Improving Human-Robot Object Exchange by Online Force Classification - Archive ouverte HAL Access content directly
Journal Articles Journal of Human-Robot Interaction Year : 2015

Improving Human-Robot Object Exchange by Online Force Classification

Abstract

Handing an object over to a human is a challenging task for a robot to perform, especially when the human partner has no experience interacting with robots. This paper presents our work to enable a robot to learn how to achieve this task with wrist force/torque sensing. Firstly, we present a device to record the data, then we discuss the techniques used for the teaching. We choose to focus on the classification problem defined to enable the robot to find the finger opening movement. The main challenge is that the classification should be run online, at a comparable rate to the controller. To achieve a computationally efficient classifier, the Wavelet Packet Transformation is used for feature extraction, and then we used the Fisher criterion to reduce the dimension of features. A Relevance Vector Machine is used for the continuous classification procedure mainly for its sparsity. Some recorded data and the results from dimension reduction are shown, then we discuss the accuracy and sparsity of the classification by Relevance Vector Machine in this application. The software of continuous classification on forces is then tested on the robot for interactive object exchange between human and robot, which gives promising results.
Fichier principal
Vignette du fichier
learnToManip_HAL.pdf (933.17 Ko) Télécharger le fichier
Origin : Files produced by the author(s)
Loading...

Dates and versions

hal-01144318 , version 1 (21-04-2015)

Identifiers

  • HAL Id : hal-01144318 , version 1

Cite

Wuwei He, Daniel Sidobre. Improving Human-Robot Object Exchange by Online Force Classification. Journal of Human-Robot Interaction, 2015, 4 (1), pp. 75-94. ⟨hal-01144318⟩
201 View
292 Download

Share

Gmail Facebook X LinkedIn More