Program at a Glance 27.04.2021

** Last updated on 08 April 2021 **


Bionics: What's Behind

Inail Direzione centrale assistenza protesica e riabilitazione (INAIL) --- ITALY

Despite the advances in robotics and mechatronic made available high performance prosthetic devices, the state of art of prosthetic control has yet not evolved enough for developing fully integrated Bionic systems. Nevertheless, Inail and its research network are currently investigating this field aiming to fuse in harmony the robotic technology and the human body. Indeed, exploiting artificial intelligence algorithms and innovative surgical techniques it has been possible to achieve simultaneous multi-limb control and restore the natural sensory feedback. Here we present the latest result of our research activity in this field showing that bionic prostheses represent a not so distant future.


Restoration of Hand Function Using Cognitive Nerve Transfers to Control Bionic Limbs

Medical University of Vienna --- AUSTRIA

Despite major improvements in primary prevention and acute treatment over the last decades, stroke is still a devastating disease and major cause of adult disability. Randomized controlled trials demonstrate the safety and efficacy of nerve root transfers for treatment of spastic arm paralysis after chronic cerebral injury. Here we present our first experience to restore hand function in patients with chronic spasticity after brainstroke using selective nerve transfers and EMG driven cognitive control of bionic limbs. This treatment has the potential to be a real game-changer in this particular patient group.


ROS2 for Powered Wheelchairs

Heidelberg University --- GERMANY

The Robot Operating System is a set of open-source software libraries and tools for building robot applications. By applying state of the art algorithms and developer tools from mobile robotics research, higher level interfaces can be implemented efficiently. We present a solution of a conventional wheelchair combined with additional sensors for evaluation of human wheelchair interaction. Combining such a system with BCI can ensure safe and fast brain controlled wheelchair navigation.


BCI controlled robotic arm as assistance to the rehabilitation of neurologically disabled patients

Canterbury Christ Church University --- UK

This presentation summarises the development of a portable and cost-efficient BCI controlled assistive technology using a non-invasive BCI headset 'OpenBCI' and an open source robotic arm, U-Arm, to accomplish tasks related to rehabilitation, such as access to resources, adaptability or home use. The resulting system used a combination of EEG and EMG sensor readings to control the arm, which could perform a number of different tasks such as picking/placing objects or assist users in eating.


Smart Robotic Device for Motor & Cognitive Learning of Individuals with Special Needs

Tel Aviv University --- ISRAEL

Technological solutions for supporting learning in people with special needs should be developed in order to satisfy a huge unmet demand. The developed solution aims at supporting learning of individuals with movement and cognitive impairments, through a real-time human-robot interaction system based on decoding of EEG signals and movement recordings performed by AI techniques. The system allows users with special needs to interact in a fun way with a 3-D printed mobile robot controlled by their brain and body signals. The developed smart robotic device for learning and training was tested on healthy subjects, adjusted for specific requirements of individuals with cerebral palsy, and tested on the pilot group with a full longitudinal study to start soon.


Towards a smart and intuitive controlled leg prosthesis: acquisition of intramuscular electromyography for motion intention detection. A pilot study.

Roessingh Research and Development --- THE NETHERLANDS

This pilot study explores the use of intramuscular EMG (iEMG) and targeted muscle reinnervation (TMR) to improve motion intention detection in transfemoral amputees. The hypothesis is that iEMG will improve intention detection because of reduced crosstalk and more consistent electrode sites. The TMR sites will provide valuable extra information for motion intention detection. Methods: A study population of able-bodied individuals (n=5), transfemoral amputees (n=5), and transfemoral amputees with TMR (n=5) will be included in this observational study. During the measurements iEMG (fine-wires), sEMG (multi-array) and lower body kinematics are measured while participants execute activities like sitting down, walking on uneven terrain, and stair/ramp ascend/descend. Results: Preliminary results will be presented.


