3D Occupancy Envelope Planning for Human-Robot Separation
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Conventional industrial robots lack accurate dynamic modeling, leading to safety concerns in collaborative human-robot applications due to limitations in joint friction, drive nonlinearities, and tracking errors, which result in unpredictable robot movements and inadequate safety protocols for human-robot collaboration.
Innovation Solution
The development of a system that generates and updates 3D spatial representations of workspaces to identify potential occupancy envelopes (POEs) for both robots and humans, allowing for constrained motion planning to ensure safe operation by restricting robot movements within defined 'keep-in' or 'keep-out' zones, using sensors to monitor and adjust robot trajectories in real-time.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Productivity
If conventional industrial robots are used in collaborative human-robot applications, then productivity and automation capabilities are improved, but safety and reliability deteriorate due to unpredictable robot movements caused by manufacturing tolerances, joint friction, drive nonlinearities, and tracking errors
Solution Approach 1:
The system performs preliminary action by computing potential occupancy envelopes (POEs) before robot execution, identifying all possible trajectories the robot may follow during task performance. This advance planning allows the safety system to know where the robot might be before movement occurs, enabling proactive safety measures rather than reactive responses to unpredictable movements
Solution Approach 2:
The invention transitions from traditional 2D safety monitoring to 3D spatial reasoning by computing volumetric POEs that encompass all possible robot trajectories in three-dimensional space. This dimensional expansion allows the system to account for manufacturing tolerances, joint friction, and drive nonlinearities by representing uncertainty as volumetric regions rather than single trajectories
2Reliability
If robot movements are constrained to ensure safety in collaborative workspaces, then safety and reliability are improved, but productivity and workspace utilization deteriorate due to limited movement freedom
Solution Approach 1:
The system applies dynamics by computing POEs that are specific to each task being performed, rather than using fixed conservative boundaries. The POEs dynamically adapt to the actual robot trajectories and task requirements, allowing the robot to utilize more of the workspace when task-specific analysis shows it is safe to do so, thereby improving productivity while maintaining safety
Solution Approach 2:
The invention implements local quality by computing POEs for specific regions of the workspace based on actual task requirements rather than applying uniform safety constraints throughout the entire workspace. This allows different levels of workspace access in different regions, maximizing productive use of space while maintaining safety where needed
3Device complexity
If traditional safety systems like light curtains or 2D area sensors are used, then safety monitoring is simplified, but workspace constraints increase and collaborative use is limited
Solution Approach 1:
The system transitions from 2D safety monitoring to 3D spatial reasoning by computing volumetric POEs that encompass all possible robot trajectories in three-dimensional space. This dimensional expansion allows the system to account for manufacturing tolerances, joint friction, and drive nonlinearities by representing uncertainty as volumetric regions rather than single trajectories
Solution Approach 2:
The POE computation framework serves multiple functions: it identifies safe human workspaces, plans robot trajectories, evaluates collision risks, and optimizes workspace utilization. This multi-functionality replaces multiple separate safety systems with a unified approach that addresses both safety and productivity requirements
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.