Paper Submission: Versatile Door Operation for Autonomous Door Operation

Here, we advance on real-time grasping pose estimation of single or multiple handles from RGB-D images, providing a speed up for assistive human-centered behaviors. We propose a versatile Bayesian framework that endows robots with the ability to infer various door kinematic models from observations of its motion. Combining this probabilistic approach with a state-of-the- art motion planner, we achieve efficient door grasping and subsequent door operation regardless of the kinematic model using the Toyota Human Support Robot.

arXiv Preprint: M. Arduengo, C. Torras, L. Sentis, A Versatile Framework for Robust and Adaptive Door Operation with a Mobile Manipulator Robot