Accurate localization for autonomous vehicle operations is essential in dense urban areas. In order to ensure safety, positioning algorithms should implement fault detection and fallback strategies. While many strategies stop the vehicle once a failure is detected, in this work a new framework is proposed that includes an improved reconfiguration module to evaluate the failure scenario and offer alternative positioning strategies, allowing continued driving in degraded mode until a critical failure is detected. Furthermore, as many failures in sensors can be temporary, such as GPS signal interruption, the proposed approach allows the return to a non-fault state while resetting the alternative algorithms used in the temporary failure scenario. The proposed localization framework is validated in a series of experiments carried out in a simulation environment. Results demonstrate proper localization for the driving task even in the presence of sensor failure, only stopping the vehicle when a fully degraded state is achieved. Moreover, reconfiguration strategies have proven to consistently reset the accumulated drift of the alternative positioning algorithms, improving the overall performance and bounding the mean error.
El posicionamiento por GPS en zonas urbanas densamente pobladas puede ser un reto, principalmente debido al bloqueo de señales por edificios o túneles. Es por ello que los vehículos autónomos necesitan implementar alternativas para estas situaciones mediante una estructura de localización tolerante a fallos. Este es un área de gran interés en la que predominan el uso de técnicas de duplicación-comparación en combinación con las belief function, además de técnicas de localización alternativas. Este trabajo propone una estructura de localización para zonas urbanas densamente pobladas que incluye tanto un algoritmo robusto de detección de errores, capaz de evaluar el rango de confianza de cada estimación, como una precisa técnica de localización alternativa basada en un algoritmo de map matching de bajo coste computacional. La validación en un entorno simulado ha verificado la funcionalidad de la propuesta.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.