Alexandros Giagkos

BeeIP - A Swarm Intelligence based routing for wireless ad hoc networks

Agent-based routing in wireless ad hoc networks defines a set of rules that all the participating nodes follow. Routing becomes a collaboration between nodes, reducing computational and resource costs. Swarm Intelligence uses agent-like entities from insect societies as a metaphor to solve the routing problem. Certain insects exchange information about their activities and the environment in which they operate in order to complete their tasks in an adaptive, efficient and scalable manner. This paper examines Swarm Intelligence based routing protocols, along with a newly proposed bee-inspired routing protocol for providing multi-path routing in wireless ad hoc networks of mobile nodes. Simulation results indicate that applying Swarm Intelligence offers a significant level of adaptability and efficiency that, under several network conditions, allow the protocol to outperform traditional approaches.

BeeIP: bee-inspired protocol for routing in mobile ad-hoc networks

We introduce a new bee-inspired routing protocol for mobile ad hoc networks. Emphasis is given to the ability of bees to evaluate paths by considering several quality factors. In order to achieve similar behaviour in the networking environment, BeeIP is using cross-layering. Fetching parameters from the lower PHY and MAC layers to the core of the protocol, offers the artificial bees the ability to make predictions about the links future performance. Our approach is compared with two well-known routing protocols in the area, the destination sequenced distance-vector protocol (DSDV), and the adaptive on-demand distance vector protocol (AODV). The outcome shows that BeeIP achieves higher data delivery rates and less control overhead than DSDV, and slightly better results compared to AODV, initializing less route discovery processes.

Swarm intelligence to wireless ad hoc networks: adaptive honeybee foraging during communication sessions

With no fixed infrastructure, discovering new ways of managing high mobility and limited resources to produce optimized routing in wireless ad hoc networks is the key objective of active research. Adaptive foraging principles found in insects have attracted the research community to develop new approaches that benefit from the simplicity and collaborative behaviours of these natural multi-agent systems. This paper discusses both traditional and swarm-intelligence-based routing and investigates the extent to which a new bee-inspired approach, termed BeeIP, results in adaptive, robust and optimized routing in networks of high mobility. BeeIP is directly and quantitatively compared with the state-of-the-art protocols using a variety of performance metrics. The results show that it outperforms the others by keeping low and balanced end-to-end packet delay under stressful network conditions, such as high traffic and mobility rates. In addition, BeeIP is indirectly and qualitatively compared with the first bee-inspired routing protocol, BeeAdHoc. The resulting discussion indicates that the proposed design can offer better packet delivery ratio and use smaller control packets, thus less overhead, by utilizing an enhanced adaptive path monitoring mechanism inspired by honeybee foraging.

Babybot challenge: Motor skills

In 1984, von Hofsten performed a longitudinal study of early reaching in infants between the ages of 1 week and 19 weeks. This paper proposes a possible model using excitation of various subsystems to reproduce the longitudinal study. The model is then implemented and tested on an iCub humanoid robot, and the results compared to the original study. The resulting model shares interesting similarities to the data presented by von Hofsten, in particular a slight dip in the quantity of reaching. However, the dip is shifted along by a few weeks, and the analysis of hand behaviour is inconclusive based on the data recorded.

Perception of Localized Features During Robotic Sensorimotor Development

The understanding of concepts related to objects are developed over a long period of time in infancy. This paper investigates how physical constraints and changes in visual perception impact on both sensorimotor development for gaze control, as well as the perception of features of interesting regions in the scene. Through a progressive series of developmental stages, simulating ten months of infant development, this paper examines feature perception toward recognition of localized regions in the environment. Results of two experiments, conducted using the iCub humanoid robot, indicate that by following the proposed approach a cognitive agent is capable of scaffolding sensorimotor experiences to allow gradual exploration of the surroundings and local region recognition, in terms of low-level feature similarities. In addition, this paper reports the emergence of vision-related phenomena that match human behaviors found in the developmental psychology literature.

Evolutionary coordination system for fixed-wing communications unmanned aerial vehicles

A system to coordinate the movement of a group of unmanned aerial vehicles that provide a network backbone over mobile ground-based vehicles with communication needs is presented. Using evolutionary algorithms, the system evolves flying manoeuvres that position the aerial vehicles by fulfilling two key requirements; i) they maximise net coverage and ii) they minimise the power consumption. Experimental results show that the proposed coordination system is able to offer a desirable level of adaptability with respect to the objectives set, providing useful feedback for future research directions.

Towards learning strategies and exploration patterns for feature perception

During infancy, infants spend a lot of time visually exploring the scene around them. Over the first year of life, the level of detail that can be perceived visually increases significantly. In this study, the ability to perceive areas of interest w.r.t. human developmental change in vision, specifically acuity and field of view over the first year of life, is investigated. Two scenarios, namely learning through a series of developmental changes and learning without any constraints, shed light on how a humanoid robot scaffolds learning of interesting areas in the scene through different emergent exploratory behaviours. Divergence/convergence in features is reported, demonstrating a potential to be used at a higher level of understanding. Staged strategies with early sensory constraints and exploratory behaviour based on “similarity searches” improve the quality of acquired features and may be used as a mechanism for better on-line learning of objects knowledge.

From Animals to Animats 14

The Animals to Animats Conference brings together researchers from ethology, psychology, ecology, artificial intelligence, artificial life, robotics, engineering, and related fields to further understanding of the behaviors and underlying mechanisms that allow natural and synthetic agents (animats) to adapt and survive in uncertain environments. The work presented focuses on well-defined models--robotic, computer-simulation, and mathematical--that help to characterize and compare various organizational principles or architectures underlying adaptive behavior in both natural animals and animats.

Developing Hierarchical Schemas and Building Schema Chains Through Practice Play Behavior

Examining the different stages of learning through play in humans during early life has been a topic of interest for various scholars. Play evolves from practice to symbolic and then later to play with rules. During practice play, infants go through a process of developing knowledge while they interact with the surrounding objects, facilitating the creation of new knowledge about objects and object related behaviors. Such knowledge is used to form schemas in which the manifestation of sensorimotor experiences is captured. Through subsequent play, certain schemas are further combined to generate chains able to achieve behaviors that require multiple steps. The chains of schemas demonstrate the formation of higher level actions in a hierarchical structure. In this work we present a schema-based play generator for artificial agents, termed Dev-PSchema. With the help of experiments in a simulated environment and with the iCub robot, we demonstrate the ability of our system to create schemas of sensorimotor experiences from playful interaction with the environment. We show the creation of schema chains consisting of a sequence of actions that allow an agent to autonomously perform complex tasks. In addition to demonstrating the ability to learn through playful behavior, we demonstrate the capability of Dev-PSchema to simulate different infants with different preferences toward novel vs. familiar objects.

Generalising Predictable Object Movements Through Experience Using Schemas

In humans, repeated exposure to the effects of events can lead to anticipation of these effects. This behaviour has been observed in infants from as young as 3 months old. During infant experiments, the infants have been observed to predict either by pre-saccadic movements or reach actions according to the expected future outcome of the event. Event anticipation or prediction is necessary for such behaviours. In this paper we demonstrate prediction of object motion events using the adaptive learning tool Dev-PSchema. Results shows that the system is able to predict the linear motion outcome of the visual event using generalised schemas.