Following an accident or motor impairment from illness, individuals often experience reduced mobility. When lower limb function is affected, individuals may lose the ability to walk and rely on a wheelchair. Despite maintaining upper limb mobility, emotional and societal factors may reduce motivation to use them. The Volting project aims to address this by developing a wheelchair with improved mobility to help users achieve their maximum potential. To overcome the limitations of traditional wheelchair controls, a device called WISP was developed, allowing control of Volting through trunk movements. This not only frees the upper limbs but also encourages users to engage their bodies in mobility. Initial experiments with a professional wheelchair dancer showed rapid adaptation to WISP usage. However, gradual implementation is recommended for non-athletic wheelchair users due to the risk of injury from unfamiliar movements. Therefore, we present a training system for WISP utilization, combining a virtual environment with haptic feedback to aid learning and adjust difficulty levels. Preliminary results demonstrate significant improvements in task completion time, collisions, and spatial errors after three sessions in our virtual environment. Additionally, trunk movements decreased, indicating more efficient adaptation to WISP use. As the next step, we plan to conduct trials with individuals with disabilities in our virtual training system, followed by integrating WISP with Volting to explore enhanced mobility.

This paper presents a novel approach to body gesture recognition for powered wheelchair users, leveraging inertial data from wrist-mounted sensors to facilitate movement and enhance autonomy in Adapted Physical Activity (APA). Gesture recognition technology interprets human gestures to allow non-direct communication with devices, enhancing human-machine interaction across various fields. APA fosters inclusion and well-being through tailored physical engagement. Our model not only identifies known gestures with high accuracy, as indicated by a mean Average Precision (mAP) score of 0.92 and a Recall@1 score of 0.983, but also demonstrates the ability to recognize gestures not included in the training set. This research contributes to the field of human-robot interaction by offering a more dynamic and inclusive form of interaction for individuals reliant on powered mobility aids.

Building upon advances on optimal transport and anomaly detection, we propose a generalization of an unsupervised and automatic method for detection of significant deviation from reference signals. Unlike most existing approaches for anomaly detection, our method is built on a non-parametric framework exploiting the optimal transportation to estimate deviation from an observed distribution. We described the theoretical background of our method and demonstrate its effectiveness on two datasets: an industrial predictive maintenance task based on audio recording and a detection of anomalous breathing relying on brain signals. In this type of problem, no negative or faulty samples are seen during training and the objective is to detect any abnormal sample without raising false alarm. The proposed approach outperforms all state-of-the-art methods for anomaly detection on the two considered datasets.

Rewarded at Laval Virtual 2014, the AccesSim project aims to develop a wheelchair simulator based on Virtual Reality (VR) and a dynamic force-feedback platform, which allows to experience and to evaluate the accessibility in complex urban or property environment. In order to address this issue, the dynamic force-feedback platform should provide haptic and vestibular feedback to various user profiles: from town-planners to wheelchair users. The platform needs to be modular and adjustable to each of these profiles. This article focuses on the dynamic force-feedback platform and specifically on the force-feedback systems used.

In this study, we present a new type of wheelchair called the cycling wheelchair, in which the user moves the wheelchair by pedaling with his/her legs and changes direction using a steering handle. This wheelchair has great potential not only as an effective rehabilitation device but also as a mobility assistive device. However, the commercially available model has several hardware limitations that affect the steering operation. In this paper, we discuss these hardware limitations before presenting methods for improving steering maneuverability. Furthermore, we propose power steering and force display controls based on environmental information. From the perspective of safety, we employ servo brakes to control the cycling wheelchair, and the assistive functions are realized based on the feasible braking control region. The proposed control methods are experimentally applied to a newly developed cycling wheelchair with servo brakes, and the results illustrate the validity of the control methods.

In this study, we propose a cycling wheelchair that assists the movement of patients with impairment of lower extremities. The wheelchair is a pedal-driven system, similar to a bicycle, moved by the pedaling force of the patient's legs. Although the lower extremities of patients are impaired, they can use both legs to smoothly rotate the pedal. However, there are several barriers to use the cycling wheelchair in an outdoor environment such as steep slopes, steps, and obstacles. In this study, we develop a cycling wheelchair controlled by a regenerative brake system. The braking control provides several assistive functions including velocity control, gravity compensation, and step/obstacle avoidance. The regenerative brake system can also charge a battery during the braking control. However, in situations such as steep-slope climbing and emergency stopping, the regenerative brake cannot generate the required force/moment and an active control is required. In these situations, the control mode is altered from braking to active, and the assistive functions are invoked using the energy charged by the braking control. For safety reasons, we propose a passive motion control method of the cycling wheelchair, even if the wheelchair operates under active control. The proposed cycling wheelchair is validated in a series of experiments in this study.

In this study, we propose a steering control method for a cycling wheelchair. The commercially available cycling wheelchair is a pedal-driven system that is similar to a bicycle, and patients with impairment of their lower extremities can move the wheelchair based on the pedaling force if they can slightly move their legs by themselves. The user can also change the wheelchair direction using the steering handle. However, right and left turns are perceived differently and a large steering torque is required while operating the steering handle because of hardware problems associated with the cycling wheelchair. To overcome this problem, we propose a new hardware solution and a method for steering motion control using servo brakes for the cycling wheelchair. The proposed method is applied to the developed cycling wheelchair, and the experimental results illustrate the validity of the system.

