Adam Berenzweig,Thomas Reardon,Christopher Osborn,Patrick Kaifosh,Brett Jurman,Daniel Wetmore
申请号：
US16557427
公开号：
US20200069211A1
申请日:
2019.08.30
申请国别(地区):
US
年份:
2020
代理人:
摘要：
Computerized systems, methods, and computer-readable storage media storing code for implementing the methods are provided for training an inference model used to generate a musculoskeletal representation. One such system includes a processor programmed to: determine, based on information obtained from at least one image, position information describing a spatial relationship between two or more connected musculoskeletal segments of a user； determine, based on a plurality of neuromuscular signals, force information； associate the position information with the force information； train an inference model to output a musculoskeletal representation consistent with the position information and/or the force information when neuromuscular input signals provided to the inference model have at least one predetermined characteristic, to produce an updated inference model； and cause the updated inference model to be stored in a memory.
