MadMayHam | 合氣道
Regular
I've been trawling (that's the correct way to spell it) for patents that mention "Brainchip" and on several occasions have hit upon Giant.ai, a company developing robotic workers. Their granted patents frequently include the prospect of sensors coupled with neuromorphic chips, of which Brainchip is mentioned as one of the producers. As an example extracted from their latest granted patent,
"[0059] Some embodiments of a robot system 102 including a plurality of sensors may be of a modular system hardware design such that each sensor (or a grouping of sensors) is coupled directly with special-purpose chipsets for performing a space (e.g., like a sub-space) encoding of sensor data prior to downstream digestion by a higher-level component or model (e.g., like an encoder) of the system for determining a state of the robot. The special-purpose chipsets can take a variety of forms, including, but not limited to, Movidius chips, tensorflow edge compute devices, Nvidia Drive PX and Jetson TX1/TX2 Module, Intel Nervana processors, Mobileye EyeQ processors, Habana processors, Qualcomm's Cloud AI100 processors and SoC AI engines, IBM's TrueNorth processors, NXP's S32V234 and S32 chips, AWS Inferentia chips, Microsoft Brainwaive chips, Apple's Neural Engine, ARM's Project Trillium based processors, Cerebras's processors, Graphcore processors, PEZY Computing processors, Tenstorrent processors, Blaize processors, Adapteva processors, Mythic processors, Kalray's Massively Parallel Processor Array, BrainChip's spiking neural network processors, AImotiv's neural network acceleration core, Hailo-8 processors, and various neural network processing units from other vendors."
Hopefully it will lead to a series of actual products then being the only commercial producer of chips we can start to see some revenue soon.
EXPEDITED ROBOT TEACH-THROUGH INITIALIZATION FROM PREVIOUSLY TRAINED SYSTEM
DOCUMENT ID
US 20230109398 A1DATE PUBLISHED
2023-04-06"[0059] Some embodiments of a robot system 102 including a plurality of sensors may be of a modular system hardware design such that each sensor (or a grouping of sensors) is coupled directly with special-purpose chipsets for performing a space (e.g., like a sub-space) encoding of sensor data prior to downstream digestion by a higher-level component or model (e.g., like an encoder) of the system for determining a state of the robot. The special-purpose chipsets can take a variety of forms, including, but not limited to, Movidius chips, tensorflow edge compute devices, Nvidia Drive PX and Jetson TX1/TX2 Module, Intel Nervana processors, Mobileye EyeQ processors, Habana processors, Qualcomm's Cloud AI100 processors and SoC AI engines, IBM's TrueNorth processors, NXP's S32V234 and S32 chips, AWS Inferentia chips, Microsoft Brainwaive chips, Apple's Neural Engine, ARM's Project Trillium based processors, Cerebras's processors, Graphcore processors, PEZY Computing processors, Tenstorrent processors, Blaize processors, Adapteva processors, Mythic processors, Kalray's Massively Parallel Processor Array, BrainChip's spiking neural network processors, AImotiv's neural network acceleration core, Hailo-8 processors, and various neural network processing units from other vendors."
Hopefully it will lead to a series of actual products then being the only commercial producer of chips we can start to see some revenue soon.
Last edited: