Swarm cognition on off-road autonomous robots

Abstract

This paper contributes with the first validation of swarm cognition as a useful framework for the design of autonomous robots controllers. The proposed model is built upon the authors' previous work validated on a simulated robot performing local navigation on a 2-D deterministic world. Based on the ant foraging metaphor and motivated by the multiple covert attention hypothesis, the model consists of a set of simple virtual agents inhabiting the robot's visual input, searching in a collectively coordinated way for obstacles. Parsimonious and accurate visual attention, operating on a by-need basis, is attained by making the activity of these agents modulated by the robot's action selection process. A by-product of the system is the maintenance of active, parallel and sparse spatial working memories. In short, the model exhibits the self-organisation of a relevant set of features composing a cognitive system. To show its robustness, the model is extended in this paper to handle the challenges of physical off-road robots equipped with noisy stereoscopic vision sensors. Furthermore, an extensive aggregate of biological arguments sustaining the model is provided. Experimental results show the ability of the model to robustly control the robot on a local navigation task, with less than 1% of the robot's visual input being analysed. Hence, with this system the computational cost of perception is considerably reduced, thus fostering robot miniaturisation and energetic efficiency. This confirms the advantages of using a swarm-based system, operating in an intricate way with action selection, to judiciously Swarm Intell (2011) 5: 45-72 control visual attention and maintain sparse spatial memories, constituting a basic form of swarm cognition.

On the role of stigmergy in cognition

“…To close the gap between swarm cognition and individual cognitive behaviour, Santana and Correia Santana and Correia (2010) and (Santana and Correia, 2011) studied how the stigmergic behaviour displayed by foraging army ants could be employed to implement robot behaviour in natural environments. The study encompassed the development of a control system composed of a set of simple virtual agents inhabiting the robot's visual input, called p-ants.…”

On Exploiting Haptic Cues for Self-Supervised Learning of Depth-Based Robot Navigation Affordances

“…Typically, the volumetric signature of obstacles is used for their detection from range data acquired by either laser scanners [8,42,39,24] or binocular vision systems [22,30,34,32]. Monocular appearance cues are also useful when exploiting known structures from the environment, such as the existence of paths to be followed [33,28].…”

On Collaborative Aerial and Surface Robots for Environmental Monitoring of Water Bodies

“…For this purpose we intend to adapt some work on all-terrain obstacle detection [15] [16] to the domain in question. An interesting point of this work is the use of visual attention parallel mechanisms, which we have been shown that, if operating in an intricate way with obstacle avoidance, the amount of processing can be considerably reduced [17], and as a consequence, the computational requirements as well. A key aspect of obstacle avoidance in aquatic environments, yet to be solved, is to filter out false positives induced by waves and large ripples in the water.…”