Multi-Cell 3D Workspace Mapping for Occlusion-Safe Monitoring
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current systems fail to reliably and safely detect, classify, and track objects, including humans, in 3D across multiple workcells in industrial environments, due to limitations in existing sensors and monitoring systems that struggle with dynamic occlusions and 3D vision field-of-view constraints.
Innovation Solution
A safety system utilizing a network of 3D sensors and controllers that generate a 3D representation of workcells, classify volumetric zones, and communicate object movements across workcells, allowing for real-time monitoring and safe operation by integrating sensors' data to mark safe and potentially occupied areas, and adjust machinery operations accordingly.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If a network of 3D sensors is deployed across multiple workcells to enable comprehensive monitoring, then safety and reliability of detecting objects and humans is improved, but device complexity and cost increase
Solution Approach 1:
The system divides the factory floor into multiple workcells, each with its own set of 3D sensors and controller. Each workcell operates semi-independently, monitoring its own volume while communicating with adjacent workcells. This segmentation allows comprehensive coverage without requiring a single complex centralized system, reducing overall device complexity while maintaining reliability.
Solution Approach 2:
The patent combines multiple 3D sensor data streams from different workcells into a unified factory-floor model. Controllers exchange information about objects and humans moving between workcells, merging local perceptions into a comprehensive safety monitoring system that achieves high reliability through data integration.
2Measurement precision
If 3D sensors are used to accurately detect and track objects in three-dimensional space, then measurement precision is improved, but difficulty of detecting and measuring increases due to dynamic occlusions and field-of-view constraints
Solution Approach 1:
The system transitions from 2D camera images to 3D volumetric representation using depth cameras and LIDAR sensors. This dimensional change enables accurate detection of object positions, sizes, and movements in three-dimensional space, overcoming the limitations of 2D imaging where occlusions and perspective distortions make measurement difficult.
Solution Approach 2:
The patent introduces a factory-control system that acts as an intermediary, receiving raw 3D sensor data, processing it into structured object models, and distributing relevant information to adjacent workcells. This intermediary layer simplifies the detection task by pre-processing data and filtering out irrelevant information before further analysis.
3Productivity
If real-time monitoring and communication between workcells is implemented, then productivity and operational efficiency are improved, but use of energy and computational resources increases
Solution Approach 1:
The system extracts only the essential safety-critical information from 3D sensor data and transmits it between workcells, rather than communicating complete raw datasets. Controllers exchange condensed object models, positions, and movement predictions, reducing computational energy consumption while maintaining real-time monitoring capability and productivity.
4Measurement precision
If safe volumetric zones are dynamically mapped and updated in real-time, then safety zone accuracy is improved, but device complexity and computational requirements increase
Solution Approach 1:
The system dynamically updates safe volumetric zones based on real-time sensor data and object movements. Instead of static safety boundaries, the controller continuously recalculates safe zones by integrating 3D sensor information about objects and humans, allowing accurate safety zone mapping that adapts to changing conditions while managing complexity through incremental updates.
Applied Scientific Principles
This section explains which scientific principles are used to turn an abstract innovation direction into a practical engineering solution.
Function Achieved in This Case
Enables reliable and safe monitoring of humans and machinery across multiple workcells, reducing the risk of collisions and improving operational efficiency by accurately identifying safe regions and predicting object movements, thus enhancing factory floor safety and productivity.
Implementation Method 1
a plurality of sensors distributed about the workcell, where each of the sensors is associated with a grid of pixels for recording images of a portion of the workcell within a sensor field of view
Data Source
Figure 1
Figure 2
Figure 3
AI summary
Safety systems in distributed factory workcells intercommunicate or communicate with a central controller so that when a person, robot or vehicle passes from one workcell or space into another on the same factory floor, the new workcell or space need not repeat the tasks of analysis and classification and can instead immediately integrate the new entrant into the existing workcell or space-monitoring schema. The workcell or space can also communicate attributes such as occlusions, unsafe areas, movement speed, and object trajectories, enabling rapid reaction by the monitoring system of the new workcell or space.