Smart Shoe PDR Using Phase Segmentation and Velocity Correction
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Pedestrian Dead Reckoning (PDR) technologies face challenges in accurately estimating position and direction due to error accumulation over time and limitations in measuring stride and step, particularly when correcting zero velocity in a stopped state, which affects the accuracy of position estimation.
Innovation Solution
A smart shoe system with a stance phase measurement unit, swing phase measurement unit, and Predict Velocity Update (PUPT) unit that detects acceleration and gyro data to determine walking conditions, correct velocity, and estimate position and direction by using equations to analyze energy, product, sum, variance, and magnitude of sensor data, and applying deep learning for compensation based on shoe size and walking style.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Ease of operation
If Zero velocity UPdaTe (ZUPT) is used to correct velocity in a stopped state, then velocity correction is simplified, but measurement precision deteriorates because standing motion is not reflected to walking motion
Solution Approach 1:
The patent segments the walking cycle into distinct phases (stance phase and swing phase) and applies different velocity correction methods to each phase. During the stance phase when the foot is in contact with the ground, the system detects and corrects velocity based on actual motion characteristics rather than simply setting it to zero. This segmentation allows the system to maintain simplicity while improving accuracy by treating different motion phases differently.
Solution Approach 2:
The patent transitions from a static velocity correction approach (ZUPT that sets velocity to zero during stopped states) to a dynamic approach that continuously adjusts velocity based on detected motion characteristics. The system dynamically identifies stance and swing phases and applies appropriate correction algorithms to each, allowing the velocity correction to adapt to the actual motion state rather than applying a fixed correction rule.
2Adaptability or versatility
If PDR technologies are used for position estimation, then position can be estimated without GPS, but reliability deteriorates due to error accumulation over time
Solution Approach 1:
The patent implements a feedback mechanism where the system continuously monitors motion characteristics during stance and swing phases, detects deviations from expected patterns, and applies corrective adjustments to the velocity estimates. This feedback loop prevents error accumulation by regularly correcting the position estimation based on detected motion anomalies, thereby maintaining reliability over extended periods without GPS.
Solution Approach 2:
The patent applies preliminary velocity corrections during the stance phase before the swing phase begins. By detecting and correcting velocity errors during the stance phase when the foot is in contact with the ground, the system prevents these errors from propagating through subsequent swing phases and accumulating over time, thereby maintaining long-term reliability.
3Measurement precision
If stride and step measurement is enhanced for accurate position estimation, then measurement precision improves, but device complexity increases
Solution Approach 1:
The patent makes the inertial sensors attached to the shoe serve multiple functions: they detect both the stance/swing phase transitions and measure acceleration for velocity correction, as well as detect gyroscopic effects for orientation determination. By making the sensor system multi-functional, the patent achieves enhanced stride and step measurement precision without adding separate dedicated sensors for each function, thereby limiting the increase in device complexity.
Applied Scientific Principles
This section explains which scientific principles are used to turn an abstract innovation direction into a practical engineering solution.
Function Achieved in This Case
Minimizes measurement errors in walking conditions, allowing accurate estimation of pedestrian position and direction even without received position information, enabling real-time monitoring of multiple pedestrians in environments without GPS, such as firefighters in a room.
Implementation Method 1
detecting acceleration and gyro in a stance phase
Implementation Method 2
detecting acceleration and gyro in a stance phase
Data Source
AI summary
Provided are a smart shoe and a data processing method thereof. The smart shoe includes: a stance phase measurement unit for, when one of two feet is set as a reference foot and a period during which the reference foot is taken off a ground and touches the ground again is set as a walking cycle, detecting acceleration and gyro in a stance phase in which the reference foot touches the ground; a swing phase measurement unit for detecting a difference between acceleration of the swing phase when the reference foot is taken off the ground and acceleration at the moment when the reference foot touches the ground; and a predict velocity update (PUPT) unit for obtaining and correcting a velocity of the stance phase condition.