Intelligent Controller Schedule Learning for Adaptive Behavior

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Existing control systems lack the flexibility and intelligence to adapt and produce desired operational behaviors specified after controller design and implementation, particularly in dynamically changing environments or user preferences.

Innovation Solution

Intelligent controllers that learn and modify control schedules over time through schedule-creation and schedule-modification interfaces, using immediate-control inputs and sensor feedback to encode desired operational behaviors into control schedules, with phases of aggressive learning and steady-state refinement.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Adaptability or versatility

If traditional control systems are used with predetermined behavior, then system reliability is maintained, but adaptability to changing environments and user preferences deteriorates

Engineering Contradiction:

ImproveadaptabilityVSAvoidcontroller complexity

Core Design Contradiction:

Adaptability or versatilityVSDevice complexity

Solution Approach 1:

The control system transitions from static predetermined behavior to dynamic adaptive behavior through machine learning algorithms that continuously update control schedules based on sensor feedback and immediate-control inputs, allowing the controller to adapt to changing environments and user preferences

Inventive Principle:

Principle #15Dynamics

Solution Approach 2:

The intelligent controller performs self-learning and self-optimization by automatically acquiring control schedules through monitoring periods and learning phases, reducing the need for manual programming and configuration while improving adaptability

Inventive Principle:

Principle #25Self-service

2Productivity

If frequent immediate-control inputs are used during aggressive learning phase, then learning speed is improved, but energy consumption increases

Engineering Contradiction:

Improvelearning speedVSAvoidenergy consumption

Core Design Contradiction:

ProductivityVSUse of energy by moving object

Solution Approach 1:

The system implements periodic monitoring periods followed by learning phases, alternating between aggressive learning with frequent control inputs and steady-state operation with minimized inputs, creating a rhythmic pattern that balances learning speed and energy consumption

Inventive Principle:

Principle #19Periodic action

Solution Approach 2:

During aggressive learning phase, the system temporarily uses excessive control inputs beyond normal operational needs to accelerate learning, then reduces to partial action during steady-state operation to conserve energy

Inventive Principle:

Principle #16Partial or excessive action

3Ease of operation

If control schedules are manually programmed, then precision of operational behavior is achieved, but ease of operation deteriorates

Engineering Contradiction:

Improveease of operationVSAvoidoperational behavior precision

Core Design Contradiction:

Ease of operationVSManufacturing precision

Solution Approach 1:

The system uses sensor feedback from the controlled system to continuously refine and update control schedules, ensuring precise operational behavior is achieved through automatic learning rather than manual programming, thereby improving ease of operation

Inventive Principle:

Principle #23Feedback

Solution Approach 2:

Manual programming operations are replaced with automated machine learning processes that use computational algorithms to acquire and refine control schedules, substituting human effort with intelligent automation while maintaining precision

Inventive Principle:

Principle #28Mechanics substitution (Replace mechanical system)

Data Source

PatentUS8630740B2Automated control-schedule acquisition within an intelligent controller

Publication Date: 2014.01.14 GOOGLE LLC

AI summary

The current application is directed to intelligent controllers that initially aggressively learn, and then continue, in a steady-state mode, to monitor, learn, and modify one or more control schedules that specify a desired operational behavior of a device, machine, system, or organization controlled by the intelligent controller. An intelligent controller generally acquires one or more initial control schedules through schedule-creation and schedule-modification interfaces or by accessing a default control schedule stored locally or remotely in a memory or mass-storage device. The intelligent controller then proceeds to learn, over time, a desired operational behavior for the device, machine, system, or organization controlled by the intelligent controller based on immediate-control inputs, schedule-modification inputs, and previous and current control schedules, encoding the desired operational behavior in one or more control schedules and/or sub-schedules.