RT Dissertation/Thesis
T1 Social navigation of autonomous robots in populated environments
A1 Pérez Higueras, Noé
K1 Robótica
K1 Robots móviles
K1 Interacción robots-humanos
K1 Algoritmos
AB Today, more and more mobile robots are coexisting with us in our daily lives.As a result, the behavior of robots that share space with humans in dynamicenvironments is a subject of intense investigation in robotics. Robots must re-spect human social conventions, guarantee the comfort of surrounding people,and maintain the legibility so that humans can understand the robot¿s intentions.Robots that move in humans¿ vicinity should navigate in a socially compliantway; this is called human-aware navigation. These social behaviors are not easyto frame in mathematical expressions. Consequently, motion planners with pre-programmed constraints and hard-coded functions can fail in acquiring properbehaviors related to human-awareness. All in all, it is easier to demonstratesocially acceptable behaviors than mathematically defining them. Therefore,learning these social behaviors from data seems a more principled approach.This thesis aims at endowing mobile robots with new social skills for au-tonomous navigation in spaces populated with humans. This work makes use oflearning from demonstration (LfD) approaches to solve the problem of human-aware navigation. Different techniques and algorithms are explored and devel-oped in order to transfer social navigation behaviors to a robot by using demon-strations of human experts performing the proposed tasks.The contributions of this thesis are in the field of Learning from Demonstra-tion applied to human-aware navigation tasks. First, a LfD technique based onInverse Reinforcement Learning (IRL) is employed to learn a policy for ¿social¿local motion planning. Then, a novel learning algorithm combining LfD conceptsand sampling-based path planners is presented. Finally, other novel approachescombining different LfD techniques, like deep learning among others, and pathplanners are investigated. The methods proposed are compared against state-of-the-art approaches and tested in different experiments with the real robotsemployed in the European projects FROG and TERESA.
YR 2018
FD 2018
LK http://hdl.handle.net/10433/6302
UL http://hdl.handle.net/10433/6302
LA en
NO Programa de Doctorado en Biotecnología, Ingeniería y Tecnología Química
NO Línea de Investigación: Ingeniería Informática
NO Clave Programa: DBI
NO Código Línea: 19
NO Universidad Pablo de Olavide de Sevilla. Departamento de Deporte e Informática
DS RIO
RD May 22, 2026