Search

Abstract Background Machine learning and robotics technologies are increasingly being used in the healthcare domain to improve the quality and efficiency of surgeries and to address challenges such as staff shortages. Robotic scrub nurses in particular offer great potential to address staff shortages by assuming nursing tasks such as the handover of surgical instruments. Methods We introduce a robotic scrub nurse system designed to enhance the quality of surgeries and efficiency of surgical workflows by predicting and delivering the required surgical instruments based on real-time laparoscopic video analysis. We propose a three-stage deep learning architecture consisting of a single frame-, temporal multi frame-, and informed model to anticipate surgical instruments. The anticipation model was trained on a total of 62 laparoscopic cholecystectomies. Results Here, we show that our prediction system can accurately anticipate 71.54% of the surgical instruments required during laparoscopic cholecystectomies in advance, facilitating a smoother surgical workflow and reducing the need for verbal communication. As the instruments in the left working trocar are changed less frequently and according to a standardized procedure, the prediction system works particularly well for this trocar. Conclusions The robotic scrub nurse thus acts as a mind reader and helps to mitigate staff shortages by taking over a great share of the workload during surgeries while additionally enabling an enhanced process standardization.

Multi-goal reinforcement learning (RL) with sparse rewards poses a significant challenge for RL methods. Hindsight experience replay (HER) addresses this challenge by learning from failures and replacing the desired goals with achieved states. However, HER often becomes inefficient when the desired goals are far away from the initial states. This paper introduces co-adapting hindsight experience replay with environment shifts (in short, COHER). COHER generates progressively more complex tasks as soon as the agent’s success surpasses a predefined threshold. The generated tasks and agent are coupled to optimize the behavior of the agent within each task-agent pair. We evaluate COHER on various sparse reward robotic tasks that require obstacle avoidance capabilities and compare COHER with hindsight goal generation (HGG), curriculum-guided hindsight experience replay (CHER), and vanilla HER. The results show that COHER consistently outperforms the other methods and that the obtained policies can avoid obstacles without having explicit information about their position. Lastly, we deploy such policies to a real Franka robot for Sim2Real analysis. We observe that the robot can achieve the task by avoiding obstacles, whereas policies obtained with other methods cannot. The videos and code are publicly available at: https://erdiphd.github.io/COHER/.

IntroductionRecent work on bats flying over long distances has revealed that single hippocampal cells have multiple place fields of different sizes. At the network level, a multi-scale, multi-field place cell code outperforms classical single-scale, single-field place codes, yet the performance boundaries of such a code remain an open question. In particular, it is unknown how general multi-field codes compare to a highly regular grid code, in which cells form distinct modules with different scales.MethodsIn this work, we address the coding properties of theoretical spatial coding models with rigorous analyses of comprehensive simulations. Starting from a multi-scale, multi-field network, we performed evolutionary optimization. The resulting multi-field networks sometimes retained the multi-scale property at the single-cell level but most often converged to a single scale, with all place fields in a given cell having the same size. We compared the results against a single-scale single-field code and a one-dimensional grid code, focusing on two main characteristics: the performance of the code itself and the dynamics of the network generating it.ResultsOur simulation experiments revealed that, under normal conditions, a regular grid code outperforms all other codes with respect to decoding accuracy, achieving a given precision with fewer neurons and fields. In contrast, multi-field codes are more robust against noise and lesions, such as random drop-out of neurons, given that the significantly higher number of fields provides redundancy. Contrary to our expectations, the network dynamics of all models, from the original multi-scale models before optimization to the multi-field models that resulted from optimization, did not maintain activity bumps at their original locations when a position-specific external input was removed.DiscussionOptimized multi-field codes appear to strike a compromise between a place code and a grid code that reflects a trade-off between accurate positional encoding and robustness. Surprisingly, the recurrent neural network models we implemented and optimized for either multi- or single-scale, multi-field codes did not intrinsically produce a persistent “memory” of attractor states. These models, therefore, were not continuous attractor networks.

