IMM Estimator Research Articles

Distributed Frobenius-Norm Finite Memory Interacting Multiple Model Estimation for Mobile Robot Localization

This paper proposes a novel state estimation algorithm, called the distributed Frobenius-norm finite memory interacting multiple model (DFFM-IMM) estimation algorithm, for mobile robot localization in wireless sensor networks (WSNs). The proposed algorithm involves finite memory estimation based on recent finite measurements; such estimation facilitates robust localization in cases of missing measurements and robot kidnapping. Furthermore, the proposed algorithm employs IMM, which facilitates accurate localization if a mobile robot abruptly changes its speed and course. Notably, average-consensus-based distributed processing renders the proposed DFFM-IMM algorithm computationally efficient, and hence, real-time processing for very short sampling times of the WSN is possible. The proposed algorithm’s performance is demonstrated by comparing it with a centralized Frobenius-norm finite memory IMM (CFFM-IMM) estimation algorithm and a localization algorithm on the basis of simulations and experiments.

Federated IMM-UKF Algorithm for Multi-Sensor Data Fusion

The accuracy of multi-sensor navigational data fusion by federated Kalman filter will be reduced in condition that the systems dynamics model is nonlinear and the noise statistical properties are unknown. To address this problem, a federated Interacting Multiple Model-Unscented Kalman Filteing (IMM-UKF) algorithm is presented. The UKF is a nonlinear estimation method which can achieve the accuracy at least to the second-order. The IMM estimation algorithm is one of the cost-effective adaptive estimation algorithm for systems involving parametric changes. The combination of IMM with UKF could deal with the problem of nonlinear filtering with uncertain noise. Simulation results show that the method can improve the accuracy of INS/GPS/odometer integrated navigation.

Erratum: A Multiple IMM Estimation Approach with Unbiased Mixing for Thrusting Projectiles

In the above titled paper, the Mach number-dependent multiplier which is missing in the equation is presented.

A Multiple IMM Estimation Approach with Unbiased Mixing for Thrusting Projectiles

We present a procedure to estimate the state of thrusting/ballistic endoatmospheric projectiles for the end purpose of impact point prediction. The short observation time and the estimation ambiguity between drag and thrust in the dynamic model motivate the development of a multiple interacting multiple model (MIMM) estimator with various drag coefficient initializations. A simple unbiased IMM mixing procedure (useful for quite general applications) is presented for state estimators with unequal dimensions and applied for the thrusting and ballistic modes in the case considered. Results with real data are given.

Ball localization and tracking in a highly dynamic table soccer environment

This article presents the development of a ball localization and tracking algorithm, that is to be applied in a highly dynamic table soccer environment. The described approach is based on an earlier survey paper on object tracking, where a general selection procedure on object detection and tracking techniques was proposed. Although the survey paper presents a variety of state estimation techniques for tracking, this article describes why these are not well suited for our specific application. For this reason, an IMM estimation technique is adopted that has not been applied in this highly dynamic context before. To evaluate the IMM estimator, it is compared to the well-known and commonly used Kalman filter, that has been optimally tuned for this specific application.

Tracking evasive move-stop-move targets with a GMTI radar using a VS-IMM estimator

We present the design of a variable structure interacting multiple model (VS-IMM) estimator for tracking evasive ground targets using ground moving target indicator (GMTI) reports obtained from an airborne sensor. In order to avoid detection by the GMTI sensor, the targets use a strategy, where a target deliberately stops or moves at a very low speed for some time before accelerating again. In this case, when the target's radial velocity (along the line of sight from the sensor) falls below a certain minimum detectable velocity, the target is not detected by the sensor. Under these conditions, the use of an estimator, which does not take care of this move-stop-move motion explicitly, will result in broken tracks. The tracker proposed here handles the evasive move-stop-move motion via the VS-IMM estimator, where the tracker mode set is augmented with a model when the estimated speed of the target falls below a certain threshold. Using this additional stopped-target model, the target track is kept alive even in the absence of a measurement. A simulated scenario is used to illustrate the selection of design parameters and the operation of the tracker. Performance measures are presented to contrast the benefits of the VS-IMM estimator, which uses the stopped-target model, over a standard IMM estimator.

Ground target tracking with variable structure IMM estimator

In this paper we present the design of a Variable Structure Interacting Multiple Model (VS-IMM) estimator for tracking groups of ground targets on constrained paths using Moving Target Indicator (MTI) reports obtained from an airborne sensor. The targets are moving along a highway, with varying obscuration due to changing terrain conditions. In addition, the roads can branch, merge or cross-the scenario represents target convoys along a realistic road network with junctions, changing terrains, etc. Some of the targets may also move in an open field. This constrained motion estimation problem is handled using an IMM estimator with varying mode sets depending on the topography, The number of models in the IMM estimator, their types and their parameters are modified adaptively, in real-time, based on the estimated position of the target and the corresponding road/visibility conditions. This topography-based variable structure mechanism eliminates the need for carrying all the possible models throughout the entire tracking period as in the standard IMM estimator, significantly improving performance and reducing computational load. Data association is handled using an assignment algorithm. The estimator is designed to handle a very large number of ground targets simultaneously. A simulated scenario consisting of over one hundred targets is used to illustrate the selection of design parameters and the operation of the tracker. Performance measures are presented to contrast the benefits of the VS-IMM estimator over the Kalman filter and the standard IMM estimator, The VS-IMM estimator is then combined with multidimensional assignment to gain time-depth. The additional benefit of using higher dimensional assignment algorithms for data association is also evaluated.

A distributed IMM fusion algorithm for multi-platform tracking

In this paper, a distributed interacting multiple model (DIMM) fusion algorithm for multi-platform tracking is developed. Locally, each platform contains its own independent tracking subsystem, using an IMM estimation algorithm. Globally, equivalent platform models and an equivalent global model are constructed so that a global multiple model fusion algorithm can be carried out. Compared with an existing benchmark DIMM fusion algorithm, the new algorithm needs less communication and less computation. Computer simulations show that the algorithm has a very good performance.