Mohamed Jallouli

EEG control of an electric wheelchair for disabled persons

This paper presents a description of an intelligent control method for controlling an electric wheelchair for several disabled persons. It also describes a non invasive approach based on EEG brain signal that can command the wheelchair with cognitive data, eye movements and head gestures. Our technique aim is to cover the largest number of handicapped person.

A multimodal wheelchair control system based on EEG signals and Eye tracking fusion

Controlling an electric powered wheelchair (EPW) is not always a simple task for certain types of disabled person. For example, persons suffering from the locked in syndrome or ALS. Many researchers use the eye tracking or the brain signals as alternative ways to control the EPW. The goal of this paper is to illustrate the EPW control performance amelioration when using multi sources compared to single source control. The first part is to elaborate separate control techniques using ElectroEncephalography (EEG) then eye tracking technologies. The second part, is combining these techniques using data fusion algorithms. Finally, testing the control performance with EEG, Eye tracking and EEG/Eye tracking.

Adaptive ANN-based control for constrained robot manipulators

An Artificial Neural Network (ANN)-based approach is proposed in this paper for the motion and force control of constrained robot manipulators. The dynamic model of constrained manipulator is modified to contain two sets of state variables, where one describes the constrained motion and the other describes the reduced, unconstrained one. An application related to a disk cutter robot is considered. The design objective is that under a prescribed radius of the disk and a desired force to be applied by the effector of the manipulator, an ANN-based control system is to be designed to develop the requested torques on the manipulator actuators. The suggested controller is simple and can be implemented easily. The main feature of employing the ANN here is that we obtained a force sensor-less control system and a good adaptation with environmental unmodelled dynamics. Simulation results are presented to validate the proposed approach.

Fuzzy-EKF Controller for Intelligent Wheelchair Navigation

Abstract The electric wheelchair gives more autonomy and facilitates movement for handicapped persons in the home or in a hospital. Among the problems faced by these persons are collision with obstacles, the doorway, the navigation in a hallway, and reaching the desired place. These problems are due to the difficult manipulation of an electric wheelchair, especially for persons with severe disabilities. Hence, we tried to add more functionality to the standard wheelchair in order to increase movement range, security, environment access, and comfort. In this context, we have developed an automatic control method for indoor navigation. The proposed control system is mounted on the electric wheelchair for the handicapped, developed in the research laboratory CEMLab (Control and Energy Management Laboratory-Tunisia). The proposed method is based on two fuzzy controllers that ensure target achievement and obstacle avoidance. Furthermore, an extended Kalman filter was used to provide precise measurements and more effective data fusion localization. In this paper, we present the simulation and experimental results of the wheelchair navigation system.

Remote control of mobile robot through 3D virtual reality environment

This paper describes teleoperation systems for remote control of robot and the use of 3D virtual reality. It presents the adopted architecture and describes the experimental implementation through simulation results for mobile robot Khepera.

Optimal trajectory of a mobile robot using hierarchical fuzzy logic controller

This paper presents the development of a complete navigation problem of an autonomous mobile robot. The problem for which the robot tries to reach the target is treated using a hierarchical fuzzy logic controller HFLC. The optimisation of the consequences of fuzzy rules is solved using genetic algorithms. A new approach based on HFLC is presented in this paper to avoid collisions with obstacles. In fact, HFLC consists of a number of low-dimensional standard fuzzy systems connected in a hierarchical fashion. Hence, it can provide a good candidate for solving high-dimensional problems. Simulation results show that the designed hierarchical fuzzy controller gives good trajectory of the robot from its current position to the target with obstacle avoidance.

Towards a parallelization and performance optimization of Viola and Jones algorithm in heterogeneous CPU-GPU mobile system

Parallel computing on heterogeneous multiprocessor architecture is a new technique used to tackle the complexity of actual media applications. Such technique is used on an embedded architecture composed of 2ARMs coupled to a GPU. In this paper, an approach for real time Viola and Jones face detection algorithm using CPU-GPU based platform is presented. First, the application is implemented and parallelized on two identical ARM CortexA9 CPUs using tasks and data levels parallelism. This technique does not achieve the timing objectives. To ensure greater performance while reducing energy ratio, we extend our parallelization technique to support a GPU as an accelerator to perform non graphical tasks. OpenCL, the heterogeneous parallel programming model, is used to ensure communication between CPU and GPU.

An embedded real-time hands free control of an electrical wheelchair

The main aim of this work is to propose a HMI alternative for hands-free control of an electrical wheelchair using both face and eyes information. An image processing based technique for the guidance of an electrical wheelchair is used. As processing unit, we choose the Panda board ES development kit based on the TI OMAP 4 SoC (System on Chip). This board is connected with the wheelchair for processing of the video streaming. The wheelchair command technique is based on image segmentation and facial detection. The adopted model relied on combining 2ARMs processing in a single chip for improving real-time performance, enhancing system flexibility and reducing system cost and power. The preliminary results are promising since a total processing time of about 0.9s is obtained.

A self configured and hybrid fusion approach for an electric wheelchair control

Despite the benefice of electric wheelchairs, some types of motor disabilities are incapable to use them. Indeed, According to experiments conducted with people with severe disabilities, the use of electric wheelchairs requires a greater customization. As a consequence, some researchers replace the joystick by alternative control such as EEG signals, eye or head tracking. In this paper, the goal is to control an EPW using an hybrid and self configured fusion technique between EEG signals, head movement and eye tracking. As the proposed system targets are persons with severe motor handicap, voice recognition was used to activate and deactivate the control system.

Development of an Android Service to add IOIO Hardware Features to Android Apps

The world is currently witnessing a revolution in the Internet of Things (IoT) field. It is predicted that one day, our everyday lifes objects will embed a computer. These devices collaborate to make all tasks as simple as possible, which is the ultimate objective of IoT. In this context, and with electronics and computer Science being one of the key skills in this field, there is a focus on lowering the entry level to these two fields, enabling a wider audience to learn the basic concepts at an early age. Different products are proposed, that simplify whether Electronics or programming tasks, however, a combination of both merely exists. The paper presents an initiative to simplify the programming task that consists of developing an Android service that integrates commands to control an electrical board called IOIO, which can be controlled via Android using Bluetooth. The service can be called by the App Inventor platform to add IOIO hardware features. With this integration, the developed Android apps can control the electrical board and electrical components connected to it. All of this without technical knowledge, which opens the way for easy prototyping of embedded systems.