Track-to-track fusion using estimates from multiple sensors can achieve better estimation performance than single sensor tracking. If the local sensors use different system models in different state spaces, the problem of heterogeneous track-to-track fusion arises. Compared with homogeneous track-to-track fusion that assumes the same system model for different sensors, the heterogeneous case poses two major challenges. The first one is that we have to fuse estimates from different state spaces (related by a certain nonlinear transformation). The second is the estimation errors’ dependence problem, which is generally recognized as the “common process noise effect.” Different heterogeneous track-to-track fusion approaches, namely, the linear minimum mean square error approach and the maximum likelihood approach, are presented and compared with the corresponding centralized measurement tracker/fuser (also known as measurement-to-track fuser).