Multi-Sensor Data Fusion
In this class, we will review the sensor fusion problem and lay out requirements. The use of multiple, heterogeneous sensors requires more processing and is more complex than situations using a single sensor type.
Many types of algorithms can be used in multi-sensor data fusion. Many are statistical, but not all. In this class, we will discuss the types of algorithms available.
Understanding the types of sensors involved is critical. Each type of sensor contains different information and covers a different spatial range. By layering sensors in an intelligent way, we can develop the picture required for the task at hand.
In this class, we pull together the lessons learned in the previous sessions to come up with a general approach to the problem. We will demonstrate how systems can be developed and discuss some of the tools that will prove useful. This includes frameworks that can be applied to multiple problems.
In this class, we will give examples of multi-sensor data fusion, which include robotics, autonomous vehicles, and military aviation.
Louis Giokas started out in the aerospace business holding positions in development and management. At General Electric Aerospace (now part of Lockheed Martin) he held positions of software engineer, systems engineer and staff engineer. While there he worked on spacecraft and military systems. Prior to that he worked for companies such as Sperry UNIVAC and Link Simulation Systems, also working or spacecraft and military systems. Over the past two decades he has worked in the database management software area for Oracle and IBM. Over the past several years he has worked on development projects and has consulted in a number of different areas, including embedded systems. He is a long-standing member of the Institute of Electrical and Electronics Engineers (IEEE). Currently, he is the secretary of the Fox Valley Subsection of the Chicago Section and chairman of the Computer Society of the Chicago Section. He has a degree in Computer Science from Villanova University and is pursuing a MS in Applied Statistics from DePaul University.