3D Workspace Motion Planning for Safe Machinery Operation
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Industrial machinery poses safety risks to humans due to hazardous operating states, and existing guarding systems struggle to detect unsafe conditions effectively, particularly in complex workspaces where human movements and machinery interactions are unpredictable, leading to suboptimal motion planning and potential collisions.
Innovation Solution
A system utilizing multiple sensors such as 3D LIDAR, time-of-flight cameras, and stereo vision cameras to monitor a workspace, classify regions as occupied, unoccupied, or unknown, and dynamically adjust motion plans to ensure safe operation by identifying and avoiding unsafe zones, allowing for efficient and safe machinery operation within defined safe volumetric zones.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If traditional guarding systems (cages, light curtains, 2D LIDAR) are used to ensure safety, then safety standards are met, but workspace utilization is reduced and motion planning becomes suboptimal due to conservative safety zones
Solution Approach 1:
The patent transitions from 2D safety monitoring (light curtains, 2D LIDAR) to 3D safety monitoring using time-of-flight cameras and 3D LIDAR. This dimensional change enables accurate detection of human body parts in three-dimensional space, allowing the system to distinguish between safe and unsafe zones more precisely. The 3D depth information allows the robot to operate closer to humans while maintaining safety, thereby improving workspace utilization without compromising safety standards.
Solution Approach 2:
The system dynamically adjusts safety parameters based on real-time detection of human position and orientation. By continuously monitoring the 3D coordinates of human body parts and calculating their distance and angle relative to the robot, the system adapts the safety zone boundaries dynamically. This allows the robot to expand its operational workspace when humans are in safe positions while maintaining strict safety constraints when humans approach, thus resolving the contradiction between safety and productivity.
2Reliability
If 2D LIDAR or light curtains are used for guarding, then safety detection is implemented, but the robot must stop well beyond arm's-length distance, reducing operational efficiency and workspace flexibility
Solution Approach 1:
The system uses time-of-flight cameras and 3D LIDAR to capture three-dimensional depth information of the workspace. This enables the robot to detect human intrusions in 3D space rather than being constrained to 2D safety zones. The 3D detection capability allows the robot to distinguish between safe and unsafe regions more accurately, permitting operation at faster speeds when humans are outside the actual danger zone, thus improving operational speed while maintaining reliable intrusion detection.
Solution Approach 2:
The safety zone boundaries are made dynamic rather than static. The system continuously updates the safe and unsafe zones based on real-time detection of human position, velocity, and trajectory. This dynamic adjustment allows the robot to maintain higher operating speeds when humans are in safe positions while automatically reducing speed or stopping when humans enter unsafe zones, thereby resolving the contradiction between detection reliability and operational speed.
3Reliability
If conservative safety zones are enforced to meet safety standards, then safety is ensured, but the robot cannot utilize the full workspace, reducing productivity and increasing factory floor space requirements
Solution Approach 1:
The patent implements 3D safety monitoring that accurately maps the workspace in three dimensions. This enables the system to identify and enforce safety constraints only in the specific regions where human-robot interaction is hazardous, rather than enforcing conservative 2D safety zones that unnecessarily restrict the entire workspace. The 3D depth information allows precise delineation of safe and unsafe zones, maximizing the usable factory floor space while maintaining strict safety enforcement where needed.
Solution Approach 2:
The system dynamically modifies the safety zone parameters (boundary positions, volumes, and constraints) based on real-time detection of human position and robot operation state. This allows the safe workspace volume to expand when humans are absent or in safe positions, and contract when humans approach hazardous areas. Consequently, the robot can utilize more factory floor space productively while safety constraints are strictly enforced only when and where necessary, resolving the contradiction between safety enforcement and space utilization.
4Reliability
If 3D sensors are used to detect human position accurately, then tighter interlock between machine and human actions is achieved, but system complexity and cost increase
Solution Approach 1:
The time-of-flight camera system serves multiple functions: it detects human position, measures distance, determines orientation, and provides 3D spatial mapping for motion planning. By using a single multi-functional sensor system rather than multiple specialized sensors, the patent achieves high safety interlock precision while minimizing system complexity. The 3D depth information from the time-of-flight camera is utilized across multiple safety and operational functions, reducing the need for additional sensors and simplifying the overall system architecture.
Solution Approach 2:
The patent combines safety detection, workspace mapping, and motion planning functions into a unified 3D sensing and processing system. The time-of-flight camera and 3D LIDAR data are integrated with the robot's control system to simultaneously perform safety monitoring and operational planning. This merging of functions reduces system complexity by eliminating separate sensor systems for safety and operation, while achieving precise safety interlock through comprehensive 3D awareness of the workspace and human position.
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 by dynamically updating safe zones in real-time, ensuring stringent safety standards are met while maximizing the use of machinery and workspace efficiency, even in complex environments with unpredictable human and machinery movements.
Implementation Method 1
2D LIDAR sensors that use active optical sensing to detect the minimum distance to an obstacle along a series of rays emanating from the sensor
Implementation Method 2
3D depth information using, for example, 3D time-of-flight cameras
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.