Potential Occupancy Envelopes for Safe Human-Robot Motion Planning
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 kinematic and dynamic performance, as they often rely on incomplete or inaccurate parameter values and do not account for human presence and movement, resulting in potential safety hazards.
Innovation Solution
A system that models and visualizes potential occupancy envelopes (POEs) for both robots and humans, using 3D sensors to dynamically compute and update spatial regions of occupancy, allowing for constrained motion planning to ensure safe operation by restricting robot movements within safe zones and maintaining a protective separation distance from humans.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Productivity
If conventional industrial robots operate in collaborative human-robot workspaces, then productivity and human capability are augmented, but safety hazards increase due to inaccurate dynamic modeling and inability to predict robot trajectories
Solution Approach 1:
The system performs preliminary computation of potential occupancy envelopes (POEs) before robot execution. The safety system computationally generates 3D spatial representations and identifies regions potentially occupied by humans augmented by envelopes of anticipated movements, then uses these pre-computed safety zones to generate constrained motion plans that ensure safety while maintaining productivity
Solution Approach 2:
The patent introduces an intermediary safety system that acts as a mediator between the robot controller and the physical robot. This safety system receives the robot's intended trajectory, computationally generates POEs, and returns constrained motion plans that satisfy both productivity requirements and safety constraints, resolving the contradiction between operation and safety
2Power
If robot arms with large inertia are used for industrial tasks, then strength and speed are achieved, but stopping distance increases significantly causing safety concerns
Solution Approach 1:
The safety system computationally generates POEs based on the robot's current state (position, velocity, acceleration) and dynamic model parameters (inertia, friction, drive nonlinearities) to predict stopping distances before the robot actually moves. This allows the system to account for the significant stopping distance of high-power robot arms while maintaining their strength and speed capabilities
Solution Approach 2:
The patent transitions from traditional 2D safety zones to 3D potential occupancy envelopes. By computationally generating 3D spatial representations and incorporating the robot's dynamic characteristics (inertia, acceleration, deceleration), the system creates volumetric safety zones that accurately represent the robot's movement potential including its stopping distance, resolving the contradiction between power and stopping distance
3Reliability
If traditional guarding systems or light curtains are used to ensure safety, then safety is maintained, but workspace collaboration flexibility is constrained
Solution Approach 1:
The system replaces static guarding systems with dynamic potential occupancy envelopes. The POEs are computationally generated based on the robot's real-time state (position, velocity, acceleration) and are updated continuously during operation. This allows the safety zones to adapt dynamically to the robot's movement, maintaining safety while enabling flexible human-robot collaboration without physical barriers
Solution Approach 2:
The patent substitutes mechanical guarding systems and light curtains with a computational safety system. Instead of physical barriers or optical sensors that create fixed safety zones, the system uses computational generation of 3D spatial representations and POEs based on the robot's dynamic model, replacing mechanical and optical safety systems with an intelligent computational approach that provides both safety and flexibility
4Manufacturing precision
If robot trajectory accuracy is improved through better control systems, then positioning precision increases, but device complexity and cost increase
Solution Approach 1:
The safety system implements feedback by continuously monitoring the robot's actual trajectory and comparing it with the computationally generated POEs. The system uses feedback from the robot's state (position, velocity, acceleration) to update the POEs and adjust the constrained motion plan in real-time, maintaining positioning accuracy through computational correction rather than requiring complex hardware modifications
Solution Approach 2:
The patent accounts for real-world parameter variations (manufacturing tolerances, joint friction, drive nonlinearities, backlash, compliances) by incorporating them into the dynamic model used for POE computation. Rather than attempting to physically eliminate these sources of error through complex control systems, the system changes the approach by using computational parameter adjustment and prediction to compensate for these variations, achieving acceptable positioning accuracy without excessive complexity
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.