The medial entorhinal cortex of rodents is known to contain grid cells that exhibit precise periodic firing patterns based on the animal’s position, resulting in a distinct hexagonal pattern in space. These cells have been extensively studied due to their potential to unveil the navigational computations that occur within the mammalian brain and interesting phenomena such as so-called grid cell distortions have been observed. Previous neuronal models of grid cells assumed their firing fields were independent of environmental boundaries. However, more recent research has revealed that the grid pattern is, in fact, dependent on the environment’s boundaries. When rodents are placed in nonsquare cages, the hexagonal pattern tends to become disrupted and adopts different shapes. We believe that these grid cell distortions can provide insights into the underlying neural circuitry involved in grid cell firing. To this end, a calibration circuit for grid cells is proposed. Our simulations demonstrate that this circuit is capable of reproducing grid distortions observed in several previous studies. Our model also reproduces distortions in place cells and incorporates experimentally observed distortions of speed cells, which present further opportunities for exploration. It generates several experimentally testable predictions, including an alternative behavioral description of boundary vector cells that predicts behaviors in nonsquare environments different from the current model of boundary vector cells. In summary, our study proposes a calibration circuit that reproduces observed grid distortions and generates experimentally testable predictions, aiming to provide insights into the neural mechanisms governing spatial computations in mammals.

Manipulating cells at a small scale is widely acknowledged as a complex and challenging task, especially when it comes to cell grasping and transportation. Various precise methods have been developed to remotely control the movement of microrobots. However, the manipulation of micro-objects necessitates the use of end-effectors. This paper presents a study on the control of movement and grasping operations of a magnetic microrobot, utilizing only 3 pairs of electromagnetic coils. A specially designed microgripper is employed on the microrobot for efficient cell grasping and transportation. To ensure precise grasping, a bending deformation model of the microgripper is formulated and subsequently validated. To achieve precise and reliable transportation of cells to specific positions, an approach that combines an extended Kalman filter with a model predictive control method is adopted to accomplish the trajectory tracking task. Through experiments, we observe that by applying the proposed control strategy, the mean absolute error of path tracking is found to be less than 0.155 mm. Remarkably, this value accounts for only 1.55% of the microrobot’s size, demonstrating the efficacy and accuracy of our control strategy. Furthermore, an experiment involving the grasping and transportation of a zebrafish embryonic cell (diameter: 800 μm) is successfully conducted. The results of this experiment not only validate the precision and effectiveness of the proposed microrobot and its associated models but also highlight its tremendous potential for cell manipulation in vitro and in vivo.

Through vehicle-to-vehicle (V2V) communication, autonomizing a vehicle platoon can significantly reduce the distance between vehicles, thereby reducing air resistance and improving road traffic efficiency. The gradual maturation of platoon control technology is enabling vehicle platoons to achieve basic driving functions, thereby permitting large-scale vehicle platoon scheduling and planning, which is essential for industrialized platoon applications and generates significant economic benefits. Scheduling and planning are required in many aspects of vehicle platoon operation; here, we outline the advantages and challenges of a number of the most important applications, including platoon formation scheduling, lane-change planning, passing traffic light scheduling, and vehicle resource allocation. This paper’s primary objective is to integrate current independent platoon scheduling and planning techniques into an integrated architecture to meet the demands of large-scale platoon applications. To this end, we first summarize the general techniques of vehicle platoon scheduling and planning, then list the primary scenarios for scheduling and planning technique application, and finally discuss current challenges and future development trends in platoon scheduling and planning. We hope that this paper can encourage related platoon researchers to conduct more systematic research and integrate multiple platoon scheduling and planning technologies and applications.

Deployment of Reinforcement Learning (RL) algorithms for robotics applications in the real world requires ensuring the safety of the robot and its environment. Safe Robot RL (SRRL) is a crucial step toward achieving human-robot coexistence. In this paper, we envision a human-centered SRRL framework consisting of three stages: safe exploration, safety value alignment, and safe collaboration. We examine the research gaps in these areas and propose to leverage interactive behaviors for SRRL. Interactive behaviors enable bi-directional information transfer between humans and robots, such as conversational robot ChatGPT. We argue that interactive behaviors need further attention from the SRRL community. We discuss four open challenges related to the robustness, efficiency, transparency, and adaptability of SRRL with interactive behaviors.

