ROS-Based Cognitive Surgical Robotics

Bihlmaier, Andreas; Beyl, Tim; Nicolai, Philip; Kunze, Mirko; Mintenbeck, Julien; Schreiter, Luzie; Brennecke, Thorsten; Hutzl, Jessica; Raczkowsky, Jörg; Wörn, Heinz

doi:10.1007/978-3-319-26054-9_12

Cited by 8 publications

(3 citation statements)

References 2 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…A medical robotics platform, the CISST library, offers an OpenIGTLink bridge to integrate image visualization software into medical robotics applications [33]. OpenIGTLink is also used with ROS-based robotic system for laparoscopic interventions [34]. The ROS-IGTL-Bridge is a generalization of those prior works aiming to extend the successful model found in the medical image computing field, and has the potential to facilitate the sharing of engineering resource between the medical robotics and medical image computing.…”

Section: Discussionmentioning

confidence: 99%

ROS-IGTL-Bridge: an open network interface for image-guided therapy using the ROS environment

et al. 2017

View full text Add to dashboard Cite

Purpose With the growing interest in advanced image-guidance for surgical robot systems, rapid integration and testing of robotic devices and medical image computing software are becoming essential in the research and development. Maximizing the use of existing engineering resources built on widely accepted platforms in different fields, such as Robot Operating System (ROS) in robotics and 3D Slicer in medical image computing could simplify these tasks. We propose a new open network bridge interface integrated in ROS to ensure seamless cross-platform data sharing. Methods A ROS node named ROS-IGTL-Bridge was implemented. It establishes a TCP/IP network connection between the ROS environment and external medical image computing software using the OpenIGTLink protocol. The node exports ROS messages to the external software over the network and vice versa simultaneously, allowing seamless and transparent data sharing between the ROS-based devices and the medical image computing platforms. Results Performance tests demonstrated that the bridge could stream transforms, strings, points, and images at 30 fps in both directions successfully. The data transfer latency was less than 1.2 ms for transforms, strings, and points, and 25.2 ms fo rcolor VGA images. A separate test also demonstrated that the bridge could achieve 900 fps for transforms. Additionally, the bridge was demonstrated in two representative systems: a mock image-guided surgical robot setup consisting of 3D Slicer, and Lego Mindstorms with ROS as a prototyping and educational platform for IGT research; and the smart tissue autonomous robot (STAR) surgical setup with 3D Slicer. Conclusion The study demonstrated that the bridge enabled cross-platform data sharing between ROS and medical image computing software. This will allow rapid and seamless integration of advanced image-based planning/navigation offered by the medical image computing software such as 3D Slicer into ROS-based surgical robot systems.

show abstract

Section: Discussionmentioning

confidence: 99%

ROS-IGTL-Bridge: an open network interface for image-guided therapy using the ROS environment

et al. 2017

View full text Add to dashboard Cite

show abstract

“…The robot's control was implemented utilizing the Robot Operating System (ROS) as middleware [25]. During hands-on mode the control software compensated for gravity forces on the robot, however recognizing forces applied by the surgeon's hand as commands [26]. Furthermore, our implementation allowed operating robots with different kinematics and varying degrees of freedom (DoF) with robots ranging from kinematically deficient (3 DoF) to kinematically redundant (7 DoF).…”

Section: Actionmentioning

confidence: 99%

A learning robot for cognitive camera control in minimally invasive surgery

et al. 2021

Self Cite

View full text Add to dashboard Cite

Background We demonstrate the first self-learning, context-sensitive, autonomous camera-guiding robot applicable to minimally invasive surgery. The majority of surgical robots nowadays are telemanipulators without autonomous capabilities. Autonomous systems have been developed for laparoscopic camera guidance, however following simple rules and not adapting their behavior to specific tasks, procedures, or surgeons. Methods The herein presented methodology allows different robot kinematics to perceive their environment, interpret it according to a knowledge base and perform context-aware actions. For training, twenty operations were conducted with human camera guidance by a single surgeon. Subsequently, we experimentally evaluated the cognitive robotic camera control. A VIKY EP system and a KUKA LWR 4 robot were trained on data from manual camera guidance after completion of the surgeon’s learning curve. Second, only data from VIKY EP were used to train the LWR and finally data from training with the LWR were used to re-train the LWR. Results The duration of each operation decreased with the robot’s increasing experience from 1704 s ± 244 s to 1406 s ± 112 s, and 1197 s. Camera guidance quality (good/neutral/poor) improved from 38.6/53.4/7.9 to 49.4/46.3/4.1% and 56.2/41.0/2.8%. Conclusions The cognitive camera robot improved its performance with experience, laying the foundation for a new generation of cognitive surgical robots that adapt to a surgeon’s needs.

show abstract

“…The ROS open-source operating system can solve these problems well and can be directly applied to practical systems. Based on this, this paper uses ROS-Melodic on Ubuntu18.04 to build the necessary nodes for underwater robot obstacle avoidance, incorporates the improved artificial potential field method into the obstacle avoidance path planning node, proposes a ROS-based underwater robot obstacle avoidance method, and conducts experimental verification [10].…”

Section: Introductionmentioning

confidence: 99%

The underwater obstacle avoidance method based on ROS

Zhang¹,

Lu²,

et al. 2023

J. Phys.: Conf. Ser.

View full text Add to dashboard Cite

To achieve real-time obstacle avoidance for underwater robots, the artificial potential field method can be selected as the obstacle avoidance path planning algorithm. However, this method applies a large attractive force to the underwater robot when it is far from the target point, causing it to collide with obstacles. Additionally, when the underwater robot just enters the repulsion influence zone, the repulsion force that it experiences undergoes an abrupt change, resulting in a non-smooth obstacle avoidance path. Furthermore, developing the obstacle avoidance function based on software platforms such as MATLAB has a long algorithm verification cycle, and it is difficult to transfer the algorithm model to practical scenarios. Therefore, this paper proposes an underwater robot obstacle avoidance method based on ROS. Firstly, a dynamic adjustment factor is introduced into the potential field function of the artificial potential field method to redefine the obstacle influence zone, and an improved artificial potential field method is designed as the obstacle avoidance path planning algorithm for underwater robots. The experiment is conducted on the ROS simulation platform, and the results show that the improved algorithm can solve the two problems existing in the artificial potential field method. Secondly, nodes required for underwater robot obstacle avoidance are established based on the ROS operating system, and the improved artificial potential field method is integrated into the obstacle avoidance path planning node. Finally, the obstacle avoidance experiment of the Bluerov2 underwater robot is conducted in a pool, and the experimental results demonstrate that the proposed method can achieve real-time obstacle avoidance for underwater robots.

show abstract

ROS-Based Cognitive Surgical Robotics

Cited by 8 publications

References 2 publications

ROS-IGTL-Bridge: an open network interface for image-guided therapy using the ROS environment

ROS-IGTL-Bridge: an open network interface for image-guided therapy using the ROS environment

A learning robot for cognitive camera control in minimally invasive surgery

The underwater obstacle avoidance method based on ROS

Contact Info

Product

Resources

About