Generating Assistive Humanoid Motions for Co-Manipulation Tasks with a Multi-Robot Quadratic Program Controller - Archive ouverte HAL Access content directly
Conference Papers Year : 2018

Generating Assistive Humanoid Motions for Co-Manipulation Tasks with a Multi-Robot Quadratic Program Controller

Abstract

Human-humanoid collaborative tasks require that the robot take into account the goals of the task, interaction forces with the human, and its own balance. We present a formulation for a real-time humanoid controller which allows the robot to keep itself stable, while also assisting the human in achieving their shared objectives. This is achieved with a multi-robot quadratic program controller, which solves for human motion reconstruction and optimal robot controls in a single optimization problem. Our experiments on a simulated robot platform demonstrate the ability to generate interactions motions and forces that are similar to what a human collaborator would produce.
Fichier principal
Vignette du fichier
root.pdf (2.41 Mo) Télécharger le fichier
Origin Files produced by the author(s)
Loading...

Dates and versions

hal-01590678 , version 1 (20-09-2017)
hal-01590678 , version 2 (22-08-2018)

Identifiers

  • HAL Id : hal-01590678 , version 2

Cite

Kazuya Otani, Karim Bouyarmane, Serena Ivaldi. Generating Assistive Humanoid Motions for Co-Manipulation Tasks with a Multi-Robot Quadratic Program Controller. ICRA 2018 - International Conference on Robotics and Automation, May 2018, Brisbane, Australia. ⟨hal-01590678v2⟩
286 View
491 Download

Share

Gmail Mastodon Facebook X LinkedIn More