Safe and human‐like trajectory planning is crucial for self‐driving cars. While model‐based planning has demonstrated reliability, it is beneficial to incorporate human demonstrations and align the results with human behaviors. This work aims at bridging the gap between model‐based planning and driver imitation by proposing a constraint imitative trajectory planning method (CITP). CITP integrates artificial potential field and dynamic movement primitives, which have achieved both the ability to imitate human demonstrations as well as ensure safety constraints. During the planning process, CITP first encodes human demonstrations, local driving target, and traffic obstacles as attractive or repulsive effects, and then the trajectory planning problem is solved through model predictive optimization. To address the dynamics of traffic scenarios, a hierarchical planning strategy is proposed based on the division of planning process. CITP is designed with five modules, including LSTM‐based target generation, encoding attractive and repulsive effects with target, demonstrations and obstacles, and trajectory planning with model predictive optimization. Data collection and experiments are carried out based on CARLA driving simulator, and the effectiveness in terms of both safety and consistency with human behavior are reported.

Abstract The mechanical properties of cells play an important role in cell development and function. Therefore, measurement of cell mechanical properties is a fundamental and essential tool for cell research. In this article, a novel method to estimate the force exerted on a living cell is proposed based on glass needle deformation, which does not require additional physical sensors compared with other force‐sensing methods. The three‐dimensional (3D) spatial state of the needle is reconstructed, and the parameters of needle deflection are obtained based on a multi‐focus image fusion algorithm. The average reconstruction error of this algorithm is 0.94 µm. Based on the deformation of the needle, a mechanical model of needle deformation is established, and the model is calibrated using a constructed calibration system. At the range of 0–200 µN, the highest resolution is 0.002 µN and the lowest resolution is 5.3 µN. The proposed method can be used to estimate the force exerted by a needle on the surface of a living cell.

Deep reinforcement learning (DRL) combines reinforcement learning algorithms with deep neural networks (DNNs). Spiking neural networks (SNNs) have been shown to be a biologically plausible and energy efficient alternative to DNNs. Since the introduction of surrogate gradient approaches that allowed to overcome the discontinuity in the spike function, SNNs can now be trained with the backpropagation through time (BPTT) algorithm. While largely explored on supervised learning problems, little work has been done on investigating the use of SNNs as function approximators in DRL. Here we show how SNNs can be applied to different DRL algorithms like Deep Q-Network (DQN) and Twin-Delayed Deep Deteministic Policy Gradient (TD3) for discrete and continuous action space environments, respectively. We found that SNNs are sensitive to the additional hyperparameters introduced by spiking neuron models like current and voltage decay factors, firing thresholds, and that extensive hyperparameter tuning is inevitable. However, we show that increasing the simulation time of SNNs, as well as applying a two-neuron encoding to the input observations helps reduce the sensitivity to the membrane parameters. Furthermore, we show that randomizing the membrane parameters, instead of selecting uniform values for all neurons, has stabilizing effects on the training. We conclude that SNNs can be utilized for learning complex continuous control problems with state-of-the-art DRL algorithms. While the training complexity increases, the resulting SNNs can be directly executed on neuromorphic processors and potentially benefit from their high energy efficiency.

Although we can measure muscle activity and analyze their activation patterns, we understand little about how individual muscles affect the joint torque generated. It is known that they are controlled by circuits in the spinal cord, a system much less well-understood than the cortex. Knowing the contribution of the muscles toward a joint torque would improve our understanding of human limb control. We present a novel framework to examine the control of biomechanics using physics simulations informed by electromyography (EMG) data. These signals drive a virtual musculoskeletal model in the Neurorobotics Platform (NRP), which we then use to evaluate resulting joint torques. We use our framework to analyze raw EMG data collected during an isometric knee extension study to identify synergies that drive a musculoskeletal lower limb model. The resulting knee torques are used as a reference for genetic algorithms (GA) to generate new simulated activation patterns. On the platform the GA finds solutions that generate torques matching those observed. Possible solutions include synergies that are similar to those extracted from the human study. In addition, the GA finds activation patterns that are different from the biological ones while still producing the same knee torque. The NRP forms a highly modular integrated simulation platform allowing these in silico experiments. We argue that our framework allows for research of the neurobiomechanical control of muscles during tasks, which would otherwise not be possible.

