Dornberger, Rolf
Lade...
E-Mail-Adresse
Geburtsdatum
Projekt
Organisationseinheiten
Berufsbeschreibung
Nachname
Dornberger
Vorname
Rolf
Name
Dornberger, Rolf
36 Ergebnisse
Suchergebnisse
Gerade angezeigt 1 - 10 von 36
- PublikationInvestigating the effects of gaze behavior on the perceived delay of a robot's response(2019) Zhong, Jia; Schmiedel, Theresa; Dornberger, Rolf; Salichs, Miguel A.; Ge, Shuzhi Sam; Ivanova Barakova, Emilia; Cabibihan, John-John; Wagner, Alan R.; Castro-González, Álvaro; He, Hongsheng [in: Social Robotics. 11th International Conference, ICSR 2019, Madrid, Spain, November 26-29, 2019, proceedings]Slow responses of social robots cause user frustration in human robot communication. This paper investigates how far the gaze behavior of a robot, meaning the way the robot looks at its conversation partner, influences the perceived delay of a robot’s response in human-robot conversations. To enhance a natural conversation pattern, a gaze behavior was designed and implemented into a humanoid robot. A within-subject experiment involving 31 test subjects was designed with two conditions (with and without gaze behavior). The results generally show a positive correlation between the gaze behavior that the robot exhibits and the perceived responsiveness of the robot (in the condition with gaze behavior). However, the perceived responsiveness is the same in both conditions. One reason for this finding may be that the response time of the robot might have been generally too short to identify an effect in the experi mental setting. Future research can directly build on our research to assess the relation between gaze behavior and perceived responsiveness in further detail and draw upon the finding that gaze behavior generally plays an important role with regard to the perceived responsiveness of a robot. Robot designers can also build on our research and consider both gaze behavior and additional factors to address a perceived delay in a robot’s response.04B - Beitrag Konferenzschrift
- PublikationOptimization of multi-robot sumo fight simulation by a genetic algorithm to identify dominant robot capabilities(2019) Lehner, Joël Enrico; Dornberger, Rolf; Simic, Radovan; Hanne, Thomas [in: 2019 IEEE Congress on Evolutionary Computation (CEC 2019). Proceedings]This paper analyzes the multirobot sumo fight simulation. This simulation is based on a computational model of several sumo fighters, which physically interact while trying to move the opponent out of the arena (lost fight). The problem is optimized using a genetic algorithm (GA), where the capabilities of not only one particular robot but of all robots simultaneously are improved. In this particular problem setup, the problem definition changes depending on the optimization path, because all robots also get better, competing against each other. The influence of different operators of the GA is investigated and compared. This paper raises the questions, which genetically controlled capabilities (e.g. size, speed) are dominant over time and how they can be identified by a sensitivity analysis using a GA. The results shed light on which parameters are dominant. This experiment typically opens up interesting fields of further research, especially about how to address optimization problems, where the optimization process influences the search space and how to eliminate the factor of randomness.04B - Beitrag Konferenzschrift
- PublikationComparison of a real kilobot robot implementation with its computer simulation focussing on target-searching algorithms(IEEE, 2018) Zhong, Jia; Umamaheshwarappa, Ramya Ramedeverahalli; Dornberger, Rolf; Hanne, Thomas [in: 2018 International Conference on Intelligent Autonomous Systems (ICoIAS’2018)]This paper presents the functionality and quality of the implementation of a search- and target-surrounding swarm robotic algorithm, which was developed and tested in the simulator V-REP, on actually running Kilobots. Ten Kilobots were used for the experiment where one Kilobot acts as target and nine Kilobots act as searchers. The algorithm allows the searchers to disperse to find the target, to avoid collisions with other searchers, to orbit other searchers, which are closer to the target, and to finally surround the target, once it is found. The results of the implementation using actual, real swarm robots are compared with the results of the computer simulation. Differences between simulation and real robot implementation are discussed. In particular, issues associated with the limitation in the Kilobots’ communication capability and their implications on the algorithm are investigated.04B - Beitrag Konferenzschrift
