B-CRATOS explained

1
2
3
4
5
1

The implant electronics use a custom-designed ASIC chip to perform brain signal acquisition. Neural signals are converted to digital data for transmission and delivered to the communication unit. The communication unit uses a high data rate backscatter link for wireless brain neural readout and another two-way low data rate for stimulation commands and implant telemetry, which also performs the WPT function. The external unit reads brain data using the RF backscattering technique, sends AI Module-generated stimulation commands, and reads implant monitoring data using another transceiver wirelessly. The neural brain data is transferred to the AI Module through the FAT-IBC channel.

2

A fat IBC platform is Integrated to the neural interface and sensorized bionic limb. It is capable of safe high-speed, high-bandwidth data transmission through the adipose tissue layers (or “fat channel”) of the body. The Fat-IBC communication platform demonstrates real-time two-way transmission of recorded neural data and sensory stimulation signals between brain and machine.

3

The AI module translates and relays signals between the brain and the prosthetic hand. It handles data in the two directions:

  • Brain to hand (downstream): the stream of data coming from the implant in brain motor cortex is translated into commands for the MIA hand by a deep neural network model trained remotely on an HPC facility and continuously updated.
  • Hand to brain (upstream): it encodes the signal of the artificial skin and hand, creating a perceptual model for closed-loop feedback to the sensory cortex stimulation implant
4

Through careful experimental design, care, and training, NHPs are trained to control a robotic limb and to interpret sensory feedback in a movement task, generating critical data sets to inform the development of decoding models and identify key parameters for the in-body communications system. In real-time demonstration of the completed B-CRATOS platform, the NHPs achieves closed-loop control of the advanced prosthetic using the neural bypass bridge technologies.

5

One enabling technology of B-Cratos is represented by a human-like prosthetic hand endowed with an electronic skin (or “eSkin”). It is linked to edge computing devices leveraging machine learning/AI techniques for real-time decoding of neural signals into hand actions and touch feedback into meaningful brain stimulation commands. The hand used is the Mia model manufactured by Prensilia