Depth Sensor Verification of Robot Position in Shared Workspaces
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing systems for monitoring shared workspaces between humans and robots lack accuracy in verifying robot position and velocity data, leading to potential safety hazards due to reliance on potentially unreliable data from robot controllers.
Innovation Solution
A method and system that utilize sensors to independently verify robot position and velocity data by comparing sensor-derived three-dimensional representations with data from the robot controller, ensuring accurate calculation of exclusion zones and safe workspace maintenance.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Ease of operation
If robot position and velocity data is retrieved from robot controller via standard communication interfaces, then the data is readily accessible and easy to obtain, but the data is prone to inaccuracies and reliability issues
Solution Approach 1:
The patent introduces an intermediary verification system consisting of external sensors (cameras, depth sensors, LIDAR) and an analysis module that independently measures robot position and compares it with controller-provided data. This intermediary layer validates the reliability of data from the robot controller without eliminating the ease of retrieval through standard interfaces.
Solution Approach 2:
The system implements feedback by continuously comparing sensor-derived position data with controller-reported position data, generating verification results that feedback into the safety monitoring system. This feedback mechanism detects discrepancies and triggers appropriate safety responses, ensuring data reliability while maintaining operational simplicity.
2Measurement precision
If three-dimensional optoelectronic sensors are used to monitor three-dimensional space, then the system can precisely identify relative locations and adapt to dynamic workplaces, but the system becomes computationally intensive and requires knowing precise position and movement velocity of robot
Solution Approach 1:
The patent creates a synthetic depth map (a copy or representation) of what the robot should see based on controller data, and compares it with actual sensor data. This copying approach allows verification without requiring the system to fully process and understand all three-dimensional spatial information, reducing computational intensity while maintaining precision.
Solution Approach 2:
The system extracts only the essential verification data needed for safety monitoring - specifically comparing depth pixel values at robot locations - rather than processing the entire three-dimensional spatial model. This extraction approach reduces computational complexity while preserving measurement precision for safety-critical parameters.
3Ease of manufacture
If light curtain is used to define exclusion zone, then the system is low cost and easy to configure, but the exclusion zone is static and lacks precision in dynamic workplaces
Solution Approach 1:
The patent transitions from static light curtain exclusion zones to dynamic exclusion zones that are continuously updated based on real-time robot position data from sensors and controllers. The exclusion zone moves and adapts with the robot's motion, maintaining precision in dynamic workplaces while keeping the underlying light curtain technology simple and easy to configure.
Data Source
Figure 1
Figure 2
Figure 3~4
AI summary
The disclosure relates to a system and method for verifying robot data that is used by a safety system monitoring a workspace shared by a human and robot. One or more sensors monitoring the workspace are arranged to obtain a three-dimensional view of the workspace. Raw data from each of the sensors is acquired and analyzed to determine the positioning and spatial relationship between the human and robot as both move throughout the workspace. This captured data is compared to the positional data obtained from the robot to assess whether discrepancies exist between the data sets. If the information from the sensors does not sufficiently match the data from the robot, then a signal from the system may be sent to deactivate the robot and prevent potential injury to the human.