Intel tracking camera guides autonomous devices
January 31, 2019
Intel has introduced a stand-alone inside-out tracking camera that will provide developers with a building block for autonomous devices, delivering guidance and navigation.
The RealSense T265 tracking camera uses proprietary visual inertial odometry simultaneous localisation and mapping (V-slam) technology with computing at the edge and suits applications that require highly accurate and low-latency tracking, including robotics, drones, augmented reality (AR) and virtual reality.
“Understanding your environment is a critical component for many devices,” said Sagi Ben Moshe, vice president at Intel. “The T265 was designed to complement our existing RealSense depth cameras and provide a quick path to product development with our next-generation integrated V-slam technology.”
The camera is powered by the Intel Movidius Myriad 2 vision processing unit, which directly handles all the data processing for tracking on the machine. This gives the camera a small footprint and reduces power consumption. Developers can implement it into existing designs or build their own intellectual property that requires rich visual intelligence.
Suitable applications include where tracking the location of a device is important, especially in locations without GPS service, such as warehouses or remote outdoor areas where the camera uses a combination of known and unknown data to navigate accurately to its destination. It is also designed for flexible implementation and can be added to small-footprint mobile devices such as lightweight robots and drones, as well as for connectivity with mobile phones or AR headsets.
For example, integrating the camera into a robot for agriculture allows the device to navigate fields in a precise lawn-mower-style pattern and intelligently adapt to avoid obstacles in its environment, including structures or people. Whether bringing medical supplies to remote, off-the-grid areas or to a lab inside a hospital ward, the T265 can be used in drone or robotic deliveries due to its wider field of view and optimisation for tracking use cases.
Inside-out tracking means the device does not rely on any external sensors to understand the environment. It delivers six degrees-of-freedom inside-out tracking by gathering inputs from two on-board fish-eye cameras, each with an approximate 170˚ range of view. The V-slam systems construct and continually update maps of unknown environments and the location of a device within that environment. Since all position calculations are performed directly on the device, tracking is platform independent and allows the camera to run on very low-compute devices.
The T265 complements RealSense D400 series cameras, and the data from both devices can be combined for applications such as occupancy mapping, improved 3D scanning, and navigation and collision avoidance in GPS-restricted environments. The only hardware requirements are sufficient non-volatile memory to boot the device and a USB 2.0 or 3.0 connection that provides 1.5W of power.
It is available for pre-order and will begin shipping at the end of February for nearly $200.