Post-Stroke Rehabilitation Using a BCI Robotic System That Provides Hand-eye Transformation

The Center for Neurobiology and Brain Restoration at the Skolkovo Institute of Science and Technology --- RUSSIA

In this talk we describe the novel approach to BCI robotics control in motor restoration. It significantly enhances the number of patients, especially stroke survivors, that can be effectively treated in early stage of decease when rehabilitation is expected to be the most effective. This approach has been successfully tested in clinical settings.


EDAN, the EMG-controlled Daily Assistant

German Aerospace Center (DLR) --- GERMANY

This talk will present EDAN, a research prototype of an assistive robotic system, to restore mobility and manipulation capabilities for people with motor impairment. EDAN can be controlled via an sEMG-based interface which allows control even in cases of severe muscular atrophy. The robot combines several robotic techniques, like impedance control and whole-body control to create a versatile and powerful system. To make use of the robot as easy as possible, so-called shared-control techniques are implemented. The robot uses its knowledge of the world to predict the users intentions and to assist accordingly in the execution of the task.


Shared Control of a Robotic Arm using Brain-Computer Interfaces and Robotic Vision

University of Bath --- UNITED KINGDOM

The brain-computer interfaces (BCIs) based on non-invasive electroencephalography (EEG) have been widely used. However, the low-quality of EEG signals may cause problems of poor decoding accuracy and low control dimension, which adversely affects the performance of non-invasive BCIs during real-time process control in complex tasks. In this work, a brain-actuated robotic arm system based on shared control was developed, which allowed noninvasive BCI users to manipulate a robotic arm with six degrees of freedom moving in a three-dimensional (3D) space and complete a pick-and-place task of multiple objects. We introduced a hybrid BCI scheme that integrated motor imagery and steady state visual evoked potentials to raise the control dimension of the robotic arm.


HyDRA-Walker project: a robotic walker guide for powered exoskeletons with neural interface

Department of Information Engineering, The University of Padova --- ITALY

Powered lower-limb exoskeletons represent a recently emerging technology in the field of wearable robotics, enabling paraplegic people to walk again. However, their use is still restricted to clinical settings or controlled environments. To overcome this limitation, herein we present the HyDRA-Walker project, about the development of a robotic walker that will act as an intelligent guiding agent to control brain-actuated exoskeletons in daily-living situations. We further present our latest advancements on a hybrid brain-computer interface (h-BCI) for walking decoding. Finally, we introduce future insight on how this interface will be adopted to control the powered exoskeleton in our project.


Feel Your Reach: Continuous robotic arm control by non-invasive EEG signals

Graz University of Technology, Institute of Neural Engineering, BCI-Lab --- AUSTRIA

Decoding intended movements from individuals with spinal cord injury (SCI) has been a central topic in brain-computer interface research for decades. Recent works, relying on neural spiking activity, demonstrated that the kinematics of intended movements can be detected and used by individuals with SCI to control end-effectors. In this work, we summarize our attempts towards realizing an EEG-based movement decoder. We summarize our efforts to address this topic from various perspectives, and we present results of a single case study with a non-disabled participant, where we decoded the intended movement trajectories, while the participant’s arm was fixed.


A multi-gesture anthropomorphic hand online control: based on surface EMG signal and neural network

The University of Manchester --- UNITED KINGDOM

Introduce an sEMG-based real-time multi-gesture control system running on a published anthropomorphic robotic hand. The raw surface EMG signal was extracted by 5 time-domine features in different sliding window size. The features were standardized and classified by two neuron network models, i.e., MLP and CNN. Weighted-voting method was adopted to obtain the classification results from the models mentioned above. The anthropomorphic hand accomplishes 11 gestures based on real-time sEMG signal of a healthy subject with 98.24% accuracy.


Development of an EEG Controlled Wheelchair Using Color Stimuli: A Machine Learning Based Approach

Bangladesh Army University of Engineering & Technology (BAUET) --- BANGLADESH

Being sensitive to the color stimuli, the EEG signal changes promises a better detection. Utilizing the Electroencephalogram (EEG changes due to different color stimuli, a methodology of wheelchair controlled by brainwaves has been presented in this study. Red, Green, Blue (primary colors) and Yellow (secondary color) were chosen as the color stimuli and utilized in a 2 × 2 color window for four-direction command, namely left and right, forward and stop. Alpha, beta, delta and theta EEG rhythms were analyzed, time and frequency domain features were extracted to find the most influential rhythm and accurate classification model.


