Colton Arnold, Zhaohan Cheng, Ajay Kapur
New Interfaces for Musical Expression - London 2026
Colton Arnold, Zhaohan Cheng, Ajay Kapur
International Computer Music Conference - Hamburg 2026
Abstract
This paper presents the modernization of the Machine Lab, a creative studio that integrates digital control with the acoustic physicality of mechatronic musical instruments. Central to this update is the installation of a mechatronic instrument, an 8×8 array of Modulets mounted on the lab’s ceiling, forming an immersive, distributed acoustic environment that enables high-resolution spatialized sound across 64 discrete locations. Key architectural updates include the reintegration of Open Sound Control (OSC), enabling performers and composers to wirelessly network for flexible ensemble configurations. In addition, a novel AI-driven calibration framework is introduced using ChucK’s ChAi library, employing a weighted ensemble of a multi-layer perceptron (MLP) and a k-nearest neighbor (KNN) model. This approach reduces the subjectivity of manual configuration of the mechatronic instruments while ensuring consistent dynamic response and timing accuracy across the Machine Lab. Together, these updates position our collection of custom-built instruments as a scalable platform for immersive performance, pedagogy, and experimental research in mechatronic music systems, supporting both structured composition and exploratory, data-driven practices.
Abstract
This paper presents a data-driven calibration framework for robotic musical instruments based on a hybrid ensemble model that combines K-nearest neighbors (KNN) and a multi-layer perceptron (MLP). KNN anchors predictions to recorded acoustic measurements, while the MLP enables nonlinear generalization and smooth interpolation across the instrument’s playable range. A distance-dependent blending strategy integrates the two models, improving consistency across sparse and dense data. The proposed approach produces stable and repeatable calibration estimates for both pitched and non-pitched instruments, outperforming standalone models across a range of sampling conditions. This work establishes a scalable foundation for automated calibration in robotic musical systems.