Burden Estimation Using Reinforcement Learning for Travel Fatigue
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing burden estimation devices cannot accurately calculate the fatigue and burden of a user when using multiple methods of travel, as they primarily focus on physical fatigue and do not account for mental fatigue or changes in travel methods, leading to incomplete and inaccurate burden assessments.
Innovation Solution
A burden estimation device and method that define a state space corresponding to a travel route, using reinforcement learning to estimate individual burdens based on various data types, including travel methods, purpose, and weather, allowing for comprehensive burden evaluation and estimation of total travel burden even on unknown routes.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If biological signals are used to calculate fatigue level, then physical strength consumption is measured, but this does not reflect the comprehensive burden including mental fatigue
Solution Approach 1:
The patent combines multiple data types including biological signals (physical fatigue), travel route information, travel method changes, purpose of travel, and weather conditions to create a comprehensive burden estimation that integrates both physical and mental fatigue components
Solution Approach 2:
The burden estimation is segmented into individual burden components (physical fatigue from biological signals, mental fatigue from travel complexity) that are estimated separately and then combined to form the total burden assessment
2Productivity
If simple fatigue level calculation is used, then calculation speed is maintained, but accuracy of burden assessment deteriorates when multiple travel methods are involved
Solution Approach 1:
The system performs preliminary estimation of individual burdens for each state in the state space before the user actually travels, allowing the total burden to be calculated by simply summing pre-estimated values during actual travel, thus maintaining calculation speed while improving accuracy
3Measurement precision
If comprehensive data collection is performed to improve burden estimation accuracy, then measurement precision improves, but device complexity and data processing burden increase
Solution Approach 1:
The system utilizes data that is already being collected by the user's smartphone for other purposes (GPS location, travel route, weather information) and repurposes it for burden estimation, avoiding the need for additional specialized sensors or data collection mechanisms
Data Source
AI summary
A burden estimation device includes a state space configuration unit, a history learning unit acquiring from the user and storing in a storage unit data related to the burden on the user when the user travels to the destination along the travel route, an individual burden estimation unit evaluating a total travel burden and estimating an individual burden that is the burden on the user in correspondence with each of the states included in the state space through reinforcement learning that sets the total travel burden as a reward, and a total travel burden estimation unit estimating the total travel burden corresponding to an unknown travel route based on the estimated individual burden if the unknown travel route is set and the individual burden has already been estimated for at least some of the states defined in correspondence with the unknown travel route.