Background: Epidural anaesthesia is a Percutaneous Procedure (PP) which plays a crucial role in surgical procedures, where accurate needle insertion is still challenging. The objective of this work is to present a Tuohy needle path planning, which allows an anaesthesiologist to drive semiautonomously, with the assistance of a teleoperated robot, the tip of the needle during this PP.Methods: We capture, analysed and modelled the anaesthetist hands' motion during the execution of this procedure, by synthetising, programing and simulating a parametrised and normalised kinematic constrains dependent on an insertion variable in a virtual robot.Results: Two preoperative path planning models were obtained, which provide a teleoperated robot with kinematic constraints to semiautonomously drive a Tuohy needle in the epidural anaesthesia procedure.Conclusions: A semiautonomous robot can assist in the execution of this PP using the kinematic constraints obtained from the study of the movement of a specialist's hands.

Surgical instrument segmentation in images is crucial for improving precision and efficiency in surgery, but it currently relies on costly and labor-intensive manual annotations. An unsupervised approach is a promising solution to this challenge. This paper introduces a surgical instrument segmentation method using unsupervised machine learning, based on the K-means algorithm, to identify Regions of Interest (ROI) in images and create the image ground truth for neural network training. The Gamma correction adjusts image brightness and enhances the identification of areas containing surgical instruments. The K-means algorithm clusters similar pixels and detects ROIs despite changes in illumination, yielding an efficient segmentation despite variations in image illumination and obstructing objects. Therefore, the neural network generalizes the image features learning for instrument segmentation in different tasks. Experimental results using the JIGSAWS and EndoVis databases demonstrate the method's effectiveness and robustness, with a minimal error (0.0297) and high accuracy (0.9602). These results underscore the precision of surgical instrument detection and segmentation, which is crucial for automating instrument detection in surgical procedures without pre-labeled datasets. Furthermore, this technique could be applied in surgical applications such as surgeon skills assessment and robot motion planning, where precise instrument detection is indispensable.

The possibility of a robot failing to perform its task can be influenced by factors related to its movement and the load it carries. This concern is particularly important in mobile robots where these factors are more noticeable. Many researchers have conducted studies to quantify the loss of stability in different types of robots. However, these studies often require expensive and complex equipment for replication. Therefore, this research proposes an alternative approach to estimate tip-over stability in a simulated environment made in MATLAB/Simulink. The methodology involves using a 3-degree-of-freedom serial manipulator placed on an angular positioning table which are imported from CAD files respectively. The stability measure is determined by applying a criterion based on the average normal reactions at the base of the manipulator. Case studies are conducted to simulate operating conditions of both systems in order to assess the potential for tipping over based on the trajectory between two desired points. Estimation of tip-over is demonstrated by the values obtained by the reaction of the stability values of each edge of the system and the normalized stability for each case. Limitation of the process is discussed.

Accurate needle insertion during epidural anesthesia is challenging due to strong dependence on clinician experience and the limited integration of guidance modalities that simultaneously provide visual feedback and physical motion constraints. Current approaches, including ultrasound guidance and augmented reality visualization, mainly offer passive assistance and do not actively regulate insertion trajectory and depth, which may lead to variability in accuracy and increased risk of complications. This work presents a multimodal human–machine assistance system that combines augmented reality guidance with virtual fixtures to support lumbar epidural needle placement. A Tuohy needle is coupled to a haptic device interacting with a patient-specific L3–L4 lumbar phantom fabricated using 3D printing and ballistic gel. A model-based force profile reproduces the mechanical response of anatomical layers during insertion. Three experimental conditions are evaluated: freehand execution, augmented reality guidance with trajectory and depth visualization, and cooperative guidance using virtual fixtures defined by a cylindrical corridor and a depth-limiting plane. Results show a progressive reduction in mean depth error from 6.82 ± 3.46 mm (freehand) to 4.96 ± 2.41 mm (augmented reality) and 2.21 ± 1.73 mm (virtual fixtures). These findings indicate that the integration of visual and haptic guidance significantly enhances insertion precision and control. The proposed approach highlights the potential of multimodal human–machine cooperation for safer training and assisted interventions.

This article presents the model and simulation of the serial robot configurations of the types RRR and RPR, applying the theories of differential kinematics, to obtain the representation of its mathematical model (Jacobian matrix) and its simulation. The differential kinematics in robotics is the relationship between vector spaces, so it is possible to make the velocity map in the joint space in the end effector workspace. We present the differential kinematic model that is obtained from the position kinematics by differentiation techniques and with the help of the asymmetric matrix we obtain the information that is part of the Jacobian matrix, which allows us to know the velocities of the joint variables as a function of linear and angular velocity in the end effector and vice versa. The simulation of the manipulators is carried out validating the mathematical differential model; through the validation of the differential kinematics of serial chains it is possible to apply the procedure to complicated manipulator robots. The method presented here is the basis of a useful tool for solving complex robots, as in the case of redundant, parallel and hybrid serial manipulator robots.