Robotic Prosthetic Limb Motor Control via BMI Neural Signal Averaging
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current prosthetic limb technologies are limited by the use of single algorithms, leading to delayed and inaccurate movements, and are cumbersome and dangerous due to their reliance on predictive technologies and the delicate nature of the human neurological system.
Innovation Solution
A system comprising a brain machine interface (BMI) with electrodes, a processor, and a wireless transceiver, and a robotic prosthetic limb with a motor, second wireless transceiver, and controller, utilizing four deep learning algorithms to generate precise direction and speed predictions for motor control, with a biocompatible coating for safety and wireless communication for accurate and efficient operation.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If a single algorithm is used for predictive control, then the system is simpler to implement, but the movement accuracy and speed prediction are insufficient
Solution Approach 1:
The patent divides the single algorithm into four separate deep learning algorithms, each specialized for specific predictive control tasks. This segmentation allows each algorithm to focus on particular aspects of movement prediction, thereby improving overall accuracy while maintaining manageable complexity through modular design
Solution Approach 2:
The patent combines multiple deep learning algorithms into an integrated system where their outputs are merged to generate comprehensive motor control signals. This merging leverages the strengths of each individual algorithm to achieve superior movement accuracy and speed prediction that cannot be obtained with a single algorithm
2Adaptability or versatility
If predictive technologies are implemented, then the prosthetic limb can anticipate user intentions, but the system becomes cumbersome and potentially dangerous due to the delicate nature of the neurological system
Solution Approach 1:
The patent introduces a wireless communication system as an intermediary between the BMI and prosthetic limb, eliminating the need for direct physical connections that could damage delicate neurological tissue. This intermediary approach maintains predictive responsiveness while significantly reducing implantation risks and system complexity
Solution Approach 2:
The patent replaces mechanical and direct electrical connections with wireless communication technology. This substitution eliminates physical intrusion into the neurological system, reducing implantation risks while preserving the ability to transmit control signals for adaptive prosthetic operation
3Measurement precision
If multiple deep learning algorithms are used, then the direction and speed prediction improves, but the processor power consumption increases
Solution Approach 1:
The patent segments the computational workload across four specialized algorithms, allowing each to process specific aspects of movement prediction efficiently. This segmentation prevents any single algorithm from consuming excessive power while collectively achieving high prediction accuracy
Solution Approach 2:
The system employs self-optimizing mechanisms where the multiple algorithms work together to efficiently process neural signals, reducing redundant computations and power consumption while maintaining high prediction accuracy through their coordinated operation
Data Source
AI summary
A system for operating a robotic prosthetic limb includes a brain machine interface (BMI) configured to sense neuron activity of a user and generate a signal indicating the sensed neuron activity and a robotic prosthetic limb configured to wirelessly communicate with the BMI. The robotic prosthetic limb includes motors connected configured to actuate the robotic prosthetic limb, a processor, and a memory. The memory includes instructions which when executed by the processor cause the system to: communicate a signal from the BMI to the robotic prosthetic limb, the signal including neuron activity of the user; input the neuron activity into four machine learning models configured to generate individual predictions of a movement of the robotic prosthetic limb; generate a motor control signal, for each of the one or more motors by averaging the individual predictions; and actuate the robotic prosthetic limb in response to the generated motor control signals.