Virtual Safety Cages for Dynamic Robot Workspace Boundaries
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Robotic devices face challenges in safely navigating shared industrial environments with humans and other objects, as they struggle to dynamically adjust their operational space to avoid collisions and optimize space usage, especially with uncertainties in their mechanical components and the movements of nearby objects.
Innovation Solution
A method for robotic devices to continuously estimate their future trajectories and those of nearby objects, dynamically determining and adjusting a 'virtual safety cage' to enclose their operational space, using sensors and databases to predict potential intersections and provide visual or audio indications of this space to ensure safe operation and efficient use of shared environments.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If a static safety cage is used to enclose robotic device operational space, then safety is improved by preventing human entry into dangerous zones, but space utilization deteriorates as the fixed cage occupies excessive space and prevents flexible reconfiguration
Solution Approach 1:
The patent transforms the static safety cage into a dynamic virtual safety cage that continuously adapts its boundaries based on real-time trajectory predictions of the robotic device and nearby objects. The virtual cage is defined by a computing device that calculates reachable spaces within predetermined time periods and adjusts the enclosed area dynamically, allowing the physical space to be utilized more efficiently while maintaining safety constraints.
2Reliability
If the virtual safety cage is expanded to account for uncertainties in mechanical components and object movements, then safety is improved by covering all potential trajectories, but space utilization deteriorates as the operational space becomes overly conservative
Solution Approach 1:
The patent applies partial action by calculating virtual safety cages based on predetermined time periods that balance safety requirements with space efficiency. Rather than enclosing all theoretically possible trajectories indefinitely, the system limits the prediction horizon to a reasonable time frame, enclosing only the reachable space within that period. This prevents excessive expansion of the virtual cage while still accounting for uncertainties in a practical manner.
Solution Approach 2:
The system dynamically adjusts parameters of the virtual safety cage including the predetermined time period, boundary definitions, and enclosed volume based on operational context. The computing device modifies these parameters to optimize the balance between safety coverage and space utilization, shrinking the virtual cage when uncertainties are low and expanding it when risks increase, rather than maintaining a fixed conservative boundary.
3Reliability
If continuous trajectory estimation and virtual safety cage adjustment are implemented, then safety and space optimization are improved, but device complexity increases due to additional sensors, processors, and coordination systems
Solution Approach 1:
The patent introduces a computing device as an intermediary that centralizes the complex calculations for trajectory estimation and virtual safety cage determination. Rather than distributing complex computational loads across multiple robotic devices and sensors, the computing device acts as a mediator that receives data from various sources, performs the sophisticated predictions, and outputs control decisions, thereby managing system complexity in a centralized manner.
Solution Approach 2:
The system creates a virtual copy or digital twin of the physical environment and robotic device trajectories. The computing device generates virtual representations of reachable spaces and safety boundaries that mirror the physical world, allowing complex safety calculations to be performed in the virtual domain without directly complicating the physical system architecture. This virtual modeling approach simplifies the interface between sensing and actuation systems.
Data Source
Figure 1A
Figure 1B
Figure 2
AI summary
Methods and systems for determining and presenting virtual safety cages are provided. An example method may involve receiving an instruction for a robotic device to perform a physical action in a physical environment occupied by the robotic device. The method may also involve, responsive to receiving the instruction, and based on one or more parameters of one or more physical components of the robotic device, determining one or more estimated trajectories along which the one or more physical components of the robotic device are estimated to move as the robotic device performs the physical action. The method may further involve, based on the one or more estimated trajectories, determining a virtual representation of a space that the robotic device is estimated to occupy in the physical environment while performing the physical action. The method may then involve providing, into the physical environment, an indication of a location of the space.