AI & ML
Design and Evaluation of a Body-Machine Interface as an Alternative Control Paradigm for Pedal-based Sewing Machines
arXiv cs.HC0 views
arXiv:2611.25261v1 Announce Type: new Abstract: Body-machine interfaces (BoMIs) exploit body movements to control assistive devices; they have been evaluated primarily in tasks such as cursor control or robotic manipulation where the entire movement repertoire is devoted toward device control. However, tasks with multiple concurrent processes require the user to share the movement repertoire used for device control with other body movements for task execution. This issue is examined here in the context of sewing, where the sewing machine is typically controlled by a pedal in coordination with hand movements for guiding the fabric. We evaluated the learning of a trunk-controlled BoMI for sewing machine control, and compared it with conventional pedal control. Twenty-four novice participants (12 BoMI, 12 Pedal) completed 10 trials of a standardized sewing assessment followed by 3 trials of a transfer task. The BoMI mapped trunk movements to the sewing machine's full functional repertoire, which included continuous speed control of the needle, and discrete actions such as presser-foot and needle lifts. The two groups learned at comparable rates, showing similar completion times and error counts; for both groups, completion time reduced by approximately 30\%. Additional analyses showed that the BoMI group had fewer presser-foot lift errors during training and fewer errors on the first transfer trial. Both groups also exhibited similar subjective workload. These findings collectively demonstrate that a BoMI interface can support sewing-machine control during concurrent manual activity, highlighting the potential for using BoMIs for increasing accessibility in industrial workplace contexts.
Source:https://arxiv.org/abs/2611.25261PreviousTowards Restorative Urban Spaces: An Exploratory Field Study of Nature Videos on Public Multi-Display SignageNextAI Deactivation Reduces Loneliness and Increases Social Interaction
Related posts

Serving Qwen3.5-0.8B with a 0.016% weight edit: measure the loops, pin the sampling on the server
0dev.to
Design Tokens for AI: Extract a Website's Real Colours, Fonts, Shadows and Icons So an LLM Builds On Brand
0dev.to
Trying to get our Arms around AI efficiency
0Stack Overflow Blog
Why an Embedded Game Fails on Some Phones, and How to Debug It
0dev.to
Microsoft 365 vs Office 2024: The Break-Even Math
0dev.to
Master AI Evals: Build Reliable, Scalable Model Evaluation Pipelines
0dev.to