About
37
Publications
9,649
Reads
How we measure 'reads'
A 'read' is counted each time someone views a publication summary (such as the title, abstract, and list of authors), clicks on a figure, or views or downloads the full-text. Learn more
378
Citations
Publications
Publications (37)
Machine learning (ML) has become highly relevant in applications across all industries, and specialists in the field are sought urgently. As it is a highly interdisciplinary field, requiring knowledge in computer science, statistics and the relevant application domain, experts are hard to find. Large corporations can sweep the job market by offerin...
Vorstellung des Projekts ML2 Menschen Lernen Maschinelles Lernen Project presentation ML2
For the RoboCup Soccer AdultSize League the humanoid robot Sweaty uses a single fully convolutional neural network to detect and localize the ball, opponents and other features on the field of play. This neural network can be trained from scratch in a few hours and is able to perform in real-time within the constraints of computational resources av...
One of the challenges in humanoid robotics is motion control. Interacting with humans requires impedance control algorithms, as well as tackling the problem of the closed kinematic chains which occur when both feet touch the ground. However, pure impedance control for totally autonomous robots is difficult to realize, as this algorithm needs very p...
![Fig. 3. FSR placed on the feet from a NAO robot [1]](profile/Klaus-Dorer/publication/313497201/figure/fig3/AS:459853547216898@1486649037267/FSR-placed-on-the-feet-from-a-NAO-robot-1_Q320.jpg)
The humanoid Sweaty was the finalist in this year's robocup soccer championship(adult size). For the optimization of the gait and the stability, data concerning forces and torques in the ankle joints would be helpful. In the following paper the development of a six-axis force and torque sensor for the humanoid robot Sweaty is described. Since comme...
![Fig. 2. Mechanical horse [7]](profile/Klaus-Dorer/publication/313497042/figure/fig2/AS:459852691578882@1486648833663/Mechanical-horse-7_Q320.jpg)
Autonomous humanoid robots require light
weight, high torque and high speed actuators to be able to
walk and run. For conventional gears with a fixed gear ratio
the product of torque and velocity is constant. On the other
hand desired motions require maximum torque and speed. In
this paper it is shown that with a variable gear ratio it is
possible t...
Soccer simulation league is one of the founding leagues of RoboCup. In this paper we discuss the past, present and planned future achievements and changes. Also we summarize the connections and interleague achievements of this league and provide an overview of the community contributions that made this league successful.
In this paper we propose a motion framework for bipedal robots that decouples motion definitions from stabilizing the robot. This simplifies motion definitions yet allows dynamic motion adaptations. Two applications, walking and stopping on one leg, demonstrate the power of the framework. We show that our framework is able to perform walking and st...
Autonomous humanoid robots need high torque actuators to be able to walk and run. One problem in this context is the heat generated. In this paper we propose to use water evaporation to improve cooling of the motors. Simulations based on thermodynamic calculations as well as measurements on real actuators show that, under the assumption of the load...
Existing approaches solving multi-vehicle pickup and delivery problems with soft time windows typ-ically use common benchmark sets to verify their performance. However, there is a gap from these benchmark sets to real world problems with respect to instance size and problem complexity. In this paper we show that a combination of existing ap-proache...
In their famous work on prospect theory Kahneman and Tversky have presented a couple of examples where human decision making
deviates from rational decision making as defined by decision theory. This paper describes the use of extended behavior networks
to model human decision making in the sense of prospect theory. We show that the experimental f...
Abstract This paper discusses a technological solution to real-time road transportation optimization using a commercial multi-agent based system, LS/ATN, which has been proven through real-world deployment to reduce transportation costs for both small and large fleets in the full and part load business. Subsequent to describing the real-time optimi...
A considerable volume of research exists concerning the domain of automatic planning and scheduling, hut many real-world scheduling problems, and especially that of transportation logistics, remain difficult to solve. In particular, this domain demands schedule-solving for every vehicle in a transportation fleet where pick-up and delivery of custom...
Agent technology provides industrial-applications developers with new abstractions for distributed-system development, new methodological tools, and a set of algorithms for creating autonomous, collaborative systems. Over the past few years, a number of industrial applications have deployed agents. However, a substantial gap still exists between th...
Multiagent systems and agent technologies provide industrial developers with a novel implementation paradigm and a wide range of ready-to-use technologies, development platforms, and techniques and algorithms. The Industry Track of the Fourth International Conference on Autonomous Agents and Multiagent Systems covered a wide range of industrial app...
