One of the most promising uses for robotics and artificial intelligence is in assisting people with serious injuries and chronic conditions. Researchers at the Neuro-Biomorphic Engineering Lab at the Open University of Israel are developing a wheelchair-mounted robotic arm to assist patients with spinal injuries in performing daily tasks. The project will use funding and technology from Accenture PLC, as well as Intel Corp.’s neuromorphic technology and Applied Brain Research Inc.’s algorithmic support.
The companies announced today that they are supporting the project through the Intel Neuromorphic Research Community (INRC). The device will be clinically evaluated and tested with children at ALYN Hospital, which said it is Israel’s most advanced adolescent rehabilitation center.
Neuromorphic computing can enable assistive technologies
More than 75 million people around the world require a wheelchair for mobility. For those with neuromuscular or spinal cord injuries that result in upper extremity impairments, even the most basic tasks — like drinking from a cup or eating with a spoon — can be nearly impossible. Among such patients, the ability to reach and accurately manipulate objects is consistently rated as one of their most important challenges.
Assistive robotics can fill this gap. Studies suggest that wheelchair-mounted robotic arms provide an increased sense of independence for users and that these tools can reduce the need for caregiver time by up to 41%. However, these devices are still very costly, making them virtually inaccessible to most people who need them. This is largely due to the expensive parts needed to enable the arm to adapt to the user and the environment in real time.
“The ability of robotic arms to benefit people today is largely limited due to high cost and excessive power consumption,” said Elishai Ezra Tsur, lead project researcher at the Open University of Israel. “This funding from Accenture, along with additional support from Intel and ABR [Applied Brain Research], is allowing us to explore the implementation of adaptive controls on neuromorphic hardware in an effort to address the need for a collaborative, user-friendly, accurate robotic arm at a significantly reduced cost.”
Intel said the real-time learning capability of its Loihi neuromorphic chip could reduce the cost of creating and operating such devices. Researchers said they can use Loihi’s real-time learning to implement adaptive control to enhance an arm’s functionality. In addition, the use of affordable parts could reduce the cost by more than 10 times.
Because Loihi is up to 1,000 times more energy-efficient than general-purpose processors, it could also allow assistive devices to run for longer periods of time without charging, making them more useful in daily life, claimed Intel.
“This research project is a powerful demonstration of the impact that neuromorphic computing can have on the development of affordable intelligent assistive devices,” stated Edy Liongosari, technology innovation growth and strategy lead and chief research scientist at Accenture. “Making these devices accessible, particularly to such young patients, can have a profound impact on their independence, improving the way they live.”
Team to build neural network controls
Researchers at the Open University of Israel and ALYN Hospital have already created the robotic arm they will use in their trial. The next step is to build the neural network model that controls the wheelchair-mounted arm. To do this, the research team will build on the recurrent error-driven adaptive control hierarchy (REACH) algorithm, which was developed by ABR and is being provided by the company for this project.
ABR has demonstrated that the REACH model, paired with neuromorphic computing, can move a simpler robotic arm through complex paths. It can conduct tasks such as handwritten words and numbers with fewer errors and a significant improvement in energy efficiency over traditional control methods.
“Neuromorphic computing is a natural fit for assistive technologies, given its low power requirements and ability to learn and adapt to new situations in real time,” said Mike Davies, director of Intel’s Neuromorphic Computing Lab. “Through Intel and Accenture’s work with the Open University of Israel and ALYN Hospital, we hope to unlock new capabilities for mobility-impaired children and improve the patients’ quality of life.”
The INRC is an ecosystem of academic groups, government labs, research institutions, and companies around the world working to further neuromorphic computing and develop innovative AI applications. Researchers interested in participating in the INRC and developing for Loihi can visit the community website. A list of current members can also be found at its site.
Algorithm work to lead to testing wheelchair-mounted arm
Researchers from Accenture Labs and Intel Labs will apply their experience in neuromorphic computing and AI to assist with the development of the neuromorphic algorithm, as well as to provide support for the design of the wheelchair robot study. The companies said they will also continue to collaborate to identify and fund additional neuromorphic research.
Once the algorithmic work is complete, the research team will deploy the new model on Intel’s neuromorphic hardware and test the capabilities of the arm. After making some refinements, the device will undergo clinical testing and evaluation with patients at ALYN Hospital who rely on electric wheelchairs and have motor impairment of their upper extremities. The participants will control the arm using a small, dedicated joystick, and researchers will collect information on the robotic arm’s performance to assess its usefulness.
“We believe that the development of a robotic arm based on neuromorphic computing can be a game-changer for people with disabilities,” said Arie Melamed-Yekel, general manager of ALYNnovation at ALYN Hospital. “It could make it easier for them to engage with the community, boost their independence, and grant them new employment opportunities. The expected cost and performance improvements are potentially disruptive to this market.”
If this project is successful, the research team plans to explore how to produce this assistive robotic arm for patients with wheelchairs. In addition, they plan to investigate applications of adaptive control technology in flexible manufacturing and industrial automation.