Robotic Task Decomposition for Flexible Action Planning Networks
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Conventional robotic systems are limited by hardcoded algorithms and data, restricting robots from performing tasks beyond their initial designation, even if they have the capability to handle them, leading to underutilization of resources.
Innovation Solution
A processor-implemented method for action planning in a robotic network, where a robotic agent decomposes assigned goals into sub-goals, identifies targets and actions, determines robot capabilities, and generates action plans based on attribute data from local and global databases, as well as real-time inputs, allowing robots to adapt and perform diverse tasks.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If robots are assigned specific tasks with hardcoded algorithms, then task execution reliability is improved, but robot versatility and resource utilization deteriorate
Solution Approach 1:
The patent implements a universal task decomposition framework where any robot task can be broken down into standardized sub-tasks (perception, localization, navigation, manipulation). This allows robots to handle diverse tasks using the same core framework, enhancing versatility while maintaining reliability through consistent task execution patterns across different applications.
Solution Approach 2:
The patent segments complex robot tasks into hierarchical sub-tasks and further into atomic actions. By decomposing high-level goals into manageable components (e.g., 'pick and place' into 'grasp', 'move', 'release'), the system maintains reliable execution of each sub-task while enabling flexible combination for various overall tasks, resolving the contradiction between reliability and versatility.
2Manufacturing precision
If hardcoded algorithms are used for specific tasks, then task execution precision is improved, but system adaptability to new tasks deteriorates
Solution Approach 1:
The patent uses parameter-based task descriptions where tasks are defined by configurable parameters rather than fixed hardcoded logic. The task decomposition framework accepts high-level task parameters and automatically generates appropriate action sequences, allowing precise execution through parameter specification while adapting to new tasks by changing parameters without modifying the underlying algorithm structure.
3Productivity
If robots are specialized for specific tasks, then task execution efficiency is improved, but overall resource utilization in robotic networks deteriorates
Solution Approach 1:
The patent implements self-service mechanisms where robots autonomously decompose their own tasks, plan actions, and execute workflows without requiring task-specific programming. Each robot can independently handle various tasks using the universal framework, eliminating the need for dedicated specialized robots for each task type and improving overall resource utilization while maintaining execution efficiency.
Data Source
AI summary
This disclosure relates generally to robotic network, and more particularly to a method and system for hierarchical decomposition of tasks and task planning in a robotic network. While a centralized system is used for action planning in a robotic network, any communication network issues can adversely affect working of the robotic network. Further, hardcoding one or more specific tasks to a robot restricts use of the robots irrespective of capabilities of the robots. The robotic agent decomposes a goal assigned to the robot to multiple sub-goals, and for each sub-goal, identifies one or more tasks to be executed/performed by the robot. An action plan is generated based on all such tasks identified, and the robot executes the action plan, in response to the goal assigned to the robot.