Multi-domain Planning Execution via Hierarchical Coordination

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Existing automated planning systems struggle with coordinating multiple domains and sub-domains in autonomous systems, leading to inefficiencies and inflexibility due to the lack of coordinated planning and real-time response to changes.

Innovation Solution

A scalable infrastructure with a modular, multi-domain, and multi-layered plan-based control system that uses a planner component to generate and dispatch plans, incorporating deliberative reasoning and inference systems for dynamic re-planning and execution, enabling flexible and efficient operation across various domains.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Adaptability or versatility

If a monolithic approach is used for automated planning, then the planning system can handle complex tasks with multiple activities, but the system becomes unwieldy and difficult to maintain

Engineering Contradiction:
Improveability to handle complex tasks with multiple activitiesVSAvoidsystem structure becomes unwieldy and difficult to maintain
Core Design Contradiction:
Adaptability or versatilityVSDevice complexity

Solution Approach 1:

The patent divides the automated planning system into separate domain models, each representing a specific domain (e.g., drilling, mud management, casing, cementing). This segmentation allows the system to handle complex tasks while maintaining manageability, as each domain model can be independently developed, maintained, and updated without affecting the entire system.

Inventive Principle:
Principle #1Segmentation

2Device complexity

If domains are broken down into sub-components using a non-monolithic approach, then the system becomes easier to maintain, but the individually generated plans are inefficient and inflexible

Engineering Contradiction:
Improvesystem structure becomes modular and easier to maintainVSAvoidplan generation efficiency and flexibility
Core Design Contradiction:
Device complexityVSProductivity

Solution Approach 1:

The patent introduces a planner that generates plans at multiple levels, combining high-level domain plans with low-level task plans. The planner coordinates actions across different domain models, ensuring that individually generated plans are efficiently integrated and can respond flexibly to changes in other domains, thus maintaining both modularity and productivity.

Inventive Principle:
Principle #5Merging (Combining)

Solution Approach 2:

The system incorporates feedback mechanisms that allow the planner to monitor and adjust plans based on changes in domain states. When changes occur in one domain, the planner can re-generate coordinated plans that account for these changes, ensuring efficiency and flexibility while maintaining the modular architecture.

Inventive Principle:
Principle #23Feedback

3Ease of operation

If plans are generated without coordination between domains, then each domain can operate independently, but the plans cannot react to changes in other domains

Engineering Contradiction:
Improveindependent domain operationVSAvoidability to react to changes in other domains
Core Design Contradiction:
Ease of operationVSAdaptability or versatility

Solution Approach 1:

The planner serves as a universal coordination mechanism that operates across all domain models. It receives plans from multiple domains, coordinates them considering interactions between domains, and generates unified plans that can react to changes in any domain while allowing independent domain operation.

Inventive Principle:
Principle #6Universality (Multi-functionality)

Data Source

PatentUS12147920B2Multi-domain planning and execution
Publication Date: 2024.11.19 SCHLUMBERGER TECH CORP
  • US12147920B2 patent drawing
  • US12147920B2 patent drawing
  • US12147920B2 patent drawing

AI summary

Multi-domain planning and execution systems and methods are disclosed whereby each planning component in a decomposed architecture is associated with its own domain, each planning component may supervise levels underneath it, and dependencies between domains are managed by the coordination of goals and constraints. For example, a computing device may be communicatively coupled to equipment; include a first-level component having a first-level planner component that generates a first-level plan associated with an operation using the equipment; and include second-level components, each associated with respective equipment and each including a second-level planner component that generates a second-level plan based on the first-level plan, wherein the second-level plan has instructions to perform a portion of the operation, and each second-level component instructs each respective equipment to execute a respective second-level plan.