Adaptation capability of cognitive map improves behaviors of social robots

Abstract

In this paper, we study the impact of the cognitive map's adaptation in the context of multi-robot system. This map governs the emergence of non-trivial behaviors and structures at both individual and social levels. In particular, we show that adding a simple imitation and deposit behavior allows the cognitive robots to adapt themselves in unknown environment to solve different navigation tasks. We show that in our architecture the individual discoveries in each robot (i.e., goals) can have an effect at the population level, which induce then a new learning at the individual level and reciprocally, from the individual to the population level. We performed a series of experimentations with robots and simulated agents to validate our system.

Learning by Imitation for the Improvement of the Individual and the Social Behaviors of Self-organized Autonomous Agents

“…The results show that adding an imitation capability can dramatically enhance the survival rate of the population from 45,66% (without imitation behavior) to 60,64% (with imitation). Indeed, coupling imitation behavior with the cognitive map allows agents to discover and to learn the position of the resources in the environment more rapidly We have also validated the positive feedback of the imitation strategy on a minimal robotics setup [13] based on the same bio-inspired architecture which has been validated in real robots in [14] . We conducted 20 experiments (this number is determined by the statistical Fisher test) composed of an imitator robot IR (having an imitation behavior) and with a leader robot LR (that has already learned the position of the goals G1 and G2 with a threshold of vigilance to learn new places equal to 0.65 and a duration of learning equal to 30 minutes).…”

Evaluation of Emergent Structures in a ”Cognitive” Multi-Agent System based on On-line Building and Learning of a Cognitive Map

“…The results obtained confirm the performance of our emergent behavior based on cognitive processes which allow us to have adequate solutions that approximate the linear programming solution. To study the limits of emergent structures in real world, we started to validate the adaptive capability of the cognitive map in a real multi-robot system (Chatty et al, 2012) and now we are trying to add the deposit system in the multi-robot system.…”

“…After having explored the environment, the agents are able to predict, in each position the locations directly reachable. This model has been used in Cognitive Multi-Robot System navigation tasks (Chatty et al, 2012) in which where the agents were able to build their cognitive maps and learn how to move towards various goals in an unknown environment.…”

Effect of low level imitation strategy on an autonomous Multi-Robot System using on-line learning for cognitive map building

“…The environment is composed of 2 sources, 2 obstacles and 2 identical robots (robulab 10 from robosoft) that are able to avoid the stable and dynamic obstacles, to navigate, to learn and to construct their on-line own cognitive map in a unknown environment (with a threshold of vigilance to learn news places equal to 0.65 and a duration of learning equal to 30 minutes). This model has been used in Cognitive multi-robot system navigation tasks [23] where the robots were able to build their cognitive map on-line and learn how to move towards various goals in unknown environment.…”

“…Our Cognitive robots are also able to select the shortest path [23] in order to reach their targets: when discovering a source (food, nest or water), the motivation associated with it (thirst, hunger or stress) is associated with the cognitive map at the location where it was found. This motivation then spreads to the graph, indicating the shortest path to reach the source from any known location.…”