Swarm Foraging Under Communication and Vision Uncertainties

Obute, Simon O.; Kilby, Philip; Dogar, Mehmet R.; Boyle, Jordan H.

doi:10.1109/tase.2022.3164044

Cited by 6 publications

(4 citation statements)

References 32 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The Boltzmann sampler gives the maximal entropy distribution of probabilities, which can be interpreted as the distribution of least assumption. Additionally, these themes of control should also make the softmax function an attractive option for a task allocation algorithm for swarm robotics, which already rely heavily on social insect inspired Hill functions (Ducatelle et al, 2010; Kanakia et al, 2016; Wu et al, 2018; Jiang et al, 2020; Obute et al, 2022).…”

Section: Discussionmentioning

confidence: 99%

Generalizing the response and satisfaction threshold models for multiple task types: A maximal entropy approach

Lynch,

Pavlic

2024

Preprint

View full text Add to dashboard Cite

Response threshold models are often used to test hypotheses about division of labor in social-insect colonies. Each worker's probability to engage in a task rapidly increases when a cue associated with task demand crosses some response threshold. Threshold variability across workers generates an emergent division of labor that is consistent over time and flexibly adaptive to increasing demands, which allows for testable predictions about the shape of hypothetical response-threshold distributions. Although there are myriad different task types in a social-insect colony, the classical response-threshold model is built to understand variability in response to a single type of task. As such, it does not immediately allow for testing predictions about how different workers prioritize different task types or how demand for some tasks interferes with responding to demand for others. To rectify this, we propose a multi-task generalization that degenerates into the standard model for a single task. We replace the classical Hill response probability with a model that draws worker choices from a Boltzmann distribution, which is an approach inspired by multi-class machine learning.

show abstract

Section: Discussionmentioning

confidence: 99%

Generalizing the response and satisfaction threshold models for multiple task types: A maximal entropy approach

Lynch,

Pavlic

2024

Preprint

View full text Add to dashboard Cite

show abstract

“…Discrete-time and continuous time random walks. Random walks (RW) are related to a stochastic process used to study the neuronal firing of the brain, or functional brain networks [125][126][127][128], movement and food hunt strategy of animals or humans [129][130][131][132][133][134][135][136], and technological systems such as a swarm of robots [137][138][139][140][141]. Depending on the structure of waiting time for hopping from one point to another, RW can be categorized as discrete-time (DT) RW or continuous time (CT) RW.…”

Section: Random Walksmentioning

confidence: 99%

Signal propagation in complex networks

et al. 2023

Physics Reports

141

View full text Add to dashboard Cite

“…The evolution of multimodal sensing and communication technologies has significantly bolstered robots' environmental perception and processing abilities. Studies [25][26][27][28][29][30][31] have highlighted the integration of diverse sensing methods to enhance robots' environmental perception and decision-making capabilities, albeit stability and accuracy in complex environments still require improvement. Moreover, advancements in collective intelligence and collaboration technologies [32][33][34][35][36][37][38] empower robotic swarms to coordinate and execute tasks efficiently, though coordination and robustness in large-scale, dynamic environments remain challenging.…”

Section: Introductionmentioning

confidence: 99%

Self-Configurable Centipede-Inspired Rescue Robot

Hou,

Xue,

Liang

et al. 2024

Applied Sciences

View full text Add to dashboard Cite

Drawing from the characteristics of centipedes, such as their low center of gravity, high stability in movement, adaptability to complex terrains, and ability to continue moving even after losing a limb, this paper designs a self-reconfigurable centipede-type rescue robot with relatively high stability while moving. The robot’s body can lift and traverse higher obstacles, and its multi-segmented structure enables self-disconnection and reconstruction for docking. Moreover, the proposed robot is adept at navigating diverse terrains and surmounting obstacles, equipped with a camera sensor facilitating life recognition, terrain surveying, scene understanding, and obstacle avoidance. Its capabilities prove advantageous for achieving challenging ground rescue missions. Motion stability tests, conducted across various terrains, showcase the robot’s ability to maintain a consistent movement path in rugged environments. Operating with a leg lift height of 0.02 m, the robot achieves a speed of 0.09 m per second. In simulated damaged conditions, the robot demonstrates the capacity to disconnect and reconnect its limbs swiftly, restoring movement capabilities within a single second. During environmental perception tasks, the robot processes and analyzes environmental data in real time at a rate of approximately 15 frames per second, with an 80% confidence level. With an F1 score exceeding 93% and an average precision rate surpassing 98%, the robot showcases its reliability and efficiency.

show abstract

Swarm Foraging Under Communication and Vision Uncertainties

Cited by 6 publications

References 32 publications

Generalizing the response and satisfaction threshold models for multiple task types: A maximal entropy approach

Generalizing the response and satisfaction threshold models for multiple task types: A maximal entropy approach

Signal propagation in complex networks

Self-Configurable Centipede-Inspired Rescue Robot

Contact Info

Product

Resources

About