Generative Adversarial Network Based Heuristics for Sampling-Based Path Planning

Sampling-based path planning is a popular methodology for robot path planning.With a uniform sampling strategy to explore the state space,a feasible path can be found without the complex geometric modeling of the configuration space.However,the quality of the initial solution is not guaranteed,and the convergence speed to the optimal solution is slow.In this paper,we present a novel image-based path planning algorithm to overcome these limitations.Specifically,a generative adversarial network(GAN)is designed to take the environment map(denoted as RGB image)as the input without other preprocessing works.The output is also an RGB image where the promising region(where a feasible path probably exists)is segmented.This promising region is utilized as a heuristic to achieve non-uniform sampling for the path planner.We conduct a number of simulation experiments to validate the effectiveness of the proposed method,and the results demonstrate that our method performs much better in terms of the quality of the initial solution and the convergence speed to the optimal solution.Furthermore,apart from the environments similar to the training set,our method also works well on the environments which are very different from the training set.

A Real-time Tracking Method for Magnetism-driven Capsule Robot

In the last decade,significant progress has been made in applying passive capsule endoscopes(CE)to medical diagnostics.However,disadvantages still need to be overcome for better utilization.A major challenge is to actively control the movement of the CE and provide real-time location information.This paper proposes a magnetic tracking method for CE driven by an external magnetic field that is generated by four sets of electromagnetic coils around the CE.The tracking method is based on a magnetic sensor array.The magnetic actuation constitutes three steps.First,the driving current from each coil is obtained according to the control requirement for a certain position and orientation.Second,the magnetic field that is generated by the driving current in the tracking space is estimated according to the magnetic field model.It can also be measured by Hall-effect sensors embedded in the position system.Third,the magnetic field generated by the CE is subtracted from the total magnetic field measured by the sensors,and then the magnetic position algorithm is applied.In the experiments,the positioning error is found to be within5.6 mm and the orientation error is under 8.5°.The proposed localization method would be used for closed-loop control of CE to achieve better and safer performance.

Convolutional Neural Network-based Leakage Detection of Crude Oil Transmission Pipes

Due to the rapid development in the petroleum industry,the leakage detection of crude oil transmission pipes has become an increasingly crucial issue.At present,oil plants at home and abroad mostly use manual inspection method for detection.This traditional method is not only inefficient but also labor-intensive.The present paper proposes a novel convolutional neural network(CNN)architecture for automatic leakage level assessment of crude oil transmission pipes.An experimental setup is developed,where a visible camera and a thermal imaging camera are used to collect image data and analyze various leakage conditions.Specifically,images are collected from various pipes with no leaking and different leaking states.Apart from images from existing pipelines,images are collected from the experimental setup with different types of joints to simulate leakage conditions in the real world.The main contributions of the present paper are,developing a convolutional neural network to classify the information in red-green-blue(RGB)and thermal images,development of the experimental setup,conducting leakage experiments,and analyzing the data using the developed approach.By successfully combining the two types of images,the proposed method is able to achieve a higher classification accuracy,compared to other methods that use RGB images or thermal images alone.Especially,compared with the method that uses thermal images only,the accuracy increases from about 91%to over 96%.

Mobile Robot Path Planningin Dynamic Environments:A Survey

There are many challenges for robot navigation in densely populated dynamic environments.This paper presents a survey of the path planning methods for robot navigation in dense environments.Particularly,the path planning in the navigation framework of mobile robots is composed of global path planning and local path planning,with regard to the planning scope and the executability.Within this framework,the recent progress of the path planning methods is presented in the paper,while examining their strengths and weaknesses.Notably,the recent developed Velocity Obstacle method and its variants that serve as the local planner are analyzed comprehensively.Moreover,as a model-free method that is widely used in current robot applications,the reinforcement learning-based path planning algorithms are detailed in this paper.

Development of a Compact Photoacoustic Tomography Imaging System with Dual Single-Element Transducers for Image Enhancement

Objective:This paper proposes a new photoacoustic computed tomography(PACT)imaging system employing dual ultrasonic transducers with different frequencies.When imaging complex biological tissues,photoacoustic(PA)signals with multiple frequencies are produced simultaneously;however,due to the limited bandwidth of a single-frequency transducer,the received PA signals with specific frequencies may be missing,leading to a low imaging quality.Methods:In contrast to our previous work,the proposed system has a compact volume as well as specific selection of the detection center frequency of the transducer,which can provide a comprehensive range for the detection of PA signals.In this study,a series of numerical simulation and phantom experiments were performed to validate the efficacy of the developed PACT system.Results:The images generated by our system combined the advantages of both high resolution and ideal brightness/contrast.Conclusion:The interchangeability of transducers with different frequencies provides potential for clinical deployment under the circumstance where a single frequency transducer cannot perform well.

