Course Code: fs3bs
Duration: 2 hours
Overview:

Objective: Introduce the team to AI techniques for sensor fusion, particularly for bridging and integrating data from multiple sensors.

Course Outline:

 

Agenda:

 

Introduction to Sensor Fusion (15 minutes)

  • Overview of sensor fusion and its importance in AI applications.
  • Examples of sensor fusion in future systems.

AI Techniques for Sensor Fusion (15 minutes)

  • Introduction to AI algorithms for sensor fusion (e.g., Kalman filters, neural networks).
  • Demonstration of a selected algorithm.

Hands-On Exercise: Implementing Sensor Fusion (30 minutes)

  • Practical exercise: Use AI to combine data from multiple sensors and improve decision-making.
  • Implementing a Kalman filter or a neural network-based sensor fusion model.

Case Study: Sensor Fusion in Action (30 minutes)

  • Review of a case study where sensor fusion was successfully applied.
  • Practical exercise: Analyze and interpret the results of the sensor fusion model.

Q&A and Future Directions (30 minutes)

  • Addressing questions and discussing future trends in AI sensor fusion.
  • Exploring additional AI tools and resources for further learning.

Materials Needed:

  • Laptops with internet access.
  • Access to AI tools and libraries for sensor fusion (e.g., Python libraries, MATLAB).
  • Sample sensor data for practical exercises.