Resource-Optimal Planning For An Autonomous Planetary Vehicle - Computer Science > Artificial IntelligenceReportar como inadecuado




Resource-Optimal Planning For An Autonomous Planetary Vehicle - Computer Science > Artificial Intelligence - Descarga este documento en PDF. Documentación en PDF para descargar gratis. Disponible también para leer online.

Abstract: Autonomous planetary vehicles, also known as rovers, are small autonomousvehicles equipped with a variety of sensors used to perform exploration andexperiments on a planet-s surface. Rovers work in a partially unknownenvironment, with narrow energy-time-movement constraints and, typically, smallcomputational resources that limit the complexity of on-line planning andscheduling, thus they represent a great challenge in the field of autonomousvehicles. Indeed, formal models for such vehicles usually involve hybridsystems with nonlinear dynamics, which are difficult to handle by most of thecurrent planning algorithms and tools. Therefore, when offline planning of thevehicle activities is required, for example for rovers that operate without acontinuous Earth supervision, such planning is often performed on simplifiedmodels that are not completely realistic. In this paper we show how theUPMurphi model checking based planning tool can be used to generateresource-optimal plans to control the engine of an autonomous planetaryvehicle, working directly on its hybrid model and taking into account severalsafety constraints, thus achieving very accurate results.



Autor: Giuseppe Della Penna 1, Benedetto Intrigila 2, Daniele Magazzeni 3, Fabio Mercorio 1 1 University of L'Aquila, Italy, 2 Univ

Fuente: https://arxiv.org/







Documentos relacionados