Fundamentals of distributed estimation and tracking

Distributed processing of multiple sensor data has advantages over centralized processing because of lower bandwidth for communicating data and lower processing load at each site. However, distributed fusion has to address dependence issues not present in centralized fusion. Bayesian distributed fusion combines local probabilities or estimates to generate the results of centralized fusion by identifying and removing redundant common information. Approximation of Bayesian distributed fusion provides practical algorithms when it is difficult to identify the common information. Another distributed fusion approach combines estimates with known means and cross covariances according to some optimality criteria. Distributed object tracking involves both track to track association and track state estimate fusion given an association. Track state estimate fusion equations can be obtained from distributed estimation equations by treating the state as a random process with measurements that are accumulated over time. For objects with deterministic dynamics, the same fusion equations for static states can be used. When the object state has non-deterministic dynamics, reconstructing the centralized estimate from the local estimates is usually not possible, but fusion equations based on means and cross covariances are still optimal with respect to their criteria. It is possible to fuse local estimates to duplicate the results of centralized tracking but the local estimates are not locally optimal and the weighting matrices depend on covariance matrices from other sensors.

[1]  Jeffrey K. Uhlmann,et al.  Scalable distributed data fusion , 2002, Proceedings of the Fifth International Conference on Information Fusion. FUSION 2002. (IEEE Cat.No.02EX5997).

[2]  A. Willsky,et al.  Combining and updating of local estimates and regional maps along sets of one-dimensional tracks , 1982 .

[3]  Shozo Mori,et al.  Adaptive distributed estimation , 1987, 26th IEEE Conference on Decision and Control.

[4]  Chee-Yee Chong,et al.  Convex Combination and Covariance Intersection Algorithms in Distributed Fusion , 2001 .

[5]  M. Hurley.  An information theoretic justification for covariance intersection and its generalization , 2002, Proceedings of the Fifth International Conference on Information Fusion. FUSION 2002. (IEEE Cat.No.02EX5997).

[6]  Yaakov Bar-Shalom,et al.  The Effect of the Common Process Noise on the Two-Sensor Fused-Track Covariance , 1986, IEEE Transactions on Aerospace and Electronic Systems.

[7]  Chee-Yee Chong,et al.  Analytical and Computational Evaluation of Scalable Distributed Fusion Algorithms , 2010, IEEE Transactions on Aerospace and Electronic Systems.

[8]  E. Tse,et al.  Distributed Estimation in Networks , 1983, 1983 American Control Conference.

[9]  Kuo-Chu Chang,et al.  Essence of Distributed Target Tracking: Track Fusion and Track Association , 2012 .

[10]  D. Teneketzis,et al.  Coordinator , 2020, EuroPLoP.

[11]  Kuo-Chu Chang,et al.  Information Fusion in Distributed Sensor Networks , 1985, 1985 American Control Conference.

[12]  E. Tse,et al.  Distributed Estimation in Distributed Sensor Networks , 1982, 1982 American Control Conference.

[13]  David Nicholson,et al.  DDF : An Evaluation of Covariance Intersection , 2001 .

[14]  Chongzhao Han,et al.  Optimal Linear Estimation Fusion — Part I : Unified Fusion Rules , 2001 .

[15]  Keshu Zhang,et al.  Best Linear Unbiased Estimation Fusion with Constraints , 2003 .

[16]  Wolfgang Koch.  Exact update formulae for distributed Kalman filtering and retrodiction at arbitrary communication rates , 2009, 2009 12th International Conference on Information Fusion.

[17]  Felix Govaers,et al.  Distributed Kalman filter fusion at arbitrary instants of time , 2010, 2010 13th International Conference on Information Fusion.

[18]  Simon J. Julier,et al.  An Empirical Study into the Use of Chernoff Information for Robust, Distributed Fusion of Gaussian Mixture Models , 2006, 2006 9th International Conference on Information Fusion.

[19]  Kuo-Chu Chang,et al.  Comparison of track fusion rules and track association metrics , 2012, 2012 15th International Conference on Information Fusion.

[20]  Jeffrey K. Uhlmann,et al.  The challenge of scalable and distributed fusion of disparate sources of information , 2006, SPIE Defense + Commercial Sensing.

[21]  Chee-Yee Chong,et al.  Track association and track fusion with nondeterministic target dynamics , 2002 .

[22]  Jason Speyer,et al.  Computation and transmission requirements for a decentralized linear-quadratic-Gaussian control problem , 1978, 1978 IEEE Conference on Decision and Control including the 17th Symposium on Adaptive Processes.

[23]  Huosheng Hu,et al.  Toward a fully decentralized architecture for multi-sensor data fusion , 1990, Proceedings., IEEE International Conference on Robotics and Automation.

[24]  Chee-Yee Chong,et al.  Fundamentals of Distributed Estimation , 2017 .

[25]  Thomas M. Cover,et al.  Elements of Information Theory , 2005 .

[26]  S. Mori,et al.  Performance evaluation for MAP state estimate fusion , 2004 .