Robot Process Definition Graph Scheduling Across Workcells
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Manual programming of robotic movements in industrial settings is tedious, time-consuming, and error-prone, and schedules generated for one workcell are often incompatible with different workcells, making it difficult to predict task completion times and optimize robotic efficiency.
Innovation Solution
A system that uses an underconstrained process definition graph and iterative transformers to generate robotics schedules, allowing for flexible and efficient programming of robots, reducing manual input, and enabling the reuse of transformers for different tasks and environments.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If manual programming is used to dictate robotic movements, then precise control over robot actions is achieved, but the programming process becomes tedious, time-consuming, and error-prone
Solution Approach 1:
The patent introduces an intermediary system consisting of a process definition graph and transformer-based planning algorithm that acts as a mediator between high-level process specifications and low-level robotic control commands. This intermediary automatically generates detailed movement schedules from abstract process definitions, eliminating the need for manual programming while maintaining precise control over robotic actions.
Solution Approach 2:
The patent replaces the mechanical/manual programming process with an automated computational system. Instead of manually creating detailed movement schedules, the system uses a planning algorithm that automatically generates optimized schedules from process definitions, substituting human effort with automated intelligence while preserving control precision.
2Manufacturing precision
If manual programming is used for each workcell, then specific task requirements are met, but the schedules cannot be reused across different workcells with varying robots, numbers of robots, or physical dimensions
Solution Approach 1:
The patent creates a universal process definition graph framework that can represent tasks across different workcells in a standardized manner. The transformer-based planning system automatically adapts these universal definitions to specific workcell configurations, enabling the same process definitions to generate appropriate schedules for various robots, robot counts, and physical dimensions while maintaining task execution accuracy.
Solution Approach 2:
The patent introduces dynamic adaptability where the planning system can adjust generated schedules based on specific workcell parameters. The transformer architecture allows the system to dynamically modify movement plans according to actual robot capabilities, workcell dimensions, and task requirements, enabling reuse across diverse environments while preserving task accuracy.
3Productivity
If more robots are added to increase productivity, then task completion speed improves, but the complexity of coordinating and scheduling robot movements increases
Solution Approach 1:
The patent segments the scheduling problem into manageable components using a process definition graph structure. Each task is broken down into discrete steps represented as graph nodes, and the transformer-based planner processes these segments systematically. This segmentation enables efficient coordination of multiple robots by treating each task component independently while maintaining overall schedule coherence, thus managing complexity even as robot numbers increase.
Solution Approach 2:
The patent introduces an intermediary planning layer that automatically manages the coordination complexity of multiple robots. This intermediary system uses the process definition graph and transformer architecture to generate coherent schedules that coordinate robot movements, resolve conflicts, and optimize task completion speed without requiring manual management of the increasing scheduling complexity.
4Ease of manufacture
If traditional scheduling methods are used, then simplicity of implementation is maintained, but the ability to predict task completion times and optimize robotic efficiency is limited
Solution Approach 1:
The patent incorporates feedback mechanisms where the planning system evaluates generated schedules against goal criteria and iteratively improves them. The transformer-based approach allows the system to assess task completion times and optimize schedules accordingly, providing predictable timing while maintaining implementation simplicity through automated optimization rather than complex manual scheduling.
Data Source
AI summary
Methods, systems, and apparatus, including computer programs encoded on computer storage media, for performing robot planning using a process definition graph. One of the methods includes receiving an initial underconstrained process definition graph for one or more robots, wherein the process definition graph is a directed acyclic graph having constraint nodes and action nodes. A plurality of transformers are repeatedly applied to the initial process definition graph, wherein each application of a transformer generates a respective modified process definition graph according to the constraint nodes of the process definition graph, wherein applying the plurality of transformers generates a schedule that specifies which of the one or more robots are to perform which of one or more actions represented by actions nodes according to constraints imposed by the constraint nodes in the process definition graph.