cuVSLAM: CUDA accelerated visual odometry and mapping
This provides a real-time visual SLAM solution optimized for edge-computing devices like NVIDIA Jetson, benefiting autonomous robotics applications.
The authors tackled the problem of accurate and robust pose estimation for autonomous robots by developing cuVSLAM, a CUDA-accelerated visual SLAM system that supports various sensor configurations and achieves best-in-class performance on state-of-the-art benchmarks.
Accurate and robust pose estimation is a key requirement for any autonomous robot. We present cuVSLAM, a state-of-the-art solution for visual simultaneous localization and mapping, which can operate with a variety of visual-inertial sensor suites, including multiple RGB and depth cameras, and inertial measurement units. cuVSLAM supports operation with as few as one RGB camera to as many as 32 cameras, in arbitrary geometric configurations, thus supporting a wide range of robotic setups. cuVSLAM is specifically optimized using CUDA to deploy in real-time applications with minimal computational overhead on edge-computing devices such as the NVIDIA Jetson. We present the design and implementation of cuVSLAM, example use cases, and empirical results on several state-of-the-art benchmarks demonstrating the best-in-class performance of cuVSLAM.