Potential Occupancy Envelopes for Safe Human-Robot Motion Planning
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Conventional industrial robots pose safety risks due to unpredictable movements and lack of accurate dynamic models, limiting their safe operation in collaborative human-robot applications, as they often rely on kinematic definitions that do not account for human presence and environmental changes.
Innovation Solution
A safety system that models potential occupancy envelopes (POEs) of robots and humans in a 3D workspace, using sensors to generate real-time spatial representations and constrained motion plans to ensure safe operation by avoiding unsafe regions and maintaining protective separation distances.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Productivity
If conventional industrial robots operate in collaborative human-robot applications, then productivity and human capability are augmented, but safety risks increase due to unpredictable movements and lack of accurate dynamic models
Solution Approach 1:
The system performs preliminary computation of potential occupancy envelopes (POEs) for the robot arm and human operator before actual operation. By pre-calculating all possible positions the robot arm may occupy during task execution and comparing this with pre-computed human POEs, the system identifies unsafe regions in advance and adjusts the robot trajectory to avoid them, ensuring safety before collisions can occur.
Solution Approach 2:
The system creates computational copies or representations of the robot arm and human operator in the form of potential occupancy envelopes. These POEs are virtual models that represent the spatial extent and possible positions of physical objects. By operating with these computational copies and their intersections, the system can predict and prevent unsafe interactions without requiring complex real-time sensing and reaction mechanisms.
2Productivity
If robot arms move rapidly and cover large workspaces, then productivity increases, but positioning accuracy decreases due to inertia, manufacturing tolerances, and dynamic effects
Solution Approach 1:
The system pre-computes the potential occupancy envelope of the robot arm based on its kinematic model, task specification, and dynamic characteristics including inertia and manufacturing tolerances. This POE represents all possible positions the arm may occupy considering its speed, acceleration, and positioning accuracy limitations. By having this information available before operation, the system can plan trajectories that account for these dynamic effects in advance.
Solution Approach 2:
The system transforms the positioning accuracy problem from a point-based consideration to a volumetric one by computing the potential occupancy envelope. Instead of tracking a single robot arm position, the system works with a three-dimensional region that encompasses all possible positions the arm may occupy. This dimensional transformation allows the system to handle positioning uncertainty and dynamic effects more effectively by operating in configuration space rather than physical space.
3Reliability
If protective separation distances are maintained between robot and human, then safety is ensured, but workspace utilization decreases
Solution Approach 1:
The system pre-computes the potential occupancy envelopes of both the robot arm and human operator, then performs an intersection operation to identify unsafe regions where their POEs overlap. By knowing these unsafe regions in advance, the system can adjust the robot trajectory to navigate around them rather than maintaining conservative fixed separation distances throughout the workspace. This allows the robot to operate closer to humans when safe, maximizing workspace utilization while ensuring safety.
Solution Approach 2:
The system applies safety constraints locally rather than globally. Instead of maintaining uniform protective separation distances throughout the entire workspace, the system identifies specific unsafe regions where the robot and human POEs intersect and applies trajectory adjustments only in those localized areas. In regions where no intersection occurs, the robot can operate without additional separation constraints, thereby maximizing workspace utilization while maintaining safety where needed.
Data Source
AI summary
Spatial regions potentially occupied by a robot (or other machinery) or portion thereof and a human operator during performance of all or a defined portion of a task or an application are computationally estimated. These “potential occupancy envelopes” (POEs) may be based on the states (e.g., the current and expected positions, velocities, accelerations, geometry and/or kinematics) of the robot and the human operator. Once the POEs of human operators in the workspace are established, they can be used to guide or revise motion planning for task execution.