Application of artificial neural networks to weighted interval Kalman filtering

Motwani, Amit; Sharma, Sanjay; Sutton, Robert I.; Culverhouse, Phil F.

doi:10.1177/0959651813520148

Cited by 9 publications

(7 citation statements)

References 8 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This mapping is realised by training an ANN. Moreover, it was shown in [7] how the incorporation of the IKF widths as inputs could aid this mapping. Hence, in this case, the eIKF widths are computed as well and used as input to the network along with the KF innovations, the target values for the training process being the desired weights.…”

Section: Weighted Average Of Interval Boundsmentioning

confidence: 99%

Computation of stable interval Kalman filter bounds for their use in robust state estimation for an uninhabited surface vehicle with bounded indeterminate system dynamics

Motwani

Sharma

Sutton

et al. 2014

2014 IEEE Intelligent Vehicles Symposium Proceedings

Self Cite

View full text Add to dashboard Cite

This paper implements an interval Kalman filter (IKF) for the navigation of the Springer uninhabited surface vehicle. Interval filters become necessary when the system dynamics are not known precisely or vary unpredictably, but can nevertheless be described in terms of bounded intervals. Such filters based on interval systems require the use of interval arithmetic (IA) for their operation. One of the main limitations to such techniques is that the interval bounds of the computed filter estimates often diverge due to the overly conservative nature of IA. In this paper, ellipsoidal rather than direct IA is used to operate the IKF and obtain bounds of the interval estimates that do not diverge due to the so called wrapping effect. From these bounds, a weighted average is computed at each time-step that is close to the true system state. To obtain this weighting, an artificial neural network (ANN) is previously trained to map residuals of an ordinary Kalman filter to the optimal weights, and this trained network is then used online in new tracking missions.

show abstract

Section: Weighted Average Of Interval Boundsmentioning

confidence: 99%

Computation of stable interval Kalman filter bounds for their use in robust state estimation for an uninhabited surface vehicle with bounded indeterminate system dynamics

Motwani

Sharma

Sutton

et al. 2014

2014 IEEE Intelligent Vehicles Symposium Proceedings

Self Cite

View full text Add to dashboard Cite

show abstract

“…Currently, the Navigation system mounted on Springer is developed using three compasses along with a gyroscope to calculate instantaneous heading and a GPS combined with an IMU to localise the position as the vehicle is navigating. To improve the accuracy of the heading information as well as overcome possible sensors malfunctions, a weighted interval Kalman filter has been implemented (Motwani et al, 2013(Motwani et al, , 2014.…”

Section: The Navigation Guidance and Control (Ngc) System Of Springermentioning

confidence: 99%

The fast marching method based intelligent navigation of an unmanned surface vehicle

2017

View full text Add to dashboard Cite

Unmanned surface vehicles (USVs) have obtained increasing interests in recent decades. Because of the features of improved mission efficiency and decreased resource costs, applications of USVs can been seen in both civilian and naval areas. In order to efficiently and effectively achieve missions without any human intervention, a robust and intelligent navigation, guidance and control (NGC) system is vital for USV. This paper has therefore presented a novel NGC system designed for a USV named Springer. The system is developed by integrating multiple functional modules, which include a reliable navigation module that provides reliable position and heading information, a robust autopilot module enabling Springer tracking well the waypoints and an intelligent path planning module that is capable of generating feasible and practical waypoints. The path planning algorithm has been developed based upon the angle guidance fast marching square method, which is able to calculate the optimal path according to vehicle's motion constraints. The designed NGC system has been validated in both real field trials and computer based simulations proving that Springer USV is able to autonomously navigate in different maritime environments with the guidance of the NGC system.

show abstract

“…Therefore, humancomputer interaction system dynamic adaptive filtering uses online dynamic adaptive filter (DAF) method to eliminate the noise in the environment awareness. 2,11,16,[28][29][30] For the measured polar coordinates (l i, j , l i, j ), the following data analysis window is established…”

Section: Longitudinal Filter: Dynamic Adaptive Filteringmentioning

confidence: 99%

Contactless multi-touch interactive technology based on adaptive filtering algorithm

Dai

Fei

2017

Proceedings of the Institution of Mechanical Engineers, Part I:

View full text Add to dashboard Cite

In this article, a contactless multi-touch interactive system based on adaptive filtering algorithm has been presented, which uses advanced computer vision technology, combined with an interactive experience technology design. Also, the adaptive filtering method from a series of incomplete noise and the measurement data is utilized to solve the effects on the multimedia presentation system of interference noise generated by the motor running. Based on the horizontal filter and vertical filter combination method together, the accurate positioning coordinates with the positional relationship is established by scanning the data with the laser sensor. The contactless multi-touch interactive system can achieve human natural contactless interaction and make a variety of information dissemination element integrated into a complete contactless type of interactive system. It can pass a new interactive feeling and a new experience in an intuitive, three-dimensional, real-time multiplayer interactive way. Verified by experimental data, the interactive system proposed in this article has the properties of real time and accuracy, which has more precise positioning and smooth interaction and is able to achieve a good multiplayer real-time interaction effect. Therefore, the contactless multi-touch interactive system has a wide range of promotion and economic sense.

show abstract

Application of artificial neural networks to weighted interval Kalman filtering

Cited by 9 publications

References 8 publications

Computation of stable interval Kalman filter bounds for their use in robust state estimation for an uninhabited surface vehicle with bounded indeterminate system dynamics

Computation of stable interval Kalman filter bounds for their use in robust state estimation for an uninhabited surface vehicle with bounded indeterminate system dynamics

The fast marching method based intelligent navigation of an unmanned surface vehicle

Contactless multi-touch interactive technology based on adaptive filtering algorithm

Contact Info

Product

Resources

About