Robot Motion Node Recombination for Conflict-Free Scheduling
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Robotics planning requires immense manual programming, which is tedious, time-consuming, and error-prone, and results in schedules that are often incompatible across different workcells due to varying physical constraints, making it difficult to predict task completion times effectively.
Innovation Solution
A system generates schedules for robots using a process definition graph, applying transformers to split and combine motion nodes, eliminating conflicts while minimizing time, by determining splitting criteria and modifying the graph to schedule motions independently or combine them when conflicts resolve.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Ease of manufacture
If manual programming is used to dictate robotic movements, then the schedule can be customized for specific tasks, but the programming becomes tedious, time-consuming, and error-prone
Solution Approach 1:
The patent replaces manual mechanical programming with an automated system that uses process definition graphs and transformers to generate robotic schedules. The system automatically processes motion nodes, identifies conflicts, and generates optimized schedules without requiring tedious manual programming, thereby reducing both time consumption and error rates while maintaining task-specific customization capabilities
Solution Approach 2:
The system enables self-service by allowing the robotic scheduling system to automatically generate and optimize its own schedules using transformers that process motion nodes and resolve conflicts autonomously. This eliminates the need for external manual programming intervention while still producing customized schedules appropriate for specific tasks and workcells
2Adaptability or versatility
If manual programming is used for one workcell, then the schedule can be optimized for that specific environment, but it cannot be reused for other workcells with different physical properties
Solution Approach 1:
The patent implements universality by creating a standardized process definition graph framework that can be applied across multiple workcells. The transformers and motion node processing logic serve universal functions that adapt to different physical environments without requiring separate manual programming for each workcell, enabling schedule reusability while maintaining optimization for specific tasks
Solution Approach 2:
The system enables parameter changes by allowing the process definition graphs and motion nodes to be configured with workcell-specific parameters such as physical dimensions, robot capabilities, and task requirements. This allows the same fundamental scheduling framework to adapt to different workcells through parameter adjustment rather than requiring complete reprogramming
3Reliability
If motion nodes are scheduled independently without splitting, then the scheduling process is simpler, but conflicts between robot paths cannot be resolved
Solution Approach 1:
The patent applies segmentation by dividing motion nodes into smaller, manageable segments that can be processed independently. The system identifies conflict regions and splits motion nodes at entry and exit points of these regions, allowing each segment to be scheduled and optimized separately while ensuring conflict-free overall scheduling through systematic recombination
4Adaptability or versatility
If the process definition graph is modified frequently to adapt to different tasks, then the system becomes more flexible, but error tracking and debugging become more difficult
Solution Approach 1:
The patent implements feedback mechanisms that track modifications to the process definition graph, enabling error tracking and debugging while maintaining flexibility. The system monitors changes to motion nodes and graph structure, providing feedback loops that help identify and correct errors systematically even as the graph is frequently modified to adapt to different tasks
Data Source
AI summary
Methods, systems, and apparatus, including computer programs encoded on computer storage media, for optimizing a plan for one or more robots using a process definition graph. One of the methods includes receiving a process definition graph for a robot, the process definition graph having a plurality of action nodes, and the plurality of action nodes including a plurality of motion nodes that were previously split from a single motion node due to a conflict with a second motion node representing a second motion to be performed by another robot; determining that the conflict with the second motion node no longer exists; and in response to determining that the conflict with the second motion node no longer exists, modifying the process definition graph including combining the plurality of motion nodes into a new single motion node representing all of the motions of the plurality of motion nodes.