Abstract A considerable amount,of research has been concerned with the domain,of automatic,planning and schedul- ing, but many real world scheduling problems such as The Pick up and Delivery Problem With Time Windows (PDPTW) are still not easily tackled. The PDPTW problem,demands,solving the schedule for each vehi- cle of a transportation fleet whe...
This paper describes LS/ATN, Living Systems®Adaptive Transportation Networks, an agent-based solution we have developed to solve transportation problems in the charter business logistics. LS/ATN provides automatic optimization and execution capabilities that extend the existing planning systems accordingly. To describe our solution and analyse its...
For more than 15 years software agent has been a fascinating area of research. During the time agent systems have matured
in terms of business application as well as technological support. After an introduction to the agent paradigm this paper
describes the ‘Living Agents’ agent server and development toolset as an example of how tool support helps...
In this paper we present how behavior networks can be extended to model behavior selection of agents in dynamic and con-tinuous domains. More precisely, the focus is on a mechanism for selection of concurrent behaviors by explicit representation of re-sources a behavior makes use of. Further it describes how the be-havior selection process can be c...
In this paper we describe our approach for an efficient design and implementation of multi-agent systems using agent oriented methodologies and tools. We demonstrate the strength of this approach taking the example of the TAC domain. The trading agent competition (TAC) is a challenging e-marketplace domain for autonomous auction agents. The develop...
Dieser Artikel beschreibt Design und Umsetzung eines Agentensystems für den Handel in vernetzten Märkten am Beispiel der Umgebung der Trading Agent Competition (TAC). Die Trading Agent Competition stellt eine Umgebung zur Verfügung
in der die Agenten als Reiseagenten tätig werden und in Konkurrenz mit anderen Agenten für ihre Kunden Hotels
Flüge un...
In this paper we descibe the process of action control used by the agents of the magmaFreiburg team. It is based on extended behavior networks, which add situation-dependent motivational influence on the agent and extend original behavior networks to exploit information from continuous domains. Advantages of the original networks, such as reactivit...
The magmaFreiburg2000 team, as its predecessor, is based on Extended Behavior Networks [4]. This paper focuses on the improvements made compared to the magmaFreiburg1999 team of Stockholm. The main domain-independent
improvements have been made by introducing concurrent behavior selection into the Extended Behavior Networks framework [3]. Domain-de...
Contents 1 Introduction 3 1.1 History . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 3 1.1.1 History of the Soccerserver . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 3 1.1.2 History of the RoboCup Simulation League . . . . . . . . . . . . . . . . . . . . . . . . . . 4 1.1...
Introduction The main interest of our research concerns motivation action control and goal management of agents (magma). Action Control of the magmaFreiburg team is based on extended behavior networks, which add situation-dependent motivational influences to the agent, extend original behavior networks to exploit information from continuous domains...
The problem of action selection by autonomous agents becomes increasingly difficult when acting in continuous, non-deterministic and dynamic environments pursuing multiple and possibly conflicting goals. We propose a method that exploits additional information gained from continuous states, is able to deal with unexpected situations, and takes mult...
Die Arbeit widmet sich dem Problem der Handlungskontrolle autonomer Agenten in dynamischen, nicht-deterministischen und kontinuierlichen Umgebungen.
Aufbauend auf Arbeiten von Maes wird vorgeschlagen, Handlungskontrolle mit Hilfe von erweiterten Verhaltensnetzwerken durchzuführen.
Diese erlauben die Berücksichtigung mehrerer, auch in Konflikt zuei...
In this paper, we present the agent-based approach we have developed to solve dynamic multi-vehicle pickup and delivery problems
with soft time windows. While many of the existing research frameworks have been focusing on reaching near-optimal solutions,
the central theme of our work is the optimization of real-world sized problems in near real tim...
This paper describes a distributed mechanism for concurrent behavior selection in agents using extended behavior networks. Resource nodes are introduced into the networks to coordinate connicting behav-iors and manage limited resources of the agent. Concurrent behavior selection improves the agent's reactivity and allows pursuing multiple goals at...
Projects
Project (1)
Machine Learning gehört zu den wichtigsten Zukunftstechnologien der Digitalisierung. Unternehmen und Anwender haben aber noch wenig Wissen über Nutzen und Einsatz von ML
Mit einem einzigartigen Konzept bringt das Projekt ML2 Studierende verschiedener Masterprogramme und Praktiker aus den Unternehmen zum Thema Machine Learning zusammen und macht sie fit für die digitale Zukunft.