The more we investigate the principles of motion learning in biological systems, the more we reveal the central role that body morphology plays in motion execution. Not only does anatomy define the kinematics and therefore the complexity of possible movements, but it now becomes clear that part of the computation required for motion control is offloaded to body dynamics (a phenomenon referred to as “Morphological Computation.”) Consequentially, a proper design of body morphology is essential to carry out meaningful simulations on motor control of robotic and musculoskeletal systems. The design should not be fixed for simulation experiments beforehand, but is a central research aspect in every motion learning experiment that requires continuous adaptation during the experimental phase. We herein introduce a plugin for the 3D modeling suite Blender that enables researchers to design morphologies for simulation experiments in, particularly but not restricted to, the Neurorobotics Platform. We include design capabilities for both musculoskeletal bodies, as well as robotic systems in the Robot Designer. Thereby, we hope to not only foster understanding of biological motions and enabling better robot designs, but enabling true Neurorobotic experiments that may consist of biomimetic models such as tendon-driven robot as a mix of both or a transition between both biology and technology. This plugin helps researchers design and parameterize models with a Graphical User Interface and thus simplifies and speeds up the overall design process.

Summary: The spinal cord is engaged in all forms of motor performance but its functions are far from understood. Because network connectivity defines function, we explored the connectivity of muscular, tendon, and tactile sensory inputs among a wide population of spinal interneurons in the lower cervical segments. Using low noise intracellular whole cell recordings in the decerebrated, non-anesthetized cat in vivo, we could define mono-, di-, and trisynaptic inputs as well as the weights of each input. Whereas each neuron had a highly specific input, and each indirect input could moreover be explained by inputs in other recorded neurons, we unexpectedly also found the input connectivity of the spinal interneuron population to form a continuum. Our data hence contrasts with the currently widespread notion of distinct classes of interneurons. We argue that this suggested diversified physiological connectivity, which likely requires a major component of circuitry learning, implies a more flexible functionality.

Frequency-modulated continuous wave radar sensors play an essential role for assisted and autonomous driving as they are robust under all weather and light conditions. However, the rising number of transmitters and receivers for obtaining a higher angular resolution increases the cost for digital signal processing. One promising approach for energy-efficient signal processing is the usage of brain-inspired spiking neural networks (SNNs) implemented on neuromorphic hardware. In this article we perform a step-by-step analysis of automotive radar processing and argue how spiking neural networks could replace or complement the conventional processing. We provide SNN examples for two processing steps and evaluate their accuracy and computational efficiency. For radar target detection, an SNN with temporal coding is competitive to the conventional approach at a low compute overhead. Instead, our SNN for target classification achieves an accuracy close to a reference artificial neural network while requiring 200 times less operations. Finally, we discuss the specific requirements and challenges for SNN-based radar processing on neuromorphic hardware. This study proves the general applicability of SNNs for automotive radar processing and sustains the prospect of energy-efficient realizations in automated vehicles.

Typical industrial workcells are composed of a plenitude of devices from various manufacturers, which rely on their own specific control interfaces. To reduce setup and reconfiguration times, a hardware-agnostic Plug & Produce system is required. In this paper, we present a system architecture that uses generic and semantically augmented OPC UA skills for robots, tools, and other system components. Standardized skill interfaces and parameters facilitate flexible component interchange and automatic parametrization with a focus on reusability of skills across different platforms and domains. The hierarchical composition of such skills allows for additional abstraction through the grouping of functionalities. Through the extension of OPC UA discovery services, available skills are dynamically detected whenever a manufacturing system's component is updated. The introduced Plug & Produce system is evaluated in multiple industrial workcells composed of robots, tool changer, electric parallel gripper, and vacuum gripper-all controlled via the proposed OPC UA skill interface. The evaluation of our system architecture demonstrates the applicability of the Plug & Produce concept in the domain of robot-based industrial assembly. Although it is necessary to adapt existing hardware to comply with the semantic skill concept, the initial one-time effort yields reoccurring efficiency gains during system reconfiguration. In particular, small lot production benefits from reduced changeover times.

