Section: New Results

Visual navigation of mobile robots

This study is concerned with visual autonomous navigation in indoor environments. As in our previous works concerning navigation outdoors [4] , the approach is based on a topological localization of the current image with respect to a set of keyframe images, but the visual features used for this localisation as well as for the visual servoing is not based on points of interest, but straight lines that are more common indoors. Satisfactory experimental results have been obtained using the Pioneer mobile robot (see Section  6.9 ) [23] .

Navigating within an unknown indoor environment using an electric wheelchair is a challenging task, especially if the user suffers from severe disabilities. We presented in [22] a framework for vision-based autonomous indoor navigation in an electric wheelchair capable of following corridors, and passing through open doorways using a single doorpost. The designed control schemes have been implemented onto a robotized wheelchair and experimental results show the robust behaviour of the designed system.

We then introduced in [40] a task-based control law which can serve as a low-level system for equitably joining interacting groups, while confirming to social conventions. The system uses the position and orientation of the participating humans with respect to a rigid sensor frame in order to control the translational and rotational velocity of a wheelchair so that the robot positions itself aptly at the meeting point

To address the wheelchair driving assistance issue, we proposed in [56] [28] a unified shared control framework able to smoothly correct the trajectory of the electrical wheelchair. The system integrates the manual control with sensor-based constraints by means of a dedicated optimization strategy. The resulting low-complex and low-cost embedded system is easily plugged onto on-the-shelf wheelchairs.

The robotic solution has been then validated through clinical trials that have been conducted within the Rehabilitation Center of Pôle Saint Hélier (France) with 25 volunteering patients presenting different disabling neuro-pathologies. This assistive tool is shown to be intuitive and robust as it respects the user intention, it does not alter perception while reducing the number of collisions in case of hazardous maneuvers or in crowded environment [27] .