- PublikationInvestigating the democracy behavior of swarm robots in the case of a best-of-n selection(2018) Pochon, Yann; Dornberger, Rolf; Zhong, Jia; Korkut, Safak; Sundaram, Suresh [in: Proceedings of the 2018 IEEE Symposium Series on Computational Intelligence (SSCI 2018)]In swarm robotics, a challenging task is to let the decentralized acting agents make a joint decision, when the individual robots of the swarm only have partial knowledge of the search space. In this paper, we propose a new nature-inspired method for decision-making in the case of a best-of-n selection, investigating the democracy behavior of honeybees and implementing it in swarm robots. The feasibility of our model is tested using a swarm consisting of real hardware robots, the so-called Kilobots. It is shown that our proposed democratic model proves to be resistant to malicious manipulation in the consensus-finding process. Thus, the democracy behavior of honeybees implemented in swarm robots robustly finds the best-of-n selection.04B - Beitrag Konferenzschrift
- PublikationOptimal learning rate and neighborhood radius of Kohonen's self-organizing map for solving the travelling salesman problem(2018) Mersiovsky, Tabea; Thekkottil, Abhilash; Hanne, Thomas; Dornberger, Rolf [in: Proceedings of the 2nd International Conference on Intelligent Systems, Metaheuristics & Swarm Intelligence]The Travelling Salesman Problem (TSP) is one of the well-studied classic combinatorial optimization problems and proved to be a non-deterministic polynomial-time (NP) hard problem. Kohonen's self-organizing map (SOM) is a type of artificial neural network, which can be applied on the TSP. The purpose of the algorithm is to adapt a special network to a set of unorganized and unlabeled data so that it can be used for clustering and simple classification tasks. In this paper, we study the effect of changing the parameters in the SOM algorithm to solve the TSP. The focus of the parameter investigation lies on the influence of changes in the SOM learning rate and neighborhood radius as well as on the number of iterations in TSP problems with varying number of cities. Thus, the investigation is based on various problem instances as well as on different parameter settings of the SOM, which are compared with each other and discussed. The results are additionally compared with the nature inspired ant colony optimization (ACO) algorithm. As a result, it is proved that with the right parameter setting the SOM generated result is improved and that it is superior to the ACO algorithm.04B - Beitrag Konferenzschrift
- PublikationA Novel Backup Path Planning Approach with ACO(08/2017) Meier, Danni; Tullumi, Ilir; Stauffer, Yannick; Dornberger, Rolf; Hanne, Thomas [in: 5th International Symposium on Computational and Business Intelligence (ISCBI)]04B - Beitrag Konferenzschrift
- PublikationFacility Layout Planning Using Fuzzy Closeness Computation and a Genetic Algorithm(09.12.2015) Menon, Dilip; Zwimpfer, Cédric; Hanne, Thomas; Dornberger, Rolf [in: 3rd International Symposium on Computational and Business Intelligence (ISCBI 2015)]04B - Beitrag Konferenzschrift
- PublikationAnalysis of Chaotic Maps Applied to Kohonen Self-organizing Maps for the Traveling Salesman Problem(05/2015) Stauffer, Michael; Ryter, Remo; Hanne, Thomas; Dornberger, Rolf [in: Proceedings of the annual IEEE Congress on Evolutionary Computation (IEEE CEC 2015)]04B - Beitrag Konferenzschrift
- PublikationEffects of weight initialization in a feedforward neural network for classification using a modified genetic algorithm(IEEE, 2015) Nienhold, Dino; Schwab, Roland; Dornberger, Rolf; Hanne, Thomas [in: 2015 3rd International Symposium on Computational and Business Intelligence. Proceedings]04B - Beitrag Konferenzschrift
- PublikationGenetic algorithm with embedded Ikeda map applied on an order picking problem in a multi-aisle warehouse(09.12.2014) Stauffer, Michael; Ryter, Remo; Davendra, Donald; Dornberger, Rolf; Hanne, Thomas04B - Beitrag Konferenzschrift