Few-shot learning of repetitive human tasks

Abstract

Few-shot learning of repetitive human tasks is provided. Few-shot learning of repetitive human tasks is performed. Sliding window-based temporal segmentation is performed of sensor data for a plurality of cycles of a repetitive task. Motion alignment is performed of the plurality of cycles, the motion alignment mapping portions of the plurality of cycles to corresponding portions of other of the plurality of cycles. Categories are constructed for each of the corresponding portions of the plurality of cycles according to the motion alignment. Meta-training is performed to teach a model according to data sampled from a labeled set of human motions and the categories for each of the corresponding portions, the model utilizing a bidirectional long short-term memory (LSTM) network to account for length variation between the plurality of cycles. The model is used to perform temporal segmentation on a data stream of sensor data in real time for predicting motion windows within the data stream.

Description

technical field [0001] The present disclosure concerns few-shot learning of repetitive human tasks. Background technique [0002] In modern industrial manufacturing, low-cost smart sensors are commonly used to monitor, analyze and improve assembly processes. In particular, body-mounted motion sensors can continuously record high-precision movement signals. Advanced machine learning systems can then be built on top of them to perform anomaly detection, efficiency analysis, and poka-yoke feedback, among other things. At each station along the assembly line, operators need to complete sequences of assembly steps in a standard and timely manner. The human activities involved are often repetitive. [0003] Few-shot learning is a task in which a classifier is adapted to new classes not seen during training, given only a few examples of each of these classes. Types of few-shot learning models include matching networks and prototype networks. A problem with systems performing f...

AI Technical Summary

Problems solved by technology

A problem with systems performing few-shot learning is overfitting, where the error on the training set is driven to a small value, but new data presented to the network gives a generally unusable large error

Images