Guzzi, Jerome and Giusti, Alessandro and Gambardella, Luca Maria and Di Caro, Gianni (2012) Bioinspired obstacle avoidance algorithms for robot swarms. In: Proceedings of the 7th International Conference on Bio-Inspired Models of Network, Information, and Computing Systems (BIONETICS) International Conference on Bio-Inspired Models of Network, Information, and Computing Systems, 10 December 2012 - 12 December 2012, Lugano. (In Press)
Text
main.pdf - Published Version Download (3MB) |
Abstract
Recent work in socio-biological sciences have introduced simple heuristics that accurately explain the behavior of pedestrians navigating in an environment while avoiding mutual collisions. We have adapted and implemented such heuristics for distributed obstacle avoidance in robot swarms, with the goal of obtaining human-like navigation behaviors which would be perceived as friendly by humans sharing the same spaces. In this context, we study the effects of using different sensing modalities and robot types, and introduce robot's emotional states, which allows us to modulate system's group behavior. Experimental results are provided for both real and simulated robots. The extensive quantitative simulations show the macroscopic behavior of the system in various scenarios, where we observe emergent collective behaviors -- some of which are similar to those observed in human crowds.
Item Type: | Article in conference proceedings or Presentation at a conference (Paper) |
---|---|
Additional Information: | To be published |
Subjects: | Computer sciences > Artificial intelligence |
Department/unit: | Dipartimento tecnologie innovative > Istituto Dalle Molle di studi sull’intelligenza artificiale USI-SUPSI |
Depositing User: | Jerome Guzzi |
Date Deposited: | 26 Mar 2014 07:51 |
Last Modified: | 26 Mar 2014 07:51 |
URI: | http://repository.supsi.ch/id/eprint/4635 |
Actions (login required)
View Item |