Most people are unIt has been estimated that more than 75 million people in the world need a wheelchair for mobility. However, some of those who need a wheelchair have neuromuscular or spinal cord injuries, which makes it hard for them to perform simple tasks like drinking from a cup or eating with a spoon
These patients were found to have difficulty in reaching and manipulating objects precisely. With that in mind, a team of engineers came with an idea of developing a wheelchair-mounted robotic arm to assist patients in performing daily tasks. Last month, Intel and Accenture have announced their support of this project.
Developing the wheelchair
The Neuro-Biomorphic Engineering Lab at the Open University of Israel, in collaboration with ALYN Hospital, is leading the Intel Neuromorphic Research Community (INRC) project. Intel will provide its neuromorphic technology and algorithmic support from Applied Brain Research (ABR). Meanwhile, Accenture will support the project through funding and providing technologies.
These resources will be used to develop a wheelchair-mounted robotic arm that will make it easy for patients in wheelchairs to perform simple tasks. Intel’s press release reveals that once the wheelchair gets developed, it will be clinically evaluated and tested with children at ALYN Hospital, Israel’s most advanced adolescent rehabilitation center.
Using Intel’s neuromorphic research chip
According to the studies performed by the team, wheelchair-mounted robotic arms can help the patients and provide them with an increased sense of independence. However, it’s expected that the device may come at a high cost, making them unavailable to the most vulnerable patients. These devices require costly parts that will enable the arm to adjust to the patient’s environment in real-time.
For that purpose, Intel’s neuromorphic research chip called Loihi will reduce the cost of developing and creating these robotic arms. Researchers theorize that since Loihi is a self-learning chip, it can theoretically implement adaptive control to enhance the arm’s functionality. At the same time, they will use cheaper parts to create the arm, exponentially reducing the costs.
Moreover, Loihi has the potential to make assistive technologies more effective in daily situations. It is a thousand times more energy-efficient than standard processors, so a device built with Loihi will require less charging.
A trial robotic arm is already developed
The researchers at the Open University of Israel and ALYN have already developed a trial version of the robotic arm. Their next step is to create the neural network model that will control the arm. To do that, the research team will work on the driven adaptive control hierarchy (REACH) algorithm, with fixed errors and significant improvements. Once that work is finished, the research team will deploy the new model on Intel’s neuromorphic hardware and test the capabilities of the arm.
If their project is successful, the research team will continue exploring how to produce its robotic arm for patients. In turn, Intel and Accenture will continue to support the teams developing the robotic arm.
Photo credit: The images used are owned by Intel and have been provided for press usage.
