# Sensor Fusion CeruleanTracker contains an advanced Extended Kalman Filter (EKF) that can combine the outputs of the Cerulean ROV Locator, the **Cerulean DVL-75**, and a topside GPS. Combining the ROVL and DVL signals allows the output signal to leverage the bounded long-error characteristic of the ROVL and the short-term stability of the DVL. Using a topside GPS in the mix (usually supplied by others) adds absolute georeferencing to the output. {% hint style="info" %} Note: Sensor fusion for the Cerulean Sonar Tracker-650 DVL is designed for use with ROV heading references via their autopilots and is not incorporated in CeruleanTracker sensor fusion. See [here ](https://docs.ceruleansonar.com/c/dvl-50/using-mavlink-and-blueos-for-position-hold-on-a-bluerov2)for an example of the Tracker-650 sending data to the BlueROV autopilot for sensor fusion. {% endhint %} CeruleanTracker also allows you to route either DVL or ROVL signals directly to the output, bypassing the EKF and the other unit. It is entirely possible for users to build their own EKF for sensor fusion without using the CeruleanTracker application. It is beyond the scope of this manual to provide help on that topic, and our engineering staff is regrettably unable to provide advice on making your own EKF. --- # Agent Instructions: Querying This Documentation If you need additional information that is not directly available in this page, you can query the documentation dynamically by asking a question. Perform an HTTP GET request on the current page URL with the `ask` query parameter: ``` GET https://docs.ceruleansonar.com/c/ceruleantracker/overview/sensor-fusion.md?ask= ``` The question should be specific, self-contained, and written in natural language. The response will contain a direct answer to the question and relevant excerpts and sources from the documentation. Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.