发明名称 Intelligent modular robotic apparatus and methods
摘要 Apparatus and methods for an extensible robotic device with artificial intelligence and receptive to training controls. In one implementation, a modular robotic system that allows a user to fully select the architecture and capability set of their robotic device is disclosed. The user may add/remove modules as their respective functions are required/obviated. In addition, the artificial intelligence is based on a neuronal network (e.g., spiking neural network), and a behavioral control structure that allows a user to train a robotic device in manner conceptually similar to the mode in which one goes about training a domesticated animal such as a dog or cat (e.g., a positive/negative feedback training paradigm) is used. The trainable behavior control structure is based on the artificial neural network, which simulates the neural/synaptic activity of the brain of a living organism.
申请公布号 US9299022(B2) 申请公布日期 2016.03.29
申请号 US201414468928 申请日期 2014.08.26
申请人 QUALCOMM TECHNOLOGIES INC. 发明人 Buibas Marius;Sweet, III Charles Wheeler;Caskey Mark S.;Levin Jeffrey Alexander
分类号 G06N3/04 主分类号 G06N3/04
代理机构 Seyfarth Shaw LLP 代理人 Seyfarth Shaw LLP
主权项 1. A computerized neuromorphic apparatus, comprising: at least one mount configured to physically secure the computerized neuromorphic apparatus inside a robotic device; a storage device configured to store a plurality of network image files, each network image file specifying an artificial neural network corresponding to a finite state machine in a particular configuration; and a processor in data communication with the storage device, the processor configured to run at least one computer program thereon, the computer program comprising a plurality of instructions configured to, when executed: access at least one network image file from the plurality of network image files;based at least in part on the at least one network image file, load the state of the neural network; andsend a command to a modular robotic component based at least in part on a subsequent state evolution of the loaded neural network;wherein the command is configured to initiate at least a control loop, an estimation loop, or combination thereof.
地址 San Diego CA US