Cross-platform GPU boost speeds up visual-inertial odometry on many devices
VkVIO: Cross-platform GPU Acceleration for Visual-Inertial Odometry with Vulkan
RoboticsComputer Vision and Pattern Recognition
Summary
Good tracking of movement and position is key for robots and augmented reality devices to work well. The authors created VkVIO, a tool that uses a graphics programming system called Vulkan to speed up this tracking on many types of devices, not just those from a single company. This means that even low-cost computers or mobile devices can run these complex calculations faster and cooler, helping make smaller and more efficient robots and AR gear. Their system matches or beats previous methods that used more limited graphics tools.
What this means in practice
- •For robotics engineers: Deploy low-latency visual-inertial odometry on diverse hardware to improve robot navigation and reduce device size and power consumption.
- •For xr device developers: Implement cross-platform GPU acceleration for state estimation to enable efficient augmented and virtual reality headsets with extended battery life.
Authors
Ole Hoffmann, Mateo de Mayo, Daniel Cremers
Abstract
Perception in robotics and XR fundamentally relies on good state estimation. Visual-inertial odometry (VIO) and Simultaneous Localization and Mapping (VI-SLAM) are proven ways of achieving this goal in a cost-effective and accurate manner. Efficiency in these systems allows for smaller, cooler, and lighter devices. GPU acceleration is a natural approach for reducing latency, thanks to their wide availability in platforms like embedded computers, mobile phones, and XR headsets. However, previous works in the literature have limited themselves to the use of CUDA for this task, significantly reducing deployment options to a single vendor. We instead leverage the vendor-agnostic Vulkan API, originally designed for the strict performance requirements of 3D graphics applications. In this work, we present VkVIO, the first, to the best of our knowledge, cross-platform GPU-accelerated VIO method. We provide state-of-the-art accuracy with causal estimates required for real-time operation. We deploy VkVIO on a diverse range of devices spanning a workstation, a laptop, and an extremely inexpensive single-board computer, while outperforming CUDA-based systems on the same hardware. VkVIO enables possibilities for low-latency, low-power, and low-cost VIO in robotics and XR.