Bee Behaviour in Multi-agent Systems
In this paper we present a new, non-pheromone-based algorithm inspired by the behaviour of bees. The algorithm combines both recruitment and navigation strategies. We investigate whether this new algorithm outperforms pheromone-based algorithms, inspired
- PDF / 1,561,850 Bytes
- 12 Pages / 430 x 660 pts Page_size
- 118 Downloads / 171 Views
CoMo, Vrije Universiteit Brussel, Belgium MICC-IKAT, Universiteit Maastricht, Netherlands {nlemmens,anowe}@vub.ac.be, {steven.dejong,k.tuyls}@MICC.unimaas.nl 2
Abstract. In this paper we present a new, non-pheromone-based algorithm inspired by the behaviour of bees. The algorithm combines both recruitment and navigation strategies. We investigate whether this new algorithm outperforms pheromone-based algorithms, inspired by the behaviour of ants, in the task of foraging. From our experiments, we conclude that (i) the bee-inspired algorithm is significantly more efficient when finding and collecting food, i.e., it uses fewer iterations to complete the task; (ii) the bee-inspired algorithm is more scalable, i.e., it requires less computation time to complete the task, even though in small worlds, the ant-inspired algorithm is faster on a time-per-iteration measure; and finally, (iii) our current bee-inspired algorithm is less adaptive than ant-inspired algorithms.
1 Introduction In this paper we introduce a new, non-pheromone-based, algorithm inspired by the social behaviour of honeybees. The algorithm consists of two strategies. First, a recruitment strategy which is used to distribute knowledge to other members of the colony. More precisely, by ‘dancing’ inside the hive agents are able to directly communicate distance and direction towards a destination, in analogy to bees ‘dancing’ inside the hive [1]. Second, a navigation strategy which is used to efficiently navigate in an unknown world. For navigation, agents use a strategy named Path Integration (PI). This strategy is based on PI in bees with which they are able to compute their present location from their past trajectory continuously and, as a consequence, can return to their starting point by choosing the direct route rather than retracing their outbound trajectory [2,3]. Pheromone-based algorithms are inspired by the behaviour of ants. For an overview, we refer to [4]. In summary, ants deposit pheromone on the path they take during travel. Using this trail, they are able to navigate towards their nest or food. Ants employ an indirect recruitment strategy by accumulating pheromone trails. When a trail is strong enough, other ants are attracted to it and will follow this trail towards a destination. More precisely, the more ants follow a trail, the more that trail becomes attractive for being followed. This is known as an autocatalitic process. Short paths will eventually be preferred but it takes a certain amount of time before such pheromone trails emerge. K. Tuyls et al. (Eds.): Adaptive Agents and MAS III, LNAI 4865, pp. 145–156, 2008. c Springer-Verlag Berlin Heidelberg 2008
146
N. Lemmens et al.
Although ant and bee foraging strategies differ considerably, both species solve the foraging problem efficiently. In the field of Computer Science, researchers have become inspired by the behaviour of social insects, since the problems these insects cope with are similar to optimization problems humans wish to solve efficiently, for instance, the Shortes
Data Loading...
