Tunnel Inspection Demo(24 Winter, Fukushima)

• Description: In the recent field test, conducted in Fukushima Robot Test Field, we deployed our self-designed UAV and dynamic mapping system within a real tunnel environment to perform comprehensive inspection tasks. The drone leveraged advanced LIO-based positioning and an integrated LiDAR-camera sensor suite, which enabled real-time dynamic object detection and tracking. This sophisticated approach ensured safe navigation throughout the tunnel, even in the presence of both static and dynamic obstacles deliberately placed to simulate real-world conditions. As a result, our system successfully completed the autonomous inspection of the entire tunnel, demonstrating its robust performance and enhanced safety in challenging environments.
• Role and Contribution:
  • Develop the dynamic obstacle detection and tracking module.
  • Use dynamic removal to assist building the global occupancy map.
  • Implemented dynamic removal for occupancy map.
  • Validated in tunnel with static and dynamic obstacles.
• Demo Video:Google Drive

Tech Stack

• Hardware:
  • Sensors:
    • LiDAR: For precise distance measurements and obstacle detection.
    • Intel RealSense D435i: Provides RGB-D information
    • PX4 IMU: High-precision IMU(Inertial Measurement Unit) for motion tracking.
  • Flight Controller: PX4 Flight Controller for managing UAV operations.
  • Processing Unit: NVIDIA Jetson Orin NX for onboard computing.
  • Communication: Wi-Fi and telemetry modules for data transmission and remote control.
• Software:
  • Operating System: Ubuntu 20.04 LTS
  • Flight Stack: PX4 Autopilot for flight control and navigation.
  • Localization & Mapping: FAST-LIO2 for real-time localization.
  • Programming Languages: C++, Python
  • Middleware: ROS Noetic for managing communication between different system components.
  • Obstacle Avoidance Algorithms: Custom algorithms integrated with sensor data for real-time obstacle detection and avoidance.

Key Features

• Autonomous Navigation: Capable of navigating complex environments without GPS by utilizing LiDAR and visual sensors for real-time localization and mapping.
• High Odometry Frequency: Enhanced odometry frequency through the integration of Fast-LIO2 and PX4 IMU, ensuring accurate and stable flight control.
• Light-Weight Design: Optimized for minimal weight to extend flight duration and improve maneuverability.
• Modular Architecture: Designed with modularity in mind, allowing for easy upgrades and maintenance of hardware and software components.