Deep learning assisted textile sensor matrix for co-adaptive human-robot collaboration

A method for textile-based interaction sensing and control, comprising:

• providing a textile substrate comprising interlaced fibers including semiconducting textile fibers intersecting with metal fibers, wherein intersections between the semiconducting textile fibers and the metal fibers form a plurality of non-ohmic junctions arranged as a distributed textile sensor matrix;
• generating, at the plurality of non-ohmic junctions, electrical signals in response to mechanical stimuli applied to the textile substrate;
• receiving, by one or more processing devices, electrical signals generated by the distributed textile sensor matrix;
• processing the electrical signals using a trained model configured to compensate for variability arising from non-conformal contact between the textile substrate and a user, wherein the trained model analyzes spatiotemporal patterns in the electrical signals;
• classifying, using the trained model, at least one of a user interaction or an object interaction based on the spatiotemporal patterns;
• and
• interfacing with an electromechanical system to cause interaction-dependent control based on the classification.