Skip to Main content Skip to Navigation
New interface

Glove-based gesture recognition for real-time outdoors robot control

Abstract : Although gesture recognition has been studied for several decades, much research stays in the realm of indoors laboratory experiments. In this thesis, we address the problem of designing a truly usable, real- world gesture recognition system, focusing mainly on the real-time control of an outdoors robot for use by military soldiers. The main contribution of this thesis is the development of a real-time gesture recognition pipeline, which can be taught in a few minutes with: very sparse input ("small data"); freely user-invented gestures; resilience to user mistakes during training; and low computation requirements. This is achieved thanks to two key innovations: first, a stream-enabled, DTW-inspired technique to compute distances between time series; and second, an efficient stream history analysis procedure to automatically determine model hyperparameters without user intervention. Additionally, a custom, hardened data glove was built and used to demonstrate successful gesture recognition and real-time robot control. We finally show this work's flexibility by furthermore using it beyond robot control to drive other kinds of controllable systems.
Document type :
Complete list of metadata

Cited literature [234 references]  Display  Hide  Download
Contributor : ABES STAR :  Contact
Submitted on : Tuesday, September 26, 2017 - 2:58:17 PM
Last modification on : Friday, August 5, 2022 - 2:54:52 PM
Long-term archiving on: : Wednesday, December 27, 2017 - 1:27:50 PM


Version validated by the jury (STAR)


  • HAL Id : tel-01593612, version 1


Marc Dupont. Glove-based gesture recognition for real-time outdoors robot control. Automatic. Université de Bretagne Sud, 2017. English. ⟨NNT : 2017LORIS437⟩. ⟨tel-01593612⟩



Record views


Files downloads