Axiles Bionics is one of the two laureates of Innoviris' Innovative Starters Award (ISA). A boost of €500,000 from this initiative supporting innovative start-ups and scale-ups with revolutionary ambitions in their field, aiming to give a push to their strategic R&D projects.
As a proud recipient of the Innovative Starters Award, Pierre Cherelle, CEO of Axiles Bionics, responds to Innoviris' questions.
Who is Pierre Cherelle?
Pierre Cherelle is the founder and CEO of Axiles Bionics. This start-up is a spin-off from BruBotics at the Vrije Universiteit Brussel, specializing in robotics, artificial intelligence, and human biomechanics. Their goal is to develop the new generation of bionic prostheses for lower limb amputees.
How does the company revolutionize the medical world?
Ankle-foot prostheses have seen little evolution in 50 years, with the majority fixed at a 90-degree angle without ankle articulation. This poses a real problem for users, forcing them to compensate with the rest of their body, resembling walking with a ski boot. Axiles Bionics aims to develop articulated prostheses that enable muscular functionality, a true innovation they have been working on for 15 to 20 years. Today, this technology is reaching maturity for everyday use by amputees.
To what extent has your project impacted the Brussels-Capital region?
The significant social impact on people with reduced mobility and the improvement of their daily lives is one aspect. Another is stimulating academic research in robotics, artificial intelligence, and biomechanics. Axiles Bionics aims to build a bionics center of excellence with research groups at the Vrije Universiteit Brussel. Importantly, all existing prosthetic manufacturers in the market are currently based abroad. As these prostheses are fully reimbursed by health insurance, it leads to economic depletion in the region and the country. Pierre Cherelle hopes to have a positive impact on the national economy.
How does artificial intelligence advance bionic prostheses?
There are several aspects of artificial intelligence that we apply in our technologies. The first one is robot intelligence. A robot operates like a human, with a structure corresponding to the human skeleton, musculature corresponding to the robot's engine, a brain corresponding to intelligence, and electronic components. Currently, a prosthesis cannot be directly connected to the human brain. We are required to introduce a form of intelligence into the prosthesis. The principle of artificial intelligence is to collect data on usage, inputs, and outputs. The more data we have, the clearer the connections become between what happens in the environment and how the prosthesis should respond to these stimuli. When you walk, if you see stairs 10 meters ahead, you have automatic cognitive feedback. You adjust your stride, the frequency of your steps to arrive precisely on the first step without even realizing it. The challenge is that a prosthesis not connected to the human brain cannot perform the same. The more data available, the better the prosthesis's intelligence becomes. It's similar to the human brain—more training in a particular task leads to increased proficiency in those activities.
The second aspect involves a different kind of artificial intelligence called reinforcement learning. The idea is to create prostheses capable of autonomous learning. How will the prosthesis adapt to differences in the size, weight, and stride of each person? This is where the Strategic Innovation Plan funded by the Innovative Starters Award comes in. The goal is to develop a data harvesting platform in the cloud that captures each prosthesis in use on the market. Each evening, when an amputee goes to bed, they remove their prosthesis and plug it in to recharge, similar to a phone. Simultaneously, we are developing this platform to send the data collected during the day to our servers, still on the cloud. Initially, the data benefits all users to enhance daily functioning, but it also allows individual refinement for each person. Specific user data can be fine-tuned. By dawn, these new parameters are sent back to the prosthesis, so the person wakes up with a prosthesis that works better than the previous day. We aim to develop artificial intelligence in the software so that our product adapts to the user, and it's not the user who has to make all the efforts to adapt.
What do you like about your work?
Everything! But what I particularly enjoy is the ability to rally people to my cause, which began 15 years ago during an academic research project. I like bringing together a large number of stakeholders: the management team, employees, future employees, as well as Brussels entities like Innoviris or Hub.brussels, prosthetists, healthcare professionals, and more. Many children dream of working in robotics or artificial intelligence, so we realize that we have a significant role to play. The positive social impact is also a great satisfaction.
What was your journey before Axiles Bionics?
Pierre is a physicist. He studied physics at the Vrije Universiteit Brussel and then pursued a Ph.D. in robotics. Thanks to the results, he received financial assistance from Innoviris to launch his spin-off. This experience allowed him to work on business development. Before starting Axiles Bionics, Pierre went through the challenging process of seeking funding and investors. One day, with his team, they successfully secured financing of several million euros, enabling him to start the company and hire his first employees. That was three years ago. Since then, he has continued to develop Axiles Bionics and its products.
According to Pierre, one of the strengths of the Innovative Starters Award is that it doesn't focus solely on technology or artificial intelligence; it also addresses new economic models that help bring a product to market.
Find the article on the ISA on the Innoviris website.