Unlocking Independence: How BCI can be used to increase access to power mobility and independent movement

University of Calgary --- CANADA

Children with severe physical disabilities could drastically benefit from access to powered wheelchairs and other power mobility devices (PMDs) to enable their independence and participation. However, these children are often ineligible for PMD funding if their severity of disability prevents them from operating traditional access methods like joysticks or switches. Brain-computer interfaces (BCI) are a promising alternative access method for these children but has seen limited clinical translation. We have developed a modular, affordable, and easy-to-use BCI-enabled PMD using a commercial-grade headset that can be used by therapists in a clinical setting to explore power mobility with severely disabled children.


Intelligent Assist Technology for Power Wheelchair: Problems and Challenges of Product Approach

Mobilis Robotics LLC --- POLAND

The analysis of current status and future prospects of intelligent assistants for power wheelchairs (IAPW) is presented. The main problems of their real application at home are noted. In particular, despite some progress in smart PW research, people with cognitive/motor impairments still have significant problems using PW and are often barred from driving PW independently. Examples of diagnoses that can affect an individual's ability to drive PW safely include cerebral palsy, Parkinson's disease etc. The complex approach to formation of system requirements, offers and results of researches by R&D Project of Mobilis Robotics LLC on development of IAPW are presented.


Learning to drive a brain-actuated intelligent wheelchair

Department of Information Engineering, Università degli Studi di Padova --- ITALY

Among the several brain-actuated neurorobotic prototypes, brain-machine interface (BMI) driven wheelchairs represent the paramount promise for people suffering from severe motor disabilities thanks to the applicability in complete paralysis. Herein, we present the latest experimental results where three tetraplegic spinal cord injury users learned to control a non-invasive, self-paced BMI-driven wheelchair and execute complex navigation tasks in real-world surroundings. We further substantiate that user's learning and robotic intelligence are the two cornerstones for developing robust and effective BMI translational applications. Finally, we introduce the next directions of our research to promote human-machine learning interactions in brain-controlled neuroprostheses.


EEG signals, feedback, and brain-computer interfaces in support of upper and lower limb rehabilitation: current status

Universidad Pedagogica y Tecnologica de Colombia --- COLOMBIA

Review of the state of the art and limitations in the development of BCI for rehabilitating the upper and lower limbs of the human body. A systematic review was conducted in databases considering using EEG signals, interface proposals to rehabilitate upper/lower limbs using motor intention or movement assistance, and utilizing virtual environments in feedback, specification, processing, and control. It was identified that 61.11% corresponded to applications to rehabilitate upper limbs, 33.33% lower limbs, and 5.56% both. Likewise, 33.33% combined visual/auditory feedback, 11.11% haptic/visual, and 11.11% visual/auditory/haptic. In addition, 27.78% had fully immersive VR, 16.67% semi-immersive VR, and 55.56% non-immersive VR.


EASY Walk: EEG Driven Walking Rehabilitation with Exoskeletons

INDI Ingenierie et Design --- FRANCE

Current clinical rehabilitation with exoskeletons faces important shortcomings: a 'one fits all' approach, limited occupational tasks, and an inadequate quantification of expected outside-of-hospital performance. Easy WALK proposes an Ambulatory, Mobile encephalography(EEG)-Amended Platform which adds robotic support and mental-workload assessment capabilities to occupational rehabilitation. Training is made possible in hospital and outdoors, allowing to 1) better tune rehabilitation techniques and 2) improve on outside-of-clinic results. This work focuses on integrating such workload-focused mobile BCI devices to pediatric exoskeletons and on improving the rehabilitation process in clinic and exoskeleton usage in outside environments, especially for children and early life-quality improvement.

The information contained herein is subject to change without prior notice.