Intelligent Control for Human-Robot Cooperation in Orthopedics Surgery

Kuang, Shaolong; Tang, Yucun; Lin, Andi; Yu, Shumei; Sun, Lining

doi:10.1007/978-981-13-1396-7_19

Cited by 15 publications

(15 citation statements)

References 27 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The robot performs the task respecting every constraint applied to it (R4) [26] Fuzzy+ MLP Control variables (5) Force Object handling…”

Section: Visionmentioning

confidence: 99%

See 1 more Smart Citation

Human-robot collaboration and machine learning: a systematic review of recent research

Semeraro¹,

Griffiths²,

Cangelosi³

2021

Preprint

View full text Add to dashboard Cite

Technological progress increasingly envisions the use of robots interacting with people in everyday life. Human-robot collaboration (HRC) is the approach that explores the interaction between a human and a robot, during the completion of an actual physical task. Such interplay is explored both at the cognitive and physical level, by respectively analysing the mutual exchange of information and mechanical power. In HRC works, a cognitive model is typically built, which collects inputs from the environment and from the user, elaborates and translates these into information that can be used by the robot itself. HRC studies progressively employ machine learning algorithms to build the cognitive models and behavioural block that elaborates the acquired external inputs. This is a promising approach still in its early stages and with the potential of significant benefit from the growing field of machine learning. Consequently, this paper proposes a thorough literature review of the use of machine learning techniques in the context of human-robot collaboration. The collection, selection and analysis of the set of 45 key papers, selected from the wide review of the literature on robotics and machine learning, allowed the identification of the current trends in HRC. In particular, a clustering of works based on the type of collaborative tasks, evaluation metrics and cognitive variables modelled is proposed. With these premises, a deep analysis on different families of machine learning algorithms and their properties, along with the sensing modalities used, was carried out. The salient aspects of the analysis are discussed to show trends and suggest possible challenges to tackle in the future research. Highlights• Machine learning is assuming a progressively important role in human-robot collaboration.• Categorizations of human-collaboration experiments based on the type of tasks, evaluation metrics, and cognitive variables considered are proposed.• Reinforcement learning is primarily used, although many researchers still use machine learning to produce an output used to select routines for the robot to perform.• It is crucial to make machine learning algorithms sensitive to time dependencies.

show abstract

“…The robot performs the task respecting every constraint applied to it (R4) [26] Fuzzy+ MLP Control variables (5) Force Object handling…”

Section: Visionmentioning

confidence: 99%

“…However, it is clear how, in this type of interaction, the physical component is predominant. In most cases, the robot simply follows the movements of the user in the displacement of the object [26,28,46]. In more complex versions of this task, the robot, while the object is being displaced, maintains certain constraints about it.…”

Section: Collaborative Tasksmentioning

confidence: 99%

Human-robot collaboration and machine learning: a systematic review of recent research

Semeraro¹,

Griffiths²,

Cangelosi³

2021

Preprint

View full text Add to dashboard Cite

show abstract

“…To establish a mathematical model of the body's own laws of motion, a mathematical model based on ''minimum jerk'' and optimization theory was proposed according to the human arm kinematics model [35]. The model of human arm kinematics can be written as in (9), shown at the bottom of this page, where t denotes time of motion, a, b and c denote the undetermined coefficient.…”

Section: Human Arm Kinematics Modelmentioning

confidence: 99%

“…First of all, to realize the doctors' smooth dragging of the robot, it was necessary to determine the damping coefficient B d in the admittance control in (8). According to the experimental methods [9], set B d = 0.5N • s/mm, which was suitable for human-robot dragging in the operating room; Then the subject dragged the robot from point A to point B and repeated 5 times. Finally, in the experiment without the GVFs, the maximum offset D max = 44.94mm as shown in Fig.4 was found, and the distance difference of the experimental trajectory and the human arm kinematics model less than 40mm accounted for 97% of the total data and the distance difference less than 30mm accounted for 71%.…”

Section: Pipeline Gvfs Experiments 1) Experimental Designmentioning

confidence: 99%

“…The safety of surgical robot can be improved though various software and hardware methods [6] such as tactile sensor [7], CT imaging technology [8], impedance /admittance control [9]- [12] and a series of adaptive control methods [13]. During the high-intensity, high-complexity and high-risk robotic surgical operating, doctors are required to intervene as much as possible in robotic movements to achieve accurate surgical requirements, which puts forward extremely high skills requirement for doctors [14].…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

A Virtual Fixtures Control Method of Surgical Robot Based on Human Arm Kinematics Model

et al. 2019

Self Cite

View full text Add to dashboard Cite

Physical human-robot interaction(pHRI) is the most popular way to ensure the safety in robot surgery. Current research of pHRI in operation room focuses on the inside of the surgical area, which adapts virtual fixtures method for ensuring the safety of drag. But the safety problems caused by human error in the stage of dragging the robot from the outside surgical area to the inside surgical area are ignored. Therefore, a method of applying virtual fixtures to the outside of the surgical area is proposed to solve the safety issues during dragging stage outside surgical area. This method takes the kinematics model of human arm as the reference motion trajectory to construct the guided virtual fixtures, which is to restrict the robot movement in a defined area during the pHRI drag. This drag is based on admittance control method to improve safety and ensure flexibility. Experiment results show that the constructed guided virtual fixtures with the trajectory of the human arm model as the central axis, with radius 30mm, and restrict area 5mm can effectively limit the robot motion to a certain range. Simultaneously, the output speed of the robot in tangent direction of the central axis can well follow the change of the force applied by the doctor, and the output speed in the normal direction of the central axis can converge to zero stably at the pipeline boundary. Consequently, the purpose of improving the safety and flexibility of the surgical robot before surgical operation is realized. INDEX TERMS Physical human-robot interaction, security control strategy, arm kinematics, virtual fixtures, surgical robot.

show abstract

Adaptive variable impedance position/force tracking control of fracture reduction robot

Zheng

Lei

et al. 2022

Robotics Computer Surgery

View full text Add to dashboard Cite

Background The operation object of robot‐assisted fracture reduction surgery is the musculoskeletal tissue with rigid‐compliance coupling characteristics. It is necessary to improve the interactive compliance and safety between the reduction robot and the musculoskeletal tissue. Method An adaptive variable impedance position/force tracking control strategy based on friction compensation is proposed. The stiffness of the reduction robot can be adaptively adjusted according to the contact force between the end‐effector and the environment. The Stribeck friction force model of the branch chain electric cylinder is derived to improve the motion control performance. Results The fracture reduction experiment is completed. The experimental results show that the adaptive variable impedance position/force control strategy can realize position and force tracking in fracture reduction. Conclusion A safety control strategy is proposed and applied to robot‐assisted fracture reduction surgery, which improves the coordination and compliance of the human‐robot interaction between the reduction robot and the patient.

show abstract

Intelligent Control for Human-Robot Cooperation in Orthopedics Surgery

Cited by 15 publications

References 27 publications

Human-robot collaboration and machine learning: a systematic review of recent research

Human-robot collaboration and machine learning: a systematic review of recent research

A Virtual Fixtures Control Method of Surgical Robot Based on Human Arm Kinematics Model

Adaptive variable impedance position/force tracking control of fracture reduction robot

Contact Info

Product

Resources

About