Development of an object recognition system for the PrHand hand prosthesis based on machine learning.

Project: Research Project

Project Details


General objective:

●Develop an object recognition system for the PrHand hand prosthesis based on pressure sensors and a Machine Learning (ML) system.

Specific objectives:

●O1. Review of the state of the art for the identification of force sensors used in hand prostheses and robotic devices, ML methods for object identification and Hardware used to implement the ML system in real time.

●O2. Integrate and characterize sensors that allow the measurement of the grip strength of the PrHand hand prosthesis in real time.

●O3. Generate a data set with different objects held by the PrHand prosthesis and train different ML models.

●O4. Evaluate the performance of ML models and select the most appropriate to implement in the system.

●O5. Check the operation of the ML model in an experiment holding objects in real time.


Exoskeleton and (industry or industrial) and empowerment and rehabilitation and (elbow or forearm)

Commitments / Obligations

●A sensor system that provides grip strength in real time in the PrHand prosthesis.

●Object recognition system for the PrHand prosthesis based on ML.

●A data set of the objects used for testing the ML system.

●A research article Q1-Q2 on the development and validation of the developed system.

● A half-day seminar will be held integrating EICT and EMCS students to disseminate the results of the project.
Effective start/end date5/17/225/30/24

UN Sustainable Development Goals

In 2015, UN member states agreed to 17 global Sustainable Development Goals (SDGs) to end poverty, protect the planet and ensure prosperity for all. This project contributes towards the following SDG(s):

  • SDG 9 - Industry, Innovation, and Infrastructure

Main Funding Source

  • Starter Funds


  • Bogotá D.C.


Explore the research topics touched on by this project. These labels are generated based on the underlying awards/grants. Together they form a unique fingerprint.