# Robust and Adaptive Door Operation with a Mobile Robot

## TL;DR

This paper presents a robust, real-time door operation framework for mobile robots that combines neural networks, Bayesian inference, and motion planning to adaptively handle various door types in assistive scenarios.

## Contribution

It introduces a novel fusion of CNNs with point cloud processing and a Bayesian approach for inferring door kinematics, enabling adaptive and efficient door manipulation.

## Key findings

- Real-time grasping pose estimation from RGB-D images.
- Successful inference of door kinematic models from observations.
- Effective door operation across different models in real-world tests.

## Abstract

The ability to deal with articulated objects is very important for robots assisting humans. In this work, a framework to robustly and adaptively operate common doors, using an autonomous mobile manipulator, is proposed. To push forward the state-of-the-art in robustness and speed performance, we devise a novel algorithm that fuses a convolutional neural network with efficient point cloud processing. This advancement enables real-time grasping pose estimation for multiple handles from RGB-D images, providing a speed up improvement for assistive human-centered applications. In addition, we propose a versatile Bayesian framework that endows the robot with the ability to infer the door kinematic model from observations of its motion and learn from previous experiences or human demonstrations. Combining these algorithms with a Task Space Region motion planner, we achieve an efficient door operation regardless of the kinematic model. We validate our framework with real-world experiments using the Toyota Human Support Robot.