Jesus Arturo Escobedo Cabello - User Intention Estimation for Semi-Autonomous Navigation of a Robotic Wheelchair

09:30
Vendredi
3
Oct
2014
Organisé par : 
Jesus Arturo Escobedo Cabello
Intervenant : 
Jesus Arturo Escobedo Cabello
Équipes : 
Information détaillée : 
Lieu de soutenance : Amphithéâtre F107 de l'Inria à Montbonnot,
 
Jury : 
  • James L. CROWLEY, professeur, INPG, France, président
  • Rachid ALAMI, drecteur de recherche, LAAS-CNRS, France, rapporteur
  • Marie BABEL, maître de conférences, INSA, Rennes, France, rapporteur
  • David DANEY, chargé  de recherche, INRIA, Bordeaux, examinateur
  • Christian LAUGIER, directeur de recherche, INRIA Rhône-Alpes, France, directeur de thèse
  • Anne SPALANZANI, maître de conférences, UPMF, Grenoble, France, co-directeur de thèse
Résumé : 
This thesis focuses on semi-autonomous wheelchair navigation. We aim to design a system respecting the following constraints.
  • Safety: The system must avoid collisions with objects and especially with humans present in the scene.
  • Usability: People with motor disabilities and elders often have problems using joysticks and other standard control devices. The use of more sophisticated and human-like ways of interacting with the robot must be addressed to improve the acceptance and comfort for the user. It is also considered that the user could just be able to move one finger and so the request of human intervention should be as reduced as possible to accomplish the navigation task.
  • Compliance: The robot must navigate securely among obstacles while reducing the frustration caused to the user by taking into account his intentions at different levels ; final destination, preferred path, speed etc.
  • Respect of social conventions: When moving, the robot may considerably disturb people around it, especially when its behavior is perceived as unsocial. It is thus important to produce socially acceptable motion to reduce disturbances. We will also addresses the issue of determining those places where the robot should be placed in order become part of an interacting group.
 
In this work we propose to estimate the user's intention in order to reduce the number of necessary commands to drive a robotic wheelchair and deal with ambiguous or inaccurate input interfaces. In this way, the wheelchair can be in charge of some part of the navigation task and alleviate the user involvement. The proposed system takes into account the user intention in terms of the final destination and desired speed. At each level, the method tries to favor the most “reasonable” action according to the inferred user intention.
 
The user intention problem is approached by using a model of the user based on the hypothesis that it is possible to learn typical destinations (those where the user spends most of his time) and use this information to enhance the estimation of the destination targeted by the user when he is driving the robotic wheelchair.
 
A probabilistic framework is used to model the existent relationship between the intention of the user and the observed command. The main originality of the approach relies on modeling the user intentions as typical destinations and the use of this estimation to check the reliability of a user's command to decide how much preeminence it should be assigned by the shared controller when managing the robot's speed.
 
The proposed shared-control navigation system considers the direction of the commands given by the user, the obstacles detected by the robot and the inferred destination to correct the robot's velocity when necessary. This system is based on the dynamic window approach modified to consider the input given by the user, his intention, the obstacles and the wheelchair's dynamic constraints to compute the appropriate velocity command.
 
All of the results obtained in this thesis have been implemented and validated with experiments, using both real and simulated data. Real data has been obtained on two different scenarios; one was at INRIA's entry hall and the other at the experimental apartment GERHOME.