Learning Controller for Robotic Gesture Control

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Existing home automation devices often require users to carry smartphones or tablets to operate robotic devices, and their user interfaces are constrained, necessitating programming and button assignments, which can be cumbersome and inconvenient.

Innovation Solution

A robotic system with a learning controller that receives wireless transmissions from sensors and determines context associations, allowing it to autonomously execute actions without continuous user input, using a combination of sensors, computing clouds, and universal controllers to transmit commands wirelessly.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Ease of operation

If users operate robotic devices using existing home automation devices with constrained user interfaces, then control functionality is provided, but user convenience deteriorates due to the requirement to carry smartphones or tablets and perform programming

Engineering Contradiction:
Improveuser convenienceVSAvoidprogramming requirement
Core Design Contradiction:
Ease of operationVSDevice complexity

Solution Approach 1:

The learning controller automatically learns and stores associations between sensory contexts and control instructions through observation of user actions, eliminating the need for users to manually program device behaviors. The system serves itself by autonomously acquiring operational knowledge.

Inventive Principle:
Principle #25Self-service

Solution Approach 2:

The learning controller acts as an intermediary between the user and the robotic device, translating observed user actions into automated context-action associations. This intermediary layer handles the complexity of programming internally while presenting a simple interface to users.

Inventive Principle:
Principle #24Intermediary (Mediator)

2Productivity

If existing home automation devices require programming and button assignments, then control functionality is achieved, but operation time increases due to the cumbersome setup process

Engineering Contradiction:
Improveoperation efficiencyVSAvoidsetup time
Core Design Contradiction:
ProductivityVSLoss of time

Solution Approach 1:

The learning controller performs preliminary learning of context-action associations by observing user actions during normal operation. This preliminary action occurs in the background without requiring dedicated setup time, and the learned associations are ready for immediate use.

Inventive Principle:
Principle #10Preliminary action

Solution Approach 2:

The learning process occurs continuously during normal device operation rather than requiring a separate programming phase. The system learns from ongoing user interactions, maintaining continuous useful action without interruption for setup.

Inventive Principle:
Principle #20Continuity of useful action

3Adaptability or versatility

If robotic devices use traditional remote control methods, then basic control is provided, but adaptability deteriorates due to lack of context awareness

Engineering Contradiction:
Improvecontext awarenessVSAvoidsensory context information
Core Design Contradiction:
Adaptability or versatilityVSLoss of information

Solution Approach 1:

The learning controller uses sensory input from sensors to detect contextual information about the environment and user actions. This feedback loop enables the system to adapt its control instructions based on observed contexts, improving adaptability while preserving contextual information.

Inventive Principle:
Principle #23Feedback

Solution Approach 2:

The learning controller integrates multiple sensor types and processes various sensory contexts to determine appropriate control instructions. This multi-functional approach enables the system to adapt to diverse situations and maintain contextual awareness across different operating conditions.

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

Data Source

PatentUS9849588B2Apparatus and methods for remotely controlling robotic devices
Publication Date: 2017.12.26 BRAIN CORP
  • US9849588B2 patent drawing
  • US9849588B2 patent drawing
  • US9849588B2 patent drawing

AI summary

Computerized appliances may be operated by users remotely. A learning controller apparatus may be operated to determine association between a user indication and an action by the appliance. The user indications, e.g., gestures, posture changes, audio signals may trigger an event associated with the controller. The event may be linked to a plurality of instructions configured to communicate a command to the appliance. The learning apparatus may receive sensory input conveying information about robot's state and environment (context). The sensory input may be used to determine the user indications. During operation, upon determine the indication using sensory input, the controller may cause execution of the respective instructions in order to trigger action by the appliance. Device animation methodology may enable users to operate computerized appliances using gestures, voice commands, posture changes, and/or other customized control elements.