MIT’s Computer Science and Artificial Intelligence Laboratory (CSAIL) has created a motion and muscle rehabilitation system using sensors, AI and virtual reality.
Called MuscleRehab, the MIT CSAIL system uses three ways to help with physical rehabilitation:
- Motion tracking
- A virtual reality headset
- A tracking suit
Why is it needed?
With an aging population and higher rates of physical ailments, physical therapy is in high demand but there are not enough physical therapists.
This has led to new sensor-based techniques — such as body motion sensors — to provide some autonomy and precision for patients.
This new technique could bring a higher level of physical rehabilitation to patients such as athletes or elderly.
How it works
Patients put on the all-black tracking suit and VR headset and then sensor and AI capture 3D movement data as the patients perform various exercises such as lunges, knee bends, deadlifts, leg raises, knee extensions, squats and more.
In the virtual environment, an avatar performs alongside a physical therapist. The motion tracking data is overlaid onto the patient’s avatar. Then a patient puts on EIT sensing straps and has the information of the motion and muscle engagement.
The two situations are compared and the professional therapist can view the data of these unsupervised exercises instead of the motion alone.
MIT said the overall accuracy of the exercises improved by 15%.
“We wanted our sensing scenario to not be limited to a clinical setting, to better enable data-driven unsupervised rehabilitation for athletes in injury recovery, patients currently in physical therapy, or those with physical limiting ailments, to ultimately see if we can assist with not only recovery, but perhaps prevention,” said Junyi Zhu, MIT CSAIL PhD student and lead of MuscleRehab. “By actively measuring deep muscle engagement, we can observe if the data is abnormal compared to a patient's baseline, to provide insight into the potential muscle trajectory.”
