Animals for surviving have developed cognitive abilities allowing them an abstract representation of the environment.
This internal representation (IR) may contain a huge amount of information concerning the evolution and interactions of
the animal and its surroundings. The temporal information is needed for IRs of dynamic environments and is one of the
most subtle points in its implementation as the information needed to generate the IR may eventually increase
dramatically. Some recent studies have proposed the compaction of the spatiotemporal information into only space,
leading to a stable structure suitable to be the base for complex cognitive processes in what has been called Compact
Internal Representation (CIR). The Compact Internal Representation is especially suited to be implemented in
autonomous robots as it provides global strategies for the interaction with real environments. This paper describes an
FPGA implementation of a Causal Neural Network based on a modified FitzHugh-Nagumo neuron to generate a
Compact Internal Representation of dynamic environments for roving robots, developed under the framework of SPARK
and SPARK II European project, to avoid dynamic and static obstacles.
Animals for surviving have developed cognitive abilities allowing them an abstract
representation of the environment. This Internal Representation (IR) could contain a huge
amount of information concerning the evolution and interactions of the elements in their
surroundings. The complexity of this information should be enough to ensure the maximum
fidelity in the representation of those aspects of the environment critical for the agent, but not so
high to prevent the management of the IR in terms of neural processes, i.e. storing, retrieving,
etc. One of the most subtle points is the inclusion of temporal information, necessary in IRs of
dynamic environments. This temporal information basically introduces the environmental
information for each moment, so the information required to generate the IR would eventually
be increased dramatically. The inclusion of this temporal information in biological neural
processes remains an open question. In this work we propose a new IR, the Compact Internal
Representation (CIR), based on the compaction of spatiotemporal information into only space,
leading to a stable structure (with no temporal dimension) suitable to be the base for complex
cognitive processes, as memory or learning. The Compact Internal Representation is especially
appropriate for be implemented in autonomous robots because it provides global strategies for
the interaction with real environments (roving robots, manipulators, etc.). This paper presents
the mathematical basis of CIR hardware implementation in the context of navigation in dynamic
environments. The aim of such implementation is the obtaining of free-collision trajectories
under the requirements of an optimal performance by means of a fast and accurate process.
Access to the requested content is limited to institutions that have purchased or subscribe to SPIE eBooks.
You are receiving this notice because your organization may not have SPIE eBooks access.*
*Shibboleth/Open Athens users─please
sign in
to access your institution's subscriptions.
To obtain this item, you may purchase the complete book in print or electronic format on
SPIE.org.
INSTITUTIONAL Select your institution to access the SPIE Digital Library.
PERSONAL Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.