Sensor Fusion Algorithm Selection for an Autonomous Wheelchair Based on EKF/UKF Comparison

Fariña, Bibiana; Toledo, Jonay; Sánchez, Leopoldo

doi:10.18178/ijmerr.12.1.1-7

Cited by 3 publications

(2 citation statements)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In the early 1990s, Julier and Uhlman proposed Unscented Kalman Filter (UKF), which is an extension of EKF and used to solve nonlinear problems without linearizing nonlinear equations, so it has a wider range of applications 16 . UKF differs from EKF in that UKF obtains sigma points by diffusing the state variable and the measured variable outward a defined distance along its mean, and calculates the mean and covariance over the range of the nonlinear function.…”

Section: Ukf Principlementioning

confidence: 99%

Sensorless control of permanent magnet synchronous motor based on UKF

Yang,

Li,

Chen

et al. 2023

Third International Conference on Electronics, Electrical and Information Engineering (ICEEIE 2023)

View full text Add to dashboard Cite

In order to solve the problems of high cost, large volume and difficult maintenance when traditional mechanical sensors are used in permanent magnet synchronous motor, a sensorless system model of permanent magnet synchronous motor based on untracked Kalman observer is established in this paper, and the running state of permanent magnet synchronous motor is predicted by untracked Kalman algorithm to achieve closed-loop control. The simulation results show that the traceless Kalman observer has the advantages of accurate prediction, good dynamic and static performance, and strong anti-interference ability. It solves the defects of traditional permanent mechanical sensors to a large extent and has great application prospects in the future.

show abstract

Section: Ukf Principlementioning

confidence: 99%

Sensorless control of permanent magnet synchronous motor based on UKF

Yang,

Li,

Chen

et al. 2023

Third International Conference on Electronics, Electrical and Information Engineering (ICEEIE 2023)

View full text Add to dashboard Cite

show abstract

“…The UKF, on the other hand, uses the unscented transform to fit the probability density distribution of non-linear equations, which allows it to avoid the loss of higher-order terms that can occur with linearization [ 2 ]. This makes the UKF a simple, fast, and precise option for non-linear systems [ 3 , 4 , 5 ].…”

Section: Introductionmentioning

confidence: 99%

Improving Odometric Model Performance Based on LSTM Networks

Fariña

Acosta

Toledo

et al. 2023

Sensors

View full text Add to dashboard Cite

This paper presents a localization system for an autonomous wheelchair that includes several sensors, such as odometers, LIDARs, and an IMU. It focuses on improving the odometric localization accuracy using an LSTM neural network. Improved odometry will improve the result of the localization algorithm, obtaining a more accurate pose. The localization system is composed by a neural network designed to estimate the current pose using the odometric encoder information as input. The training is carried out by analyzing multiple random paths and defining the velodyne sensor data as training ground truth. During wheelchair navigation, the localization system retrains the network in real time to adjust any change or systematic error that occurs with respect to the initial conditions. Furthermore, another network manages to avoid certain random errors by using the relationship between the power consumed by the motors and the actual wheel speeds. The experimental results show several examples that demonstrate the ability to self-correct against variations over time, and to detect non-systematic errors in different situations using this relation. The final robot localization is improved with the designed odometric model compared to the classic robot localization based on sensor fusion using a static covariance.

show abstract

GPS/IMU/Hydrodynamic Model Fusion State Estimation for Unmanned Surface Vehicles Based on Moving Horizon Estimation Method

Ma,

Chen,

2023

2023 5th International Conference on Robotics and Computer Vision (ICRCV)

View full text Add to dashboard Cite

Sensor Fusion Algorithm Selection for an Autonomous Wheelchair Based on EKF/UKF Comparison

Cited by 3 publications

References 0 publications

Sensorless control of permanent magnet synchronous motor based on UKF

Sensorless control of permanent magnet synchronous motor based on UKF

Improving Odometric Model Performance Based on LSTM Networks

GPS/IMU/Hydrodynamic Model Fusion State Estimation for Unmanned Surface Vehicles Based on Moving Horizon Estimation Method

Contact Info

Product

Resources

About