Belief State Planning for Autonomous Driving : Planning with Interaction, Uncertain Prediction and Uncertain Perception

Belief State Planning for Autonomous Driving Planning with Interaction, Uncertain Prediction and Uncertain Perception

This work presents a behavior planning algorithm for automated driving in urban environments with an uncertain and dynamic nature. The algorithm allows to consider the prediction uncertainty (e.g. different intentions), perception uncertainty (e.g. occlusions) as well as the uncertain interactive be...

Descripción completa

Detalles Bibliográficos
Otros Autores: Hubmann, Constantin (auth)
Formato: Libro electrónico
Idioma:Inglés
Publicado: Karlsruhe KIT Scientific Publishing 2021
Colección:Schriftenreihe / Institut für Mess- und Regelungstechnik, Karlsruher Institut für Technologie
Materias:
Mechanical engineering & materials
Autonomes Fahren
Entscheidungsfindung
Verhaltensgenerierung
Trajektorienplanung
Interaktion
Autonomous Driving
Decision Making
Behavior Planning
Trajectory Planning
Interactive Planning
Ver en Biblioteca Universitat Ramon Llull:https://discovery.url.edu/permalink/34CSUC_URL/1im36ta/alma991009654207006719
Descripción
Sumario:This work presents a behavior planning algorithm for automated driving in urban environments with an uncertain and dynamic nature. The algorithm allows to consider the prediction uncertainty (e.g. different intentions), perception uncertainty (e.g. occlusions) as well as the uncertain interactive behavior of the other agents explicitly. Simulating the most likely future scenarios allows to find an optimal policy online that enables non-conservative planning under uncertainty.
Descripción Física:1 electronic resource (180 p.)
Acceso:Open access

Ejemplares similares