Collision Avoidance Route Planning for Autonomous Medical Devices Using Multiple Depth Cameras

Abstract

Radiography is one of the most widely used imaging techniques in the world. Since its inception, it has continued to evolve, leading to the development of intelligent and automated radiography systems that are able to perceive parts of their environment and respond accordingly. However, such systems do not provide a complete view of the examination space and are therefore unable to detect multiple objects and fully ensure the safety of patients, staff and equipment during the execution of the movement. In this paper, we present a system architecture based on ROS (Robot Operating System) to solve these challenges and integrate an autonomous X-ray device. The architecture retrieves point clouds from range sensors placed at specific locations in the examination room. By integrating different subsystems, the architecture merges the data from the different sensors to map the space. It also implements downsampling and clustering methods to identify objects and later distinguish obstacles. A subsystem generates bounding boxes based on the detected obstacles and feeds them to a motion planning framework (MoveIt!) to enable collision avoidance during motion execution. At the same time, a subsystem implements a deep neural network model (PointNet) to classify the detected obstacles. Finally, the developed system architecture provided promising results after being deployed in a Gazebo simulated examination space and on a use case test platform.

Emerging Trends in Realistic Robotic Simulations: A Comprehensive Systematic Literature Review

“…They ensure that while a robot remains agile in its movements, it doesn't endanger its integrity or that of its environment. [116], ICP 3 + SVM 4 [132], 2D multi-SLAM [77], GMapping [87], [88], [105], FNN 5 [27], Visual-SLAM + RTAB-Map 6 [126], RTAB-Map [94], Cartographer [65], Monocular SLAM + RL [36], KimeraMulti [133] 2 -Object Detection YOLOv4 7 [62], [103], YOLOv3 [31], [59], [62], YOLOv2 [134], PointNet [135], CNN 8 [21], [23], [136], SVM [137], MobileNet [138], YOLOv2 + JPDA 9 + IMM 10 [139] 3 -Object Tracking…”

Autonomous Navigation of Robots: Optimization with DQN

“…Due to technological advances, the research and implementation of robotic systems are in constant development, trying to optimize self-control, leading their system to be based on autonomous operations and intelligent decision making [42,43]. Especially for movement, different control methods have been designed that vary according to their field of application; however, the most used is the predictive model, which is based on generating a decision based on statistics, which in turn uses a large amount of data in industrial environments [44][45][46][47][48][49].…”

Three-Dimension Digital Twin Reference Architecture Model for Functionality, Dependability, and Life Cycle Development Across Industries

“…The other life cycle stages elements have been added for demonstration purposes. The first application represents the work of Mahmeen et al (2022) [45] and can be described according to the Digital Twin applications model of Newrzella et al (2021) [4] as follows. Mahmeen et al describe a Digital Twin of a Radiography device's environment using real-time device encoder data and point cloud data from room depth cameras in a rule-based model for enabling autonomous collision avoiding movement of the device.…”