A parsimonious model for locomotor in virtual agents based on dynamical coupling with the environment. (4th October 2016)

• Record Type: Journal Article
• Authors: Zaldivar Pino, Angel; Gonzalez Bedia, Manuel; Seron Arbeloa, Francisco José
• Is Part Of: Computer animation and virtual worlds. Volume 28:Number 6(2017)
• Page Start: n/a
• Page End: n/a
• Publication Date: 2016-10-04
• Subjects: artificial evolution -- dynamical modeling -- locomotor behavior -- oscillators networks -- virtual agents; Computer animation -- Periodicals; Visualization -- Periodicals; 006.6
• DOI: 10.1002/cav.1733
• Languages: English
• ISSNs: 1546-4261

Abstract

Abstract: In the domain of virtual agents modeling, computationalist approaches tend to predominate. The lack of plausibility of the rules in nature provides models with a low capacity to generalize and a very limited insight into behavioral phenomena. An alternative view is that behavior could emerge as a whole from the basic principles of non‐linear dynamics that underlie such behavior in the environment. This paper presents a dynamic agent endowed with a sensing device, a controller and actuators to interact with the environment. The control architecture is based on ordinary differential equations with the function of modulating the stimulus signals to action signals under a sensory‐motor flow. The parameter values are defined in an evolutionary process depending on the task to be performed. A series of experiments are presented to illustrate certain qualities of our model such as the adaptability to change, a highly intuitive and flexible design methodology, and a high degree of individual autonomy, among others. We think this kind of modeling is useful in the animation world for modeling flocks, crowds, and swarms as a valid alternative to other less parsimonious techniques. Abstract : In this paper, the main proposition assumes that the agent does not need a full model or to make inferences before taking actions; rather, the information necessary for any action can be derived from the environment with simple computations and very little internal state. The agents are endowed with a sensing device, an oscillator network as controller and actuators to interact with the environment. The parameter values are defined in an evolutionary process depending on the task to be performed.