Abstract
To provide a platform to enable the study of simulated olfactory circuitry in context, we have integrated a simulated neural olfactorimotor system with a virtual world which simulates both computational fluid dynamics as well as a robotic agent capable of exploring the simulated plumes. A number of the elements which we developed for this purpose have not, to our knowledge, been previously assembled into an integrated system, including: control of a simulated agent by a neural olfactorimotor system; continuous interaction between the simulated robot and the virtual plume; the inclusion of multiple distinct odorant plumes and background odor; the systematic use of artificial evolution driven by olfactorimotor performance (e.g., time to locate a plume source) to specify parameter values; the incorporation of the realities of an imperfect physical robot using a hybrid model where a physical robot encounters a simulated plume. We close by describing ongoing work toward engineering a high dimensional, reversible, low power electronic olfactory sensor which will allow olfactorimotor neural circuitry evolved in the virtual world to control an autonomous olfactory robot in the physical world. The platform described here is intended to better test theories of olfactory circuit function, as well as provide robust odor source localization in realistic environments.
Highlights
Brain sensory and control systems evolved to enable action which leads to organism survival
In all but one case, aside from the present study, the sensorimotor control system was not neural, though a variety motor strategies observed in nature were implemented in non-neural control systems
We describe the development of a new class of high dimensional, rapidly reversible, low power electronic artificial olfactory sensor which, when available, could be the front end for a fully autonomous neural olfactory robotic, with a neural control system co-evolved in virtual and physical environments. This olfactory sensor platform will be made available to the research community to both explore the development of working olfactory robotic devices and to enable the study of highly neural simulated olfactory circuitry in the sensorimotor context for which it evolved
Summary
Brain sensory and control systems evolved to enable action which leads to organism survival. With respect to the control algorithms much work has been motivated by the apparent search strategies adopted by animals, and over the last 15 years a compelling body of work on robotic olfactorimotor control has developed (reviewed in Kowadlo and Russell, 2008; McGill and Taylor, 2011) Most of these studies have incorporated a more traditional robotic sensorimotor controller, and there has far been little work embedding a neural olfactory sensorimotor system in a simulated (or real) olfactory environment. We argue for the use of artificial evolution of the parameters controlling the simulated brain, and describe how the virtual closed world can be linked to a physical robot, both before and after the development of a physical olfactory sensor with the high dimensionality and rapid reversibility needed to enable plume exploration, so that neural olfactorimotor systems can be evolved in virtual and real worlds in tandem. Describing the components we have chosen to assemble for this integrated system, and addressing some of the constraints encountered and the trade-offs entailed, is the purpose of the present work
Sign-in/Register to view highlights & summary Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
