Wearable Flight Control Using Deep RL for User Physique Adaptation

Solution Overview

Problem

Conventional control methods for user-wearable flight devices struggle to adapt to individual user physiques, requiring significant time and economic costs for adjustments each time a new user uses the device.

Innovation Solution

A control device utilizing deep reinforcement learning to process state and manipulation data, enabling the flight device to be appropriately controlled regardless of the user's physique or presence.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Adaptability or versatility

If conventional control methods are used for user-wearable flight devices, then the control method can be adjusted in accordance with the user, but it requires significant time and economic costs for adjustments each time a new user uses the device

Engineering Contradiction:

Improveadaptability to user physiqueVSAvoidtime for recalibration

Core Design Contradiction:

Adaptability or versatilityVSLoss of time

Solution Approach 1:

The control device performs preliminary acquisition of user information (body weight, height, circumferences) before flight operations, and pre-calculates appropriate control parameters. This preliminary action eliminates the need for time-consuming recalibration when users change, as the system can quickly adapt using pre-established models and algorithms.

Inventive Principle:

Principle #10Preliminary action

Solution Approach 2:

The system creates a digital model or profile representing each user's physique characteristics. This copied representation is then used to automatically adjust control parameters without requiring physical recalibration, significantly reducing the time and cost associated with adapting to different users.

Inventive Principle:

Principle #26Copying

2Adaptability or versatility

If conventional control methods are used for user-wearable flight devices, then the control method can be adjusted in accordance with the user, but it requires significant economic costs for adjustments each time a new user uses the device

Engineering Contradiction:

Improveadaptability to user physiqueVSAvoideconomic cost

Core Design Contradiction:

Adaptability or versatilityVSReliability

Solution Approach 1:

The system creates a digital model or profile representing each user's physique characteristics. This copied representation is then used to automatically adjust control parameters without requiring physical recalibration, significantly reducing the time and cost associated with adapting to different users.

Inventive Principle:

Principle #26Copying

Solution Approach 2:

The control device automatically adjusts control parameters based on user physique data (body weight, height, circumferences) by changing numerical values in the control algorithm. This parameter-based adaptation eliminates the need for expensive manual recalibration processes while maintaining high adaptability to different users.

Inventive Principle:

Principle #35Parameter changes

3Volume of moving object

If the flight device is designed to be wearable and compact, then it is more portable, but it becomes significantly affected by human physique difference

Engineering Contradiction:

Improvedevice sizeVSAvoidsensitivity to user physique

Core Design Contradiction:

Volume of moving objectVSAdaptability or versatility

Solution Approach 1:

The control device performs preliminary acquisition of user information (body weight, height, circumferences) before flight operations, and pre-calculates appropriate control parameters. This preliminary action eliminates the need for time-consuming recalibration when users change, as the system can quickly adapt using pre-established models and algorithms.

Inventive Principle:

Principle #10Preliminary action

Solution Approach 2:

The control device automatically adjusts control parameters based on user physique data (body weight, height, circumferences) by changing numerical values in the control algorithm. This parameter-based adaptation eliminates the need for expensive manual recalibration processes while maintaining high adaptability to different users.

Inventive Principle:

Principle #35Parameter changes

Data Source

PatentUS20250333165A1Control device, control method, and storage medium

Publication Date: 2025.10.30 JAPAN AEROSPACE EXPLORATION AGENCY

AI summary

According to an embodiment, a control device controls a user-wearable flight device and includes a processing unit configured to acquire state data related to a state of the flight device and manipulation data related to a manipulation of the flight device, input the acquired state data and the acquired manipulation data to a model trained using deep reinforcement learning, and control the flight device on the basis of an output result of the model to which the state data and the manipulation data are input.