Cheap or Robust? The practical realization of self-driving wheelchair technology

Burhanpurkar, Maya; Labbé, Mathieu; Guan, Charlie; Michaud, François; Kelly, Jonathan

doi:10.1109/icorr.2017.8009393

Cited by 17 publications

(9 citation statements)

References 25 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The lidar’s large field of view also helped during navigation when the robot had to avoid an obstacle, allowing it to localize even if the robot was oriented differently during the mapping. Another example is its use on a low‐cost autonomous wheelchair using only a RGB‐D camera for SLAM and navigation (Burhanpurkar, Labbé, Guan, Michaud, & Kelly, ). To handle textureless corridor environments, wheel odometry was used instead of visual odometry (or visual–inertial odometry) to avoid getting lost as soon as entering a corridor.…”

Section: Discussionmentioning

confidence: 99%

RTAB‐Map as an open‐source lidar and visual simultaneous localization and mapping library for large‐scale and long‐term online operation

Labbé

Michaud

2018

Journal of Field Robotics

707

325

View full text Add to dashboard Cite

Distributed as an open-source library since 2013, real-time appearance-based mapping (RTAB-Map) started as an appearance-based loop closure detection approach with memory management to deal with large-scale and long-term online operation. It then grew to implement simultaneous localization and mapping (SLAM) on various robots and mobile platforms. As each application brings its own set of constraints on sensors, processing capabilities, and locomotion, it raises the question of which SLAM approach is the most appropriate to use in terms of cost, accuracy, computation power, and ease of integration. Since most of SLAM approaches are either visual-or lidar-based, comparison is difficult. Therefore, we decided to extend RTAB-Map to support both visual and lidar SLAM, providing in one package a tool allowing users to implement and compare a variety of 3D and 2D solutions for a wide range of applications with different robots and sensors. This paper presents this extended version of RTAB-Map and its use in comparing, both quantitatively and qualitatively, a large selection of popular real-world datasets (e.g., KITTI, EuRoC, TUM RGB-D, MIT Stata Center on PR2 robot), outlining strengths, and limitations of visual and lidar SLAM configurations from a practical perspective for autonomous navigation applications. K E Y W O R D S perception, position estimation, SLAM

show abstract

Section: Discussionmentioning

confidence: 99%

RTAB‐Map as an open‐source lidar and visual simultaneous localization and mapping library for large‐scale and long‐term online operation

Labbé

Michaud

2018

Journal of Field Robotics

707

325

View full text Add to dashboard Cite

show abstract

“…The experimental results indicated that the door detection rate decreases below 70% as the angle increases. Burhanpurkar, Labbe, Guan, Michaud, and Kelly (2017) separated walls in the point cloud data and filtered points according to the z-axis to obtain the midsection of the wall. In this way, they aimed to develop a method robust against occlusions.…”

Section: Point Cloud Based Approachesmentioning

confidence: 99%

Iç Ortamlarda Kapilarin Tespi̇ti̇ İçi̇n Deri̇n Öğrenme Tekni̇kleri̇ni̇n Karşilaştirilmasi

Kaleci

Turgut

2021

Eskişehir Osmangazi Üniversitesi Mühendislik Ve Mimarlık Fakültesi Dergisi

View full text Add to dashboard Cite

In indoor environments, the detection of doors (open, semi-opened, and closed) is a crucial task for a variety of fields such as robotics, computer vision, and architecture. The studies that are addressed the door detection problem can be divided into three major categories: 1) closed doors via visual data, 2) open doors via range data, and 3) open, semi-opened, and closed doors via point cloud data. Although some successful studies have been proposed being detected doors via visual and range data under specific circumstances, in this study, we exploited point cloud data due to its ability to describe the 3D characteristic of scenes. The main contribution of this study is two-fold. Firstly, we mainly intended to discover the potential of point-based deep learning architectures such as PointNet, PointNet++, Dynamic Graph Convolutional Neural Network (DGCNN), PointCNN, and Point2Sequence, in contrast to previous studies that generally defined a set of rules depending on the type of door and characteristics of the data. Secondly, the OGUROB DOORS dataset is constructed, which contains point cloud data captured in the GAZEBO simulation environment in different robot positions and orientations. We used precision, recall, and F1-score metrics to analyze the merit and demerit aspects of these architectures. Also, some visual results were given to describe the characteristics of these architectures. The test results showed that all architectures are capable of classifying open, semi-opened, and closed doors over 98% accuracy.

show abstract

“…Recent works have used cameras as an exteroceptive sensor to overcome the high price of laser scanners, which increases the accessibility of the IWs. For example, the work Burhanpurkar et al (2017) uses a depth camera RGB-D for mapping and localization. The passages are recognized based on the 3D cloud.…”

Section: Related Work and Backgroundmentioning

confidence: 99%

Methodology for Autonomous Crossing Narrow Passages Applied on Assistive Mobile Robots

Maciel

Pinto

Júnior

et al. 2019

J Control Autom Electr Syst

View full text Add to dashboard Cite

The assistive robotics field works with technologies aimed at assisting people with physical impairments. Simple tasks like passing through doorways can be a significant challenge for motored wheelchairs users. Besides, depending on the disability degree, the task may be impossible to complete without help. Therefore, mobile robotics technologies have been implemented in wheelchairs to give them intelligence, and a supervisory interface inserts the user in the control loop to complete the objectives. Thus, this research proposes an innovative method to assist the user to cross narrow passages automatically. The methodology works in known and unknown environments. Besides, it does not require mapping and global localization algorithms. In this technique, a depth camera recognizes the edges between a narrow path. A Kalman filter method is used to improve the precision of these points even when the passage leaves the camera field of view. Finally, a nonlinear controller performs the narrow passage crossing. This methodology was analyzed using a MATLAB model, Gazebo simulation platform, and a real mobile robot Pioneer-P3DX. The results demonstrated promising applicability. Keywords Narrow passages • Assistive robotics • Mobile robots • Collision avoidance • Intelligent wheelchair 1 Introduction Depending on the disability degree, many people are not able to use both manuals and motorized wheelchairs with an independent movement. For instance, people with quadriplegia or with neuromuscular diseases and older people are unable to use wheelchairs with independence. Therefore, in the last years, researches have been using original mobile robotics technologies for the development of intelligent wheelchairs (IWs) to overcome this issue, such as in Simpson (2005). Different from conventional motorized wheelchairs, the IW has good processing capability, sensors, actuator, and communication interfaces with the user. An intelligent wheelchair is a standard power wheelchair containing a sen

show abstract

Cheap or Robust? The practical realization of self-driving wheelchair technology

Cited by 17 publications

References 25 publications

RTAB‐Map as an open‐source lidar and visual simultaneous localization and mapping library for large‐scale and long‐term online operation

RTAB‐Map as an open‐source lidar and visual simultaneous localization and mapping library for large‐scale and long‐term online operation

Iç Ortamlarda Kapilarin Tespi̇ti̇ İçi̇n Deri̇n Öğrenme Tekni̇kleri̇ni̇n Karşilaştirilmasi

Methodology for Autonomous Crossing Narrow Passages Applied on Assistive Mobile Robots

Contact Info

Product

Resources

About