A Novel Online Adaptation Mechanism in Artificial Systems Provides Phenotypic Plasticity

Braccini, Michele; Roli, Andrea; Kauffman, Stuart

doi:10.1007/978-3-031-23929-8_12

Cited by 4 publications

(2 citation statements)

References 34 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Critical RBNs have proven capable of properly reproducing many biological processes [ 26 , 27 , 28 , 29 , 30 , 31 , 32 , 33 , 34 ] and have proven efficient when used as controllers of artificial agents, such as robots [ 27 ].…”

Section: The Modelmentioning

confidence: 99%

See 1 more Smart Citation

Sensory–Motor Loop Adaptation in Boolean Network Robots

Braccini,

Gardinazzi,

Roli

et al. 2024

Sensors

Self Cite

View full text Add to dashboard Cite

Recent technological advances have made it possible to produce tiny robots equipped with simple sensors and effectors. Micro-robots are particularly suitable for scenarios such as exploration of hostile environments, and emergency intervention, e.g., in areas subject to earthquakes or fires. A crucial desirable feature of such a robot is the capability of adapting to the specific environment in which it has to operate. Given the limited computational capabilities of a micro-robot, this property cannot be achieved by complicated software but it rather should come from the flexibility of simple control mechanisms, such as the sensory–motor loop. In this work, we explore the possibility of equipping simple robots controlled by Boolean networks with the capability of modulating their sensory–motor loop such that their behavior adapts to the incumbent environmental conditions. This study builds upon the cybernetic concept of homeostasis, which is the property of maintaining essential parameters inside vital ranges, and analyzes the performance of adaptive mechanisms intervening in the sensory–motor loop. In particular, we focus on the possibility of maneuvering the robot’s effectors such that both their connections to network nodes and environmental features can be adapted. As the actions the robot takes have a feedback effect to its sensors mediated by the environment, this mechanism makes it possible to tune the sensory–motor loop, which, in turn, determines the robot’s behavior. We study this general setting in simulation and assess to what extent this mechanism can sustain the homeostasis of the robot. Our results show that controllers made of random Boolean networks in critical and chaotic regimes can be tuned such that their homeostasis in different environments is kept. This outcome is a step towards the design and deployment of controllers for micro-robots able to adapt to different environments.

show abstract

Section: The Modelmentioning

confidence: 99%

“…The basic steps defining adaptation strategy 1 and 3 are actually the same as those used in the online adaptation mechanism proposed in [ 27 ]. See Figure 3 .…”

Section: The Modelmentioning

confidence: 99%