Sensor fusion is one of the core elements of autonomous technology, and it is something that has really exploded in both capability and needs on ground vehicle autonomous mobility.

Core Elements of an Autonomous System:

  • Sensor measurement and collection of data
  • Interpretation of the data
  • Formulating a plan from the perception of the data
  • Acting on that plan

Sensor fusion is the intersection of the gathering and interpretation of the data.

Reasons to Use Sensor Fusion in Autonomous Mobility

  • Increase data quality:
    • Using sensors with different transducer technology decreases things like common mode, sources of uncertainty, or error.
  • Additional sensors will provide improved ability to estimate unmeasured states.
  • Redundancy:
    • For autonomous systems, we need high levels of robustness and the ability to continue to operate safely.

Problems that Kalman Filter Solves:

  • Improving the estimation of a measurement of a state with much better accuracy and less noise.
  • Using and understanding of the system dynamics and measurement/ process uncertainty.

The Kalman Filter and Sensor Fusion Module in the Intro to Autonomous Mobility 2.0 course will provide the student with the ability to improve localization of the real vehicle data with advanced sensor fusion methods.

Learn More about Sensor Fusion

If you are interested in learning more about sensor fusion in our Intro to Autonomous Mobility 2.0 course, contact us today!

Written by Sarah McClellan