首页|Patent Issued for Classification parallelization architecture (USPTO 12067768)
Patent Issued for Classification parallelization architecture (USPTO 12067768)
扫码查看
点击上方二维码区域，可以放大扫码查看
原文链接
NETL
NSTL
The following quote was obtained by the news editors from the background informa tion supplied by theinventors: “Stable and reliable robotic systems are becomin g increasingly common, which has contributedto the recent advancement and proli feration of unmanned system technologies. These technologies canbe ground-based systems, aerial-based systems, and/or maritime-based systems. In many instances thesesystems are equipped with one or more cameras, one or more microphones, a nd/or other recordingequipment. The image/sound stream from the unmanned system (s) may be sent to an operator’s controldevice to make the operator aware of wh at is happening on the ground. In many cases it may be usefulfor the image stre am to be annotated with different objects detected within the video/audio stream .Currently, objects within images/sound frames are generally detected using mac hine learning models.These machine learning models are generally hosted on dedi cated hardware with dedicated data sources.However, in operational scenarios it may be critical to use third-party models (e.g., from entities that areable to train those models because those entities have the required training data). Mor eover, operators inthe field may want to choose which object types need to be d etected for a particular operation becauseindicating other object types may int erfere with the operator being able to assess the operational situation.Thus, e nabling this functionality on an unmanned vehicle or another device with limited computationresources is challenging at best.”
BusinessCyborgsEmerging TechnologiesMachine LearningTomahawk Robotics Inc.
NETL
NSTL
