Flexible needle insertion with bevel tips is becoming a preferred method for approaching targets in the human body in the least invasive manner. However, to successfully implement needle insertion, surgeons require pr...
详细信息
ISBN:
(纸本)9781728145693
Flexible needle insertion with bevel tips is becoming a preferred method for approaching targets in the human body in the least invasive manner. However, to successfully implement needle insertion, surgeons require prolonged training processes and long-term experience to develop essential handling skills. 'this paper presents a new path planning approach with Deep Reinforcement Learning (DRL) to implement automatic needle insertion using a surgical robot. In this paper, Deep Q-Network (DQN) algorithm is utilized to learn the control policy for flexible needle steering with needle-tissue interaction. As the human body is composed of a complex environment such as tissues, blood vessels, bones, and muscles, the uncertainty of the needle-tissue interaction should be considered during insertion. To model this complex interaction in path planning, utilizing a neural network to approximate the action-value function is more efficient than using traditional array methods in terms of time and accuracy. In our simulation, the agent (needle) can he controlled with 2 degrees of freedom (bevel direction rotation and insertion) and received negative rewards when it collides with obstacles, goes out of range, or exceeds a predefined number of rotations. During the training, the agent demonstrates the accuracy and efficiency of the learned policy through feedback scores in every episode. In addition, this system incorporates the uncertainty within flexible needle-tissue interaction using a stochastic environment. Compared with other traditional methods for flexible needle path planning, we demonstrated that motion planning of bevel-tip flexible needles in complex human bodies using DRL has better efficiency and accuracy.
The paper presents an analysis of dynamic singularities in n-link pendulum-like models that are controlled using input-output feedback linearisation. The dynamic singularities are caused by the decoupling matrix being...
详细信息
The paper presents an analysis of dynamic singularities in n-link pendulum-like models that are controlled using input-output feedback linearisation. The dynamic singularities are caused by the decoupling matrix being singular for particular configurations. The examples include 3-link planar pendulum, 3-link 3D pendulum and a simplified humanoid-like robot model. Partial stabilisation results are presented for specific physical parameters.
A visual localization method utilizing a fisheye monocular camera is proposed to enhance navigation accuracy of autonomous mobile robots in indoor environments for warehouse or service robotics applications. Existing ...
详细信息
ISBN:
(数字)9781665490429
ISBN:
(纸本)9781665490429
A visual localization method utilizing a fisheye monocular camera is proposed to enhance navigation accuracy of autonomous mobile robots in indoor environments for warehouse or service robotics applications. Existing visual infrastructure-aided localization algorithms take advantage of uniquely colored or lit robots that limit their application to ideal lighting conditions, occlusion-free scenarios or multi-modal fusion with stereo vision, LiDAR, and inertial sensors which inevitably increases their complexity. Using fisheye monocular vision imposes challenges such as depth estimation, frame warping, and low accuracy of the state estimation for far objects. The proposed augmented localization framework includes an uncertainty-aware state observer employing a motion model with a learning-based input estimator and point cloud clusters over a region of interest, to estimate the position of a robot while maintaining effective computational efficiency. Observability of the developed state estimator and asymptotic stability of the estimation error dynamics are also studied. Various tests including occlusion, low visibility for far objects, and noisy depth estimation (from the clustered region of interest), have been conducted in indoor settings to validate the method. The tests confirm robust performance of the augmented visual localization framework in presence of intermittent measurements due to environmental conditions or low reliability of vision-based depth estimation. Furthermore, a significant increase in accuracy and consistency of visual localization is shown without using additional stereo, inertial, or LiDAR measurements.
Recently, the product matching and retrieval methods based on users' real needs are becoming a hot spot in academic research, especially in the era of big data, more efficient and accurate matching methods become ...
详细信息
A model of a combination of antiangiogenic treatment and chemotherapy is proposed and analyzed. The model is a modified Hahnfeldt model and the analysis has two goals: first of all we check stability of the equilibriu...
详细信息
A model of a combination of antiangiogenic treatment and chemotherapy is proposed and analyzed. The model is a modified Hahnfeldt model and the analysis has two goals: first of all we check stability of the equilibrium point of the model to find conditions leading to tumour eradication for constant dosing and periodic treatment then we propose an optimization problem and give necessary conditions of its solution. We discuss modifications of the model which enable more realistic description of treatment effects.
In this paper a method is introduced that combines Inertial Measurement Unit (IMU) readouts with low accuracy and temporarily unavailable velocity measurements (e.g., based on kinematics or GPS) to produce high accura...
详细信息
ISBN:
(纸本)9781479987023
In this paper a method is introduced that combines Inertial Measurement Unit (IMU) readouts with low accuracy and temporarily unavailable velocity measurements (e.g., based on kinematics or GPS) to produce high accuracy estimates of velocity and orientation with respect to gravity. The method is computationally cheap enough to be readily implementable in sensors. The main area of application of the introduced method is mobile robotics.
Many problems in computer vision such as pose recovery and structure estimation are formulated as a minimization process. These problems vary in the use of image measurements directly or using them to extract 3D cues ...
详细信息
In this paper, road roughness model for the right and the left tracks are constructed by utilizing two methods. In the first method, from time-domain measurements the empirical auto and cross-power spectral densities ...
详细信息
ISBN:
(纸本)9788993215120
In this paper, road roughness model for the right and the left tracks are constructed by utilizing two methods. In the first method, from time-domain measurements the empirical auto and cross-power spectral densities of the left and the right tracks are estimated by using the Welch method. Next, the road roughness is decomposed into three stochastically independent random processes and the linear-shape filter parameters of the right and the left tracks are estimated via a recently developed subspace-based identification algorithm. In the second method, a multi-input/multi-output subspacebased identification algorithm is directly used, without employing spectral decomposition to derive the spatial-domain models of the right and the left tracks from the Welch power spectral density estimates. Profile measurements for a specific road section from the Long Term Pavement Performance archive of the University of Michigan Transportation Research Institute is used to demonstrate the successfull application of the subspace approach.
In this research, the combination of hyperspectral technology and chemometrics was applied for non-destructive testing of the internal quality of Hami melon. Sugar content and firmness serve as crucial indicators in a...
详细信息
In this paper, we present a numerical method to solve fractional ordinary differential equation (FDE) with Caputo derivative of order in the range (0,1]. The proposed scheme is a variant of Adams - Bashforth - Moulton...
详细信息
ISBN:
(纸本)9781479987023
In this paper, we present a numerical method to solve fractional ordinary differential equation (FDE) with Caputo derivative of order in the range (0,1]. The proposed scheme is a variant of Adams - Bashforth - Moulton method. In the final part, examples of numerical results are discussed.
暂无评论