Passing through Open/Closed Doors: A Solution for 3D Scanning Robots

Abstract

In this article, a traversing door methodology for building scanning mobile platforms is proposed. The problem of passing through open/closed doors entails several actions that can be implemented by processing 3D information provided by dense 3D laser scanners. Our robotized platform, denominated as MoPAD (Mobile Platform for Autonomous Digitization), has been designed to collect dense 3D data and generate basic architectural models of the interiors of buildings. Moreover, the system identifies the doors of the room, recognises their respective states (open, closed or semi-closed) and completes the aforementioned 3D model, which is later integrated into the robot global planning system. This document is mainly focused on describing how the robot navigates towards the exit door and passes to a contiguous room. The steps of approaching, door-handle recognition/positioning and handle–robot arm interaction (in the case of a closed door) are shown in detail. This approach has been tested using our MoPAD platform on the floors of buildings composed of several rooms in the case of open doors. For closed doors, the solution has been formulated, modeled and successfully tested in the Gazebo robot simulation tool by using a 4DOF robot arm on board MoPAD. The excellent results yielded in both cases lead us to believe that our solution could be implemented/adapted to other platforms and robot arms.

Mapping beyond what you can see: Predicting the layout of rooms behind closed doors

“…Our method assumes that the robot can detect the position of closed doors inside the environment (blue dots in Fig. 2a), for example by using existing computer vision methods like [6,7]. Consequently, the initial input of our method is a grid map M and a set of closed door locations d ∈ D. Although doors are represented as line segments in 2D maps, our method considers their middle points.…”

“…We assume a robot that is able to build a 2D grid map of an indoor environment in which some doors are closed and that is able to detect the positions of such closed doors. Since detecting doors (e.g., from vision) is not the purpose of this paper, we assume that the robot employs a method like [6,7]. Given a grid map (Fig.…”

Towards a balancing safety against performance approach in human–robot co-manipulation for door-closing emergencies

“…In some cases, the researchers would suitably treat the unlocked door driven by external dis-turbances depending on the further task's difficulty. For easy tasks such as opening the door only to traverse it [32,33], it is no need to care too much about the unlocked door's state information due to a quick pass through after door-opening. However, complex tasks such as opening the door to get handwork inside [34,35], are generally more time-consuming and need more operating precision.…”

Efficient multitask learning with an embodied predictive model for door opening and entry with whole-body control

“…There are a lot of motion patterns in the door-opening and passing-through task that depend on complex factors such as door type (inward, outward, and sliding), door construction (open right or left), and door handle type/position. Therefore, door opening is a difficult task that requires the extraction and programming of all possible situations and their behavioral patterns for a particular situation (39)(40)(41)(42)(43). In an experiment, we train three motions using DPL for outwardopening doors (approaching, opening, and passing through a door) and confirm whether a sequence of motions (opening outward door and passing through) can be generated on the basis of the certainty of each module.…”