Opening a door with a humanoid robot using multi-sensory tactile feedback

Abstract

This paper presents a multi-sensor based generic approach to opening doors for a dexterous robot. Once the handle has been located by a computer vision algorithm and properly grasped, we are able to open doors without using a model or other prior knowledge of the door geometry. This is done by combining the sensor information of both a force-torque sensor in the robot wrist and a tactile sensor matrix in the robot gripper itself. Our experimental results show that the combination of both sensors achieves the most successful way to open the door.

Adaptive Force/Velocity control for opening unknown doors1

“…Schmid et al (2008) use combination of a tactile and a force-torque sensor in order to control the position and the orientation of the end-effector with respect to the handle and enable a backward pulling of the door to result successful door opening. Kessens et al (2010) use a magnetic end-effector and a specific hardware configuration with clutches that disengage selected robot motors from the corresponding actuating joints and hence enable passive rotation of these joints.…”

Compliant Task-Space Control with Back-Drivable Servo Actuators

“…They use force sensors to decide, when the controller fails to grasp the handle or when the door is blocked. Schmid et al [8] design a controller to adjust the gripper position and orientation in a fixed pose towards the door leaf. They measure deviations from the intended end-effector pose using force and tactile feedback.…”

“Open sesame!” adaptive force/velocity control for opening unknown doors

“…In [19], a combination of tactile-sensor and force-torque sensor is used to control the position and the orientation of the end-effector with respect to the handle. In [20], a specific hardware configuration with clutches that disengage selected robot motors from the corresponding actuating joints and hence enable passive rotation of these joints is used.…”