AI strategy may promise more widespread use of portable, robotic exoskeletons—on Earth and in space

The recent study published in Nature has presented a new controller for portable, robotic exoskeletons that leverages data-intensive artificial intelligence (AI) and computer simulations for training. This new controller provides smooth, continuous torque assistance for walking, running, or climbing stairs without the need for any human-involved testing. The controller is driven by three interconnected, multi-layered neural networks and learns as it goes, improving human mobility through "millions of epochs of musculoskeletal simulation." The experiment-free, "learning-in-simulation" framework, when deployed on a custom hip exoskeleton, has generated the highest metabolic rate reductions of portable hip exoskeletons to date, with an average of 24.3%, 13.1%, and 15.4% reduced energy expenditure by wearers for walking, running, and stair-climbing, respectively. The approach bridges the simulation-to-reality gap and offers a generalizable and scalable strategy for the rapid, widespread deployment of assistive robots for both able-bodied and mobility-impaired individuals.

The "learned" controller that leverages artificial intelligence (AI) in training exoskeletons offers several specific benefits:

1. Eliminates the need for human-involved testing: The controller provides smooth, continuous torque assistance for walking, running, or climbing stairs without the need for any human-involved testing. This makes the development process faster and more efficient.

2. Improves energy efficiency: The experiment-free, "learning-in-simulation" framework deployed on a custom hip exoskeleton generated the highest metabolic rate reductions of portable hip exoskeletons to date. It achieved an average of 24.3%, 13.1%, and 15.4% reduced energy expenditure by wearers for walking, running, and stair-climbing, respectively.

3. Enhances human mobility: The controller learns as it goes, evolving through "millions of epochs of musculoskeletal simulation to improve human mobility." This enhances the performance of the exoskeleton in assisting human movements.

4. Bridges the simulation-to-reality gap: The AI-driven controller is the first to demonstrate the feasibility of developing controllers in simulation that can effectively be deployed in real-world scenarios, improving human performance.

5. Offers a scalable solution: The framework "may offer a generalizable and scalable strategy for the rapid, widespread deployment of a variety of assistive robots for both able-bodied and mobility-impaired individuals."

6. Potential applications in rehabilitation: Future research will focus on unique gaits for walking, running, or stair climbing to help people who have disabilities such as stroke, osteoarthritis, and cerebral palsy, as well as those with amputations.

Overall, the "learned" controller using AI in training exoskeletons significantly improves the efficiency, mobility, and adaptability of exoskeletons, making them more accessible and beneficial to a wider range of users.