The joint offering will, the two companies say, enable manufacturers of AR/VR/MR headsets and home/industrial robots to integrate efficient, low-latency 3D sensing and SLAM into their products. The solution merges Occipital’s Structure Core embeddable depth sensor with Inuitive’s NU3000 depth processing chip.
The combination of Structure Core and NU3000 is designed for use in the new generation of home & industrial robots as well as headsets. In particular, Structure Core’s dual infrared cameras can be used for stereo depth sensing when ambient sunlight would otherwise blind robotic navigation systems that rely on time-of-flight or structured light depth sensors.
For the past year, Occipital and Inuitive have worked together to tightly integrate Structure Core and NU3000 to achieve levels of performance that minimize host system loads while delivering an high levels of user experience, and at low power consumption.
The outcome is a system able to sense depths from 30 cm to greater than 5m with an accuracy as high as ±0.17% RMS at 1m (using fit-to-plane). The integrated solution reduces CPU load to be equivalent to <25% of a recent dual-core ARM CPU during 6-DoF (degrees-of-freedom) tracking. [Ed. Note; six degrees being motion in 3 axes and rotation about three axes.]
System latency (from camera to fully-tracked pose) is 10 msec. Even with this high performance, the power consumption for depth + visible is between 1.3W and 2.0W, depending on the configuration selected.
Along with Structure Core, Occipital also offers Bridge Engine, an MR [merged- or mixed-reality] software engine and development platform. Available on multiple platforms, Bridge Engine allows manufacturers to accelerate development of market-ready devices with advanced position-tracked VR and mixed reality capabilities.
Inuitive’s products combine 3D Depth sensing, Computer Vision and Deep Learning capabilities; https://inuitive.com