and Systems (IROS), 2007)
In this paper, we introduce a planning framework that extends ON to the general case, where different types of terrain classes directly map to specific robot skills, such as climbing stairs and ramps. This extension is based on a new concept called behavior maps, which is utilized for the planning and execution of complex skills. Behavior maps are directly generated from elevation maps, i.e. two-dimensional grids storing in each cell the corresponding height of the terrain surface, and a set of skill descriptions.

Workshop Papers

Visual Odometry for Tracked Vehicles (Proc. of the IEEE Int. Workshop on Safety, Security and Rescue Robotics (SSRR), 2006)
In this paper we describe a solution to the pose estimation problem by utilizing a consumer-quality camera and an Inertial Measurement Unit (IMU). The basic idea is to continuously track salient features with the KLT feature tracker over multiple images taken by the camera and to extract from the tracked features image vectors resulting from the robot's motion.
Wearable computing meets multiagent systems: A real-world interface for the RoboCupRescue simulation platform (First International Workshop on Agent Technology for Disaster Management at AAMAS06, 2006)
We propose preliminary results from a wearable computing device, acquiring disaster relevant data, such as locations of victims and blockades, and show the data integration into the RoboCupRescue Simulation platform, which is a benchmark for MAS within the RoboCup competitions.
Mapping disaster areas jointly: RFID-Coordinated SLAM by Humans and Robots (Proc. of the IEEE Int. Workshop on Safety, Security and Rescue Robotics (SSRR), 2007)
In this paper, we introduce a method for jointly correcting individual trajectories of humans and robots by utilizing RFID technology for data association. Hereby the poses of humans and robots are tracked by a PDR (Pedestrian Dead Reckoning), and slippage sensitive odometry, respectively.
Towards the Integration of Real-Time Real-World Data in Urban Search and Rescue Simulation (Int. Workshop on Mobile Information Technology for Emergency Response - MobileResponse 2007, 2007)
The coordinated reaction to a large-scale disaster is a challenging research problem. The Robocup rescue simulation league addresses this research problem but is currently lacking an interface to real-world real-time data to test the validity of both simulation and simulated reactions. In this paper, we describe a wearable-computing-based real world interface to the Robocup Resuce simulation software and provide some updated results of preliminary evaluations.

(This webpage was created with bibtex2web.)