Personalizing a Service Robot by Learning Human Habits from Behavioral Footprints

For a domestic personal robot, personalized services are as important as predesigned tasks, because the robot needs to adjust the home state based on the operator's habits. An operator's habits are composed of cues, behaviors, and rewards. This article introduces behavioral footprints to describe the operator's behaviors in a house, and applies the inverse reinforcement learning technique to extract the operator's habits, represented by a reward function. We implemented the proposed approach with a mobile robot on indoor temperature adjustment, and compared this approach with a baseline method that recorded all the cues and behaviors of the operator. The result shows that the proposed approach allows the robot to reveal the operator's habits accurately and adjust the environment state accordingly.

Design and evaluation of a novel biopsy needle with hemostatic function

Biopsy is a method commonly used for early cancer diagnosis.However,bleeding complications of widely available biopsy are risky for patients.Safer biopsy will result in a more accurate cancer diagnosis and a decrease in the risk of complications.In this article,we propose a novel biopsy needle that can reduce bleeding during biopsy procedures and achieve stable hemostasis.The proposed biopsy needle features a compact structure and can be operated easily by left and right hands.A predictive model for puncture force and tip deflection based on coupled Eulerian–Lagrangian(CEL)method is developed.Experimental results show that the biopsy needle can smoothly deliver the gelatin sponge hemostatic plug into the tissue.Although the hemostatic plug bends,the overall delivery process is stable,and the hemostatic plug retains in the tissue without being affected by the withdrawal of the needle.Further experiments indicate that the specimens are well obtained and evenly distributed in the groove of the outer needle without scattering.Our proposed design of biopsy needle possesses strong ability of hemostasis,tissue cutting,and tissue retention.The CEL model accurately predicts the peak of puncture force and produces close estimation of the insertion force at the postpuncture stage and tip position.

Erratum to "A survey of the development of biomimetic intelligence and robotics" [Biomim. Intell. Robotics 1 (2021) 100001]

The publisher regrets that the Declaration of Competing Interest statements was not included in the published version of the article "A survey of the development of biomimetic intelligence and robotics".The appropriate Declaration of Competing Interest statement,provided by the authors,is included below.

A survey of learning-based robot motion planning

A fundamental task in robotics is to plan collision-free motions among a set of obstacles.Recently,learning-based motion-planning methods have shown significant advantages in solving different planning problems in high-dimensional spaces and complex environments.This article serves as a survey of various different learning-based methods that have been applied to robot motion-planning problems,including supervised,unsupervised learning,and reinforcement learning.These learning-based methods either rely on a human-crafted reward function for specific tasks or learn from successful planning experiences.The classical definition and learning-related definition of motion-planning problem are provided in this article.Different learning-based motion-planning algorithms are introduced,and the combination of classical motion-planning and learning techniques is discussed in detail.

A review of bio-inspired needle for percutaneous interventions

Bio-inspired design translates the knowledge of natural or biological structures or behaviors into novel theories and technologies,providing new directions for research and developments.Although the medical needles for percutaneous intervention technology appear to be mature,biomimetic solutions become popular to further facilitate the performance of the medical needles.In this paper,we review the current state of bio-inspired medical needle designs for percutaneous interventions,including a variety of biomimetic mechanisms and insertion strategies.Existing and experimental designs of biomimetic medical needles are classified into five groups with respect to the applications,while their characteristics are identified and discussed.Such classification and discussion will not only provide technical insights into previous studies but also identify undiscovered directions for future research.

EMD-based Adaptive Wavelet Threshold for Pulse Wave Denoising

It is inevitable that noises will be introduced during the acquisition of pulse wave signal, which can result in morphology changes of the original pulse wave,and affect the hemodynamic analysis and diagnosis based on pulse wave signals. In order to remove these noises, an adaptive de-noising method based on empirical mode decomposition(EMD) and wavelet threshold is proposed in this paper. Compared with the wavelet threshold method for denoising pulse wave, the proposed approach is more effective, especially at low signal-to-noise ratio.

Bridging AI to Robotics via Biomimetics

Throughout human history,people have always fascinated about creating machines capable of mimicking human behaviors and actions.Recorded in the ancient Chinese bestiary “Shan Hai Jing(The Classic of Mountains and Seas)”,Huang Di(The Yellow Emperor)built and used navigation mobile robots in the battle against an enemy deity named Chi You some 5000 years ago.Since then,many robots,be they imaginative or actual,have been invented and recorded,such as the wooden flying birds of Lu Ban some 2500 years ago that can fly for three days without landing.People’s imagination,fantasy,and desire to invent,build,and use robots have never stopped.With the quickening pace of technological development in the past few decades,research in robotics and AI has in particular reached a new level of attention and involvement.As an intuitive approach,human beings draw their inspiration from the nature and biological systems when inventing,designing,and developing machines and algorithms in the effort to recreate and duplicate their functionalities.