Robot Control Learning for Human Interference Avoidance
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Conventional control devices for robots experience productivity degradation when a person enters their operation area, as they either stop or reduce speed to avoid collisions, which can lead to inefficient operation.
Innovation Solution
A control device equipped with a machine learning system that observes the robot's and person's states, determines interference conditions, and learns optimal commands to adjust the robot's speed and path dynamically using reinforcement learning algorithms, allowing the robot to continue operating safely and efficiently.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If the robot stops or reduces speed when a person enters the operation area, then safety is improved, but productivity deteriorates
Solution Approach 1:
The robot's speed and operation mode are dynamically adjusted based on the detected state of the person. When a person is detected in the operation area, the robot transitions from high-speed automatic operation to slow-speed manual operation or stops, providing dynamic adaptability between safety and productivity based on real-time conditions
Solution Approach 2:
The system continuously detects the person's presence and state in the operation area, providing feedback to the control device. This feedback loop enables real-time adjustment of robot operation, allowing the system to maintain productivity when safe and ensure safety when persons are present
2Reliability
If the robot changes path to avoid a person, then safety is improved, but operation efficiency deteriorates
Solution Approach 1:
The robot's operation mode is dynamically changed from automatic path following to manual operation based on person detection. This allows the robot to avoid persons safely while maintaining operational flexibility, rather than rigidly changing paths which would reduce efficiency
Data Source
AI summary
A control device that outputs a command for a robot includes a machine learning device that learns a command for the robot. The machine learning device includes a state observation unit that observes a state of the robot and a state of a person present in a peripheral area of the robot, as state variables representing a current state of an environment, a determination data acquisition unit that acquires determination data representing an interference state between the robot and the person, and a learning unit that learns the state of the robot, the state of the person present in the peripheral area of the robot, and the command for the robot obtained by associating the state of the robot and the state of the person present in the peripheral area of the robot by using the state variables and the determination data.