Door opening and traversal with an industrial cartesian impedance controlled mobile robot

Abstract

This paper presents a holistic approach for door opening with a cartesian impedance controlled mobile robot, a KUKA KMR iiwa. Based on a given map of the environment, the robot autonomously detects the door handle, opens doors and traverses doorways without knowledge of a door model or the door's geometry. The door handle detection uses a convolutional neural network (CNN)-based architecture to obtain the handle's bounding box in an RGB image that works robustly for various handle shapes and colors. We achieve a detection rate of 100% for an evaluation set of 38 different door handles, by always selecting for highest confidence score. Registered depth data segmentation defines the door plane to construct a handle coordinate frame. We introduce a control structure based on the task frame formalism that uses the handle frame for reference in an outer loop for the manipulator's impedance controller. It runs in soft real-time on an external computer with approximately 20 Hz since access to inner controller loops is not available for the KMR iiwa. With the approach proposed in this paper, the robot successfully opened and traversed for 22 out of 25 trials at five different doors.

Phollower—The Universal Autonomous Mobile Robot for Industry and Civil Environments with COVID-19 Germicide Addon Meeting Safety Requirements

“…Potential safety and security features during the design level phase of AMR development were studied in [11], but the presented solutions suffer from low latency in communication systems. Commercial AMRs with comparable technology to Phollower [12][13][14][15][16] mostly use safety LiDAR system with probabilistic algorithms.…”

Consolidating Kinematic Models to Promote Coordinated Mobile Manipulations

“…Notable efforts have recently been dedicated to algorithms or system implementations, focusing on interactive manipulation tasks. For instance, equilibrium point control [4] and impedance control structure [27] are introduced to open doors and drawers. To improve efficiency, Gochev et al used a heuristic-based method to reduce the search space [28].…”

Behavior-Tree-Based Person Search for Symbiotic Autonomous Mobile Robot Tasks

“…Malfunctions can be mitigated by forewarning the users [12] or purposefully utilizing human collaboration in autonomous plans [13]. When a situation occurs where the robot needs help, this must first be identified, for example by detecting a closed door [3] or an elevator [14].…”

“…Contrary to their strength in socially interacting with people, they usually do not have physical manipulators for reasons of cost and complexity. This prevents them from making full use of the environment and, for example, opening doors [3] or operating elevators without further equipment [4]. An approach to compensate for these weaknesses is symbiotic autonomy, which considers the recognition of an individually unsolvable situation and the active involvement of people in problem solving [5].…”