5.3. SLAM

A multi-sensor tightly coupled odometry system that fuses LiDAR, vision, and IMU.
Developed based on the FAST-LIVO project open-sourced by the HKU-MARS laboratory, specifically adapted and optimized for Active Camera, it can output the pose of Active Camera in real-time and generate three-dimensional point clouds with color information.

The computational platforms currently supported by this algorithm are listed in the table below:

Computing Platform	General X86 Architecture Computers	Radxa ROCK5B+	OrangePi 5 Ultra	NVIDIA Jetson Orin Nano Super	NVIDIA Jetson AGX Orin	D-Robotics RDK X5
Computing Platform	●	●	●	●	●	●
Sensor	AC1

The following videos demonstrates the offline SLAM effects on two scenic areas using supported computing platforms.

Video Data: Climbing Spot

Video Data: European architecture
Source Code: AC1 SLAM