Ultrasonic Sensor Data Acquisition and Gaussian Modeling for Transparent and Reflective Object Recognition in ROS

Aug 1, 2023 · 1 min read

Project Duration: May. 2023 to Aug. 2023

Project Details

  1. Implement URDF-based sensor emulation in Gazebo to match real-world sensor physics
  2. Fine-tune Gazebo object properties for high reflectivity and transparency to evaluate sensor performance
  3. Streamline ROS data collection from ultrasonic sensors, construct Gaussian models, and estimate parameters via Maximum Likelihood Estimation
  4. Calculate the accuracy, recall, and F1 score of recognition, and optimize model parameters

Achievements

Achieved precise acquisition of ultrasonic sensor data and improved the recognition accuracy of highly reflective and highly transparent objects through the Gaussian model.

ROS Sensor Data Machine Learning Gaussian Modeling
LI ZHOUJIAN
Authors
LI ZHOUJIAN
Postgraduate Student