IEEE 802.11p is the new standard for inter-vehicular communications (IVC) using the 5.9 GHz frequency band; it is planned to be widely deployed to enable cooperative systems. 802.11p uses and performance have been studied theoretically and in simulations over the past years. Unfortunately, many of these results have not been confirmed by on-tracks experimentation. In this paper, we describe field trials of 802.11p technology with our test vehicles. Metrics such as maximum range, latency and frame loss are examined.

This paper presents key points of a human machine interface (HMI) for disabled people suffering from tetraplegia. It proposes an original HMI based on a monocular camera that controls an exoskeletal orthosis for the upper limb. The aim of this paper is to identify innovative research paths in intelligent camera interface (ICI). It shows how far can a camera be used as a control interface and its application to a 4 axis exoskeletal orthosis. Two methods are presented: head control using planar face detection and 3D face modelling and mouth expression control. The preliminary results show that the intelligent camera interface can be an effective issue in human machine interaction especially for disabled people since commonly used HMI are difficult to use, unreliable or tiring.

The goal of this project is to develop an upper limb exoskeletal orthosis destinated to help disabled population to achieve arm movements. This orthosis is principally designed for people suffering from myopathy and muscle degeneration. Such patients cannot generate enough force to move alone their arm. This poster presents a new approach to control the exoskeleton using pressure sensors.

This paper deals with solving robot cooperative task conflict using robot assistive behavior processing. These conflicts could occur in reactive multi mobile robot task. To manage such conflicts, each robot must assist the other units from their own capacities. A role method based on capacity adjustment is proposed. A role is a specific robot assistive behavior. Conflicts are then compensated by role switching. The same processing can be used in man-robot interaction. In this case, the robot has to define the efficient role in order to assist the man. A specific multi mobile robot conflict problem is studied: a constraint case of a reactive handling task with two mobile robots. This is a critical task since the object transported is only held by robot compression. Any degraded case, hardware failure or tactical conflict occurrences, would lead to a task deadlock. To define the global assistive role, on-line fuzzy reinforcement is used to adjust basic behaviors. In the studied case, no explicit communication is used to define the relationship between the robots in order to be generalized to man-machine cooperation. Our goal is to develop a strategy to manage interaction with handicapped persons. We studied a robotic rollator. In this case, the assistive role of rollator has to be adjusted in order to compensate the man's task

Evaluation systems for handicapped people through adapted interface are used to measure of people motor disability parameters and to provide assistance. In this work, a friendly reconfigurable evaluation and assistance platform for handicapped people is presented. A set of interfaces (mouse, joysticks, etc.) is used for controlling the pointing system. Different systems can be controlled (PCs cursor, robot Khepera, electric wheelchair). The main characteristics of this platform are the availability of several interface devices, exercises interaction with 2D models or 3D models, the saving of experimental data, the easy configuration of different scenarios, and the remote access capabilities. The system is illustrated through an implementation example and preliminary results are shown on a child with cerebral palsy

Due to specific pathologies, a part of the handicapped population does not have a correct adaptation of his wheelchair command and sometimes this adaptation is never found. This article presents a study about an automatic autoadaptation of the technical aid behavior with regard to the user characteristics. Different experiments are realized with two handicapped person on a robotic wheelchair. The obtained results present the possibilities of this adaptation on an electric wheelchair in order to take into account heavy difficulties of handicapped person commands (like cerebral motor infirmity, Sclerosis)

Due to technical progress and to the growth of the dependent population in our society (elderly and/or handicapped people), needs in advanced technical aids represent a great challenge for robotics. This article presents a study about technical systems for locomotion aid integrating robotic process and adaptive neural controller. The system specificities are an automatic auto-adaptation of the technical aid behavior with regard to the user characteristics. Different experiments have been realized with a robotic walker to evaluate our system. We also integrated it on a robotic wheelchair to show his portability on other technical aids. The obtained results present the possibilities of this adaptation on a walker system and on an electric wheelchair in order to take into account heavy difficulties of handicapped person commands (like Cerebral Motor Infirmity).

This article presents a study about a mobility aid system, which integrates adaptive control interface for a robotic walker. The objective is to give to the patient more flexibility in the choice of a technical aid. The specificity of our system is based on an auto-adaptive interface, which improves the configuration choice of the patient's driving commands. The results obtained from experimentations show the capabilities of our method for a technical aid. The learning process is applied on line to a neural network controller. The experiment is focused on sensors configuration and command of a powered walker interface.

Describes a concurrent programming language, named IAda, for robot applications. IAda is based on the Ada language and includes two programming levels: the first one to perform concurrent applications with tasks or procedures written in Ada, and the second one to control the execution of the previous. To reach this second goal, the authors include, in the definition of this language, a constraint scheme whose semantic is to verify properties during the execution of the task level program. The authors describe this language and its construction to show the high portability of IAda.>