Use and advances in the Active Grammar-based Modeling architecture

Luis Jesús Manso Fernández-Argüelles

Abstract

The choice of using a robotic architecture and one of its possible implementations is one of the most crucial design decisions when developing robots.
Such decision affects the whole development process, the limitations of the robot, and changing minds can be prohibitively time consuming.

This paper presents the redesign and the most relevant implementation issues of the Active Grammar-based Modeling architecture (AGM), as well as the latest developments thereof. AGM is flexible, modular and designed with computation distribution and scalability in mind. In addition to a continuous refactoring of the API library and planner, the most relevant improvements are an enhanced mission specification syntax, support for representations combining symbolic and metric properties, redesigned communication patterns, and extended middleware support.

A few use examples are presented to demonstrate successful application of the architecture and why some of its features were needed.


Keywords

Robotic architectures; Artificial intelligence

References


Luis Vicente Calderita Estévez. Deep State Representation: an unified internal representation for the robotics cognitive architecture CORTEX. PhD thesis, Universidad de Extremadura, 2016.

D. McDermott et al. PDDL: the planning domain definition language. Technical Report DCS TR 1165, Yale Center for Vision and Control, 1998.

L.J. Manso et al. RoboComp: a Tool-based Robotics Framework. In Simulation, Modeling and Programming for Autonomous Robots, pages 251–262. Springer, 2010. https://doi.org/10.1007/978-3-642-17319-6_25

E. Gat. On three-layer architectures. Artificial intelligence and mobile robots, pages 195–210, 1998.

Marco Antonio Gutierrez Giraldo. Progress in robocomp. Journal of Physical Agents, 7(1):38–47, 2013.

L.J. Manso. Perception as Stochastic Sampling on Dynamic Graph Spaces”, school=Escuela Politécnica de Cáceres, Universidad de Extremadura year=2013. PhD thesis.

L.J. Manso, P. Bustos, R. Alami, G. Milliez, and P. Núñez. Planning human-robot interaction tasks using graph models. In Proceedings of International Workshop on Recognition and Action for Scene Under-standing (REACTS 2015), pages 15–27, 2015.

L.J. Manso, P. Bustos, P. Bachiller, and P. Núñez. A perception-aware architecture for autonomous robots. International Journal of Advanced Robotic Systems, 12(174):13, 2015. https://doi.org/10.5772/61742

Jesús Martınez-Gómez, Rebeca Marfil, Luis V. Calderita, Juan P. Bandera, Luis J. Manso, Antonio Bandera, Adrián Romero-Garcés, and Pablo Bustos. Toward social cognition in robotics: Extracting and internalizing meaning from perception. In XV Workshop of Physical Agents (WAF 2014), León, Spain, pages 93–104, 2014.

Marvin Minsky. Society of mind. Simon and Schuster, 1988.

Adrián Romero-Garcés, Luis Vicente Calderita, Jesús Martı́nez-Gómez, Juan Pedro Bandera, Rebeca Marfil, Luis J. Manso, Pablo Bustos, and Antonio Bandera. The cognitive architecture of a robotic salesman. environment, 15(6):16, 2015.

Martin Theobald, Mauro Sozio, Fabian Suchanek, and Ndapandula Nakashole. Urdf: Efficient reasoning in uncertain rdf knowledge bases with soft and hard rules. 2010.




DOI: https://doi.org/10.14198/JoPha.2017.8.1.05