A hierarchical training method of generating collective foraging behavior for a robotic swarm

Generating collective foraging behavior for robotic swarm using deep reinforcement learning

Artificial Life and Robotics ◽

10.1007/s10015-020-00642-2 ◽

2020 ◽

Vol 25 (4) ◽

pp. 588-595

Author(s):

Boyin Jin ◽

Yupeng Liang ◽

Ziyao Han ◽

Kazuhiro Ohkura

Keyword(s):

Reinforcement Learning ◽

Foraging Behavior ◽

Robotic Swarm ◽

Collective Foraging

Download Full-text

The physiology of forager hydration and variation among harvester ant (Pogonomyrmex barbatus) colonies in collective foraging behavior

Scientific Reports ◽

10.1038/s41598-019-41586-3 ◽

2019 ◽

Vol 9 (1) ◽

Cited By ~ 8

Author(s):

Daniel A. Friedman ◽

Michael J. Greene ◽

Deborah M. Gordon

Keyword(s):

Foraging Behavior ◽

Pogonomyrmex Barbatus ◽

Harvester Ant ◽

Collective Foraging

Download Full-text

A Multiscale Review of Behavioral Variation in Collective Foraging Behavior in Honey Bees

Insects ◽

10.3390/insects10110370 ◽

2019 ◽

Vol 10 (11) ◽

pp. 370 ◽

Cited By ~ 3

Author(s):

Natalie J. Lemanski ◽

Chelsea N. Cook ◽

Brian H. Smith ◽

Noa Pinter-Wollman

Keyword(s):

Individual Differences ◽

Foraging Behavior ◽

Collective Behavior ◽

Individual Variation ◽

Honey Bees ◽

Multiple Scales ◽

Model System ◽

Bee Foraging ◽

Collective Foraging ◽

The Impact

The emergence of collective behavior from local interactions is a widespread phenomenon in social groups. Previous models of collective behavior have largely overlooked the impact of variation among individuals within the group on collective dynamics. Honey bees (Apis mellifera) provide an excellent model system for exploring the role of individual differences in collective behavior due to their high levels of individual variation and experimental tractability. In this review, we explore the causes and consequences of individual variation in behavior for honey bee foraging across multiple scales of organization. We summarize what is currently known about the genetic, developmental, and neurophysiological causes of individual differences in learning and memory among honey bees, as well as the consequences of this variation for collective foraging behavior and colony fitness. We conclude with suggesting promising future directions for exploration of the genetic and physiological underpinnings of individual differences in behavior in this model system.

Download Full-text

Learning a Swarm Foraging Behavior with Microscopic Fuzzy Controllers Using Deep Reinforcement Learning

Applied Sciences ◽

10.3390/app11062856 ◽

2021 ◽

Vol 11 (6) ◽

pp. 2856

Author(s):

Fidel Aznar ◽

Mar Pujol ◽

Ramón Rizo

Keyword(s):

Reinforcement Learning ◽

Obstacle Avoidance ◽

Foraging Behavior ◽

Target Position ◽

Light Detection And Ranging ◽

Complex Task ◽

Training Phase ◽

Learning Techniques ◽

Robotic Swarm ◽

Foraging Task

This article presents a macroscopic swarm foraging behavior obtained using deep reinforcement learning. The selected behavior is a complex task in which a group of simple agents must be directed towards an object to move it to a target position without the use of special gripping mechanisms, using only their own bodies. Our system has been designed to use and combine basic fuzzy behaviors to control obstacle avoidance and the low-level rendezvous processes needed for the foraging task. We use a realistically modeled swarm based on differential robots equipped with light detection and ranging (LiDAR) sensors. It is important to highlight that the obtained macroscopic behavior, in contrast to that of end-to-end systems, combines existing microscopic tasks, which allows us to apply these learning techniques even with the dimensionality and complexity of the problem in a realistic robotic swarm system. The presented behavior is capable of correctly developing the macroscopic foraging task in a robust and scalable way, even in situations that have not been seen in the training phase. An exhaustive analysis of the obtained behavior is carried out, where both the movement of the swarm while performing the task and the swarm scalability are analyzed.

Download Full-text

Larval pheromones act as colony-wide regulators of collective foraging behavior in honeybees

Behavioral Ecology ◽

10.1093/beheco/ary090 ◽

2018 ◽

Vol 29 (5) ◽

pp. 1132-1141 ◽

Cited By ~ 3

Author(s):

R Ma ◽

G Villar ◽

C M Grozinger ◽

J Rangel

Keyword(s):

Foraging Behavior ◽

Collective Foraging

Download Full-text

Temporal and Spatial Foraging Behavior of the Larvae of the Fall WebwormHyphantria cunea

Psyche A Journal of Entomology ◽

10.1155/2015/359765 ◽

2015 ◽

Vol 2015 ◽

pp. 1-6

Author(s):

Terrence D. Fitzgerald

Keyword(s):

Foraging Behavior ◽

Laboratory Experiments ◽

Central Place ◽

Host Tree ◽

Simple System ◽

Hyphantria Cunea ◽

Feeding Sites ◽

Collective Foraging ◽

Temporal And Spatial

During their first three larval stadia, caterpillars ofHyphantria cunea(Lepidoptera: Arctiidae) are patch-restricted foragers, confining their activity to a web-nest they construct in the branches of the host tree. Activity recordings of eight field colonies made over 46 colony-days showed that the later instars become central place foragers, leaving their nests at dusk to feed at distant sites and then returning to their nests in the morning. Colonies maintained in the laboratory showed that same pattern of foraging. In Y-choice laboratory experiments, caterpillars were slow to abandon old, exhausted feeding sites in favor of new food finds. An average of approximately 40% of the caterpillars in five colonies still selected pathways leading to exhausted sites at the onset of foraging bouts over those leading to new sites after feeding exclusively at the new sites on each of the previous four days. On returning to their nests in the morning, approximately 23% of the caterpillars erred by selecting pathways that led them away from the nest rather than toward it and showed no improvement over the course of the study. The results of these Y-choice studies indicate that, compared to other previously studied species of social caterpillars, the webworm employs a relatively simple system of collective foraging.

Download Full-text