Machinery Motion Planning With 3D Sensor Safety Zones
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Industrial machinery poses safety risks to humans due to unpredictable human movements and complex workspace interactions, requiring advanced safety-constrained motion planning that integrates real-time monitoring and dynamic adjustments to ensure safe operation while maximizing machinery efficiency.
Innovation Solution
A system utilizing multiple sensors (time-of-flight sensors, 3D LIDAR, and stereo vision cameras) to create a 3D representation of the workspace, identifying safe zones, and generating a constrained motion plan that avoids unsafe areas, with real-time updates and cost-based trajectory selection to ensure efficient and safe operation.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If traditional guarding approaches (cages, light curtains) are used to ensure human safety, then safety is improved, but workspace utilization and machinery efficiency deteriorate due to restricted access and operational interruptions
Solution Approach 1:
The system dynamically adjusts the robot's speed and stopping distance based on real-time detection of human presence and movement. When no human is detected, the robot operates at full speed. When a human is detected within a safe distance, the robot automatically reduces speed or stops, allowing the workspace to remain accessible while maintaining safety
Solution Approach 2:
The patent replaces traditional mechanical guarding systems (cages, physical barriers) with an optical sensing system (2D LIDAR, 3D time-of-flight cameras) that creates virtual safety zones. This substitution eliminates physical restrictions on workspace access while maintaining safety through automated detection and response
2Device complexity
If 2D LIDAR sensors are used for guarding, then intrusion detection is simplified, but detection accuracy deteriorates because they cannot distinguish depth, leading to overly conservative safety zones
Solution Approach 1:
The system merges multiple sensor types (2D LIDAR for basic radial distance measurement, 3D time-of-flight cameras for depth mapping, stereo vision cameras for additional spatial information) to create a comprehensive three-dimensional understanding of the workspace. This combination allows the system to accurately distinguish between objects at different depths while maintaining the simplicity of 2D LIDAR operation
Solution Approach 2:
The patent transitions from two-dimensional detection (2D LIDAR scanning planes) to three-dimensional detection by incorporating time-of-flight depth information and stereo vision. This adds the depth dimension, enabling the system to create accurate 3D safety zones and distinguish objects at different distances from the robot
3Reliability
If safety standards require stopping machinery at detected intrusions, then human safety is ensured, but operational efficiency deteriorates due to frequent interruptions
Solution Approach 1:
The system changes the response parameter from binary (stop/go) to continuous (speed modulation). Instead of immediately stopping the robot upon detecting a human, the system adjusts the robot's speed based on the distance and movement of the detected object. This allows the robot to maintain motion at reduced speed when safe, minimizing operational interruptions while ensuring safety
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
The system effectively prevents collisions and ensures safe operation by dynamically adjusting motion plans based on real-time sensor data, maximizing the use of machinery while adhering to stringent safety standards and minimizing downtime.
Implementation Method 1
A system utilizing multiple sensors (time-of-flight sensors, 3D LIDAR, and stereo vision cameras) to create a 3D representation of the workspace
Implementation Method 2
stereo vision cameras to create a 3D representation of the workspace
Data Source
AI summary
Systems and methods monitor a workspace for safety purposes using sensors distributed about the workspace. The sensors are registered with respect to each other, and this registration is monitored over time. Occluded space as well as occupied space is identified, and this mapping is frequently updated. Based on the mapping, a constrained motion plan of machinery can be generated to ensure safety.