US Patent Application 18043623. MEDICAL ARM CONTROL SYSTEM, MEDICAL ARM DEVICE, MEDICAL ARM CONTROL METHOD, AND PROGRAM simplified abstract

From WikiPatents
Jump to navigation Jump to search

MEDICAL ARM CONTROL SYSTEM, MEDICAL ARM DEVICE, MEDICAL ARM CONTROL METHOD, AND PROGRAM

Organization Name

Sony Group Corporation


Inventor(s)

DAISUKE Nagao of TOKYO (JP)

MEDICAL ARM CONTROL SYSTEM, MEDICAL ARM DEVICE, MEDICAL ARM CONTROL METHOD, AND PROGRAM - A simplified explanation of the abstract

This abstract first appeared for US patent application 18043623 titled 'MEDICAL ARM CONTROL SYSTEM, MEDICAL ARM DEVICE, MEDICAL ARM CONTROL METHOD, AND PROGRAM

Simplified Explanation

The patent application describes a medical arm control system that uses supervised learning and reinforcement learning techniques to autonomously control the movement of a medical arm.

  • The system includes a first determination unit that uses first input data and first training data to perform supervised learning and generate an autonomous movement control model for the medical arm.
  • A second determination unit uses second input data and second training data to perform supervised learning and generate a reward model. This reward model calculates a reward to be given to the movement of the medical arm.
  • A reinforcement learning unit then uses third input data to execute the reward model and reinforce the autonomous movement control model using the reward calculated by the reward model.


Original Abstract Submitted

Provided is a medical arm control system including a first determination unit () that performs supervised learning using first input data and first training data and generates an autonomous movement control model for autonomously moving a medical arm, a second determination unit () that performs supervised learning using second input data and second training data and generates a reward model for calculating a reward to be given to a movement of the medical arm, and a reinforcement learning unit () that executes the reward model using third input data and reinforces the autonomous movement control model using the reward calculated by the reward model.