Robot Task Planning With Measurement Variance Thresholds
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Manual programming of robotic movements in industrial robotics is tedious, time-consuming, and error-prone, and existing systems lack the ability to adapt process definitions across different workcells with varying physical dimensions, leading to decreased confidence in sensor measurements and impaired robotic control.
Innovation Solution
A system that generates modified process definitions for robotic control systems by dynamically estimating measurement variances and interpolating sequences of actions, allowing for precise control of robot movements and maintaining a threshold level of confidence in workcell measurements, even with deformable or occluded objects, by inserting additional measurement actions and adjusting sensor positions.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Manufacturing precision
If manual programming is used to dictate robotic movements, then precise control of robot actions can be achieved, but the programming process becomes tedious, time-consuming, and error-prone
Solution Approach 1:
The system enables robots to automatically perform measurement actions and update process definitions without human intervention. The robotic control system autonomously determines when measurements are needed, executes measurement actions, and updates process definitions based on measurement variances, eliminating the need for manual programming while maintaining precision.
Solution Approach 2:
The system dynamically adjusts process definitions by inserting measurement actions at optimal points in the sequence based on computed measurement variances. This automatically optimizes the timing and placement of measurements without manual programming, reducing programming time while maintaining control precision.
2Manufacturing precision
If a process definition is manually generated for one workcell, then specific task requirements can be met, but the plan cannot be used for other workcells with different physical dimensions
Solution Approach 1:
The system dynamically adapts process definitions to different workcells by computing measurement variances specific to each workcell's physical properties and sensor configurations. The process definition is automatically modified to insert measurement actions at appropriate points, enabling the same base process to be adapted to various workcells without manual reprogramming.
Solution Approach 2:
The system changes parameters of the process definition based on workcell-specific characteristics such as physical dimensions and sensor positions. By computing measurement variances that account for these parameters, the system automatically generates workcell-adapted process definitions that maintain task execution accuracy across different environments.
3Measurement precision
If constant sensor measurement is performed to maintain confidence in measurements, then measurement accuracy can be ensured, but difficulty increases when robots move in and out of sensor field of view or when objects are deformable
Solution Approach 1:
The system performs preliminary computation of measurement variances for each action in the sequence before execution. Based on these pre-computed variances, the system determines in advance where measurement actions should be inserted to maintain confidence levels, avoiding the need for constant measurement while ensuring accuracy where needed.
Solution Approach 2:
The system uses feedback from computed measurement variances to dynamically adjust the measurement strategy. By monitoring the accumulated measurement variance and comparing it against confidence thresholds, the system automatically inserts measurement actions only when necessary to maintain measurement confidence, reducing unnecessary measurements while ensuring accuracy.
4Measurement precision
If additional measurement actions are inserted to maintain measurement confidence, then measurement accuracy improves, but the sequence of actions becomes more complex and time-consuming
Solution Approach 1:
The system pre-computes measurement variances for all actions in the sequence and determines the optimal placement of measurement actions before execution. This preliminary analysis ensures that measurement actions are inserted only where necessary to maintain confidence levels, minimizing the number of measurement actions and reducing overall execution time while maintaining accuracy.
Solution Approach 2:
The system optimizes the process definition by changing parameters such as the timing and placement of measurement actions based on computed variances. By strategically positioning measurement actions only where measurement confidence would otherwise degrade below thresholds, the system maintains measurement accuracy while minimizing the time added to the action sequence.
Data Source
AI summary
Methods, systems, and apparatus, including computer programs encoded on computer storage media, for modifying a process definition to ensure accuracy, timeliness, or both of workcell measurement. One of the methods includes receiving an initial process definition for a process to be performed by a robot, wherein the process definition defines a sequence of actions to be performed in a workcell, and wherein a first action in the sequence of actions has an associated measurement tolerance; computing a predicted accumulated measurement variance for each of one or more actions that occur before the first action in the sequence; determining that the predicted accumulated measurement variance for the one or more actions that occur before the first action in the sequence exceeds a threshold; and in response, generating a modified process definition that inserts a measurement action at a location in the sequence before the first action.