Single-frame 3D detection is a well-studied vision problem with dedicated benchmarks and a large body of work. This knowledge has translated to a myriad of real-world applications. However, frame-by-frame detection suffers from inconsistencies between independent frames, such as flickering bounding box shape and occasional misdetections. Safety-critical applications may not tolerate these inconsistencies. For example, automated driving systems require robust and temporally consistent detection output for planning. A vehicle’s 3D bounding box shape should not change dramatically across independent frames. Against this backdrop, we propose a multi-frame RGB-Lidar feature alignment strategy to refine and increase the temporal consistency of 3D detection outputs. Our main contribution is aligning and aggregating object-level features using multiple past frames to improve 3D detection quality in the inference frame. First, a Frustum PointNet architecture extracts a frustum-cropped point cloud using RGB and lidar data for each object frame-by-frame. After tracking, multi-frame frustum features of unique objects are fused through a Gated Recurrent Unit (GRU) to obtain a refined 3D box shape and orientation. The proposed method improves 3D detection performance on the KITTI tracking dataset by more than 4% for all classes compared to the vanilla Frustum PointNet baseline. We also conducted extensive ablation studies to show the efficacy of our hyperparameter selections. Codes are available at https://github.com/emecercelik/Multi-frame-3D-detection.git.

This paper introduces the a framework that simplifies the process of designing and describing autonomous vehicle platooning manoeuvres which implements four design principles: Standardisation, Encapsulation, Abstraction, and Decoupling (SEAD). Although a large body of research has been formulating platooning manoeuvres, it is still challenging to design, describe, read, and understand them. This difficulty largely arises from missing formalisation. To fill this gap, we analysed existing ways of describing manoeuvres, derived the causes of difficulty, and designed a framework that simplifies the manoeuvre design process. Alongside, a Manoeuvre Design Language was developed to structurally describe manoeuvres in a machine-readable format. Unlike state-of-the-art manoeuvre descriptions that require one state machine for every participating vehicle, the SEAD framework allows describing any manoeuvre from the single perspective of the platoon leader. We hope that the SEAD framework will pave the way for further research in the area of new manoeuvre design and optimisation by largely simplifying and unifying platooning manoeuvre representation.

Processing sensor data with spiking neural networks on digital neuromorphic chips requires converting continuous analog signals into spike pulses. Two strategies are promising for achieving low energy consumption and fast processing speeds in end-to-end neuromorphic applications. First, to directly encode analog signals to spikes to bypass the need for an analog-to-digital converter. Second, to use temporal encoding techniques to maximize the spike sparsity, which is a crucial parameter for fast and efficient neuromorphic processing. In this work, we propose an adaptive control of the refractory period of the leaky integrate-and-fire (LIF) neuron model for encoding continuous analog signals into a train of time-coded spikes. The LIF-based encoder generates phase-encoded spikes that are compatible with digital hardware. We implemented the neuron model on a physical circuit and tested it with different electric signals. A digital neuromorphic chip processed the generated spike trains and computed the signal’s frequency spectrum using a spiking version of the Fourier transform. We tested the prototype circuit on electric signals up to 1 kHz. Thus, we provide an end-to-end neuromorphic application that generates the frequency spectrum of an electric signal without the need for an ADC or a digital signal processing algorithm.

Planar motion constraint occurs in visual odometry (VO) and SLAM for Automated Guided Vehicles (AGVs) or mobile robots in general. Conventionally, two-point solvers can be nested to RANdom SAmple Consensus to reject outliers in real data, but the performance descends when the ratio of outliers goes high. This study proposes a globally-optimal Branch-and-Bound (BnB) solver for relative pose estimation under general planar motion, which aims to figure out the globally-optimal solution even under a quite noisy environment. Through reasonable modification of the motion equation, we decouple the relative pose into relative rotation and translation so that a simplified bounding strategy can be applied. It enhances the efficiency of the BnB technique. Experimental results support the global optimality and demonstrate that the proposed method performs more robustly than existing approaches. In addition, the proposed algorithm outperforms state-of-art methods in global optimality under the varying level of outliers.

An important aspect of the perception system for intelligent vehicles is the detection and signal measurement of vehicle taillights. In this work, we present a novel vision-based measurement (VBM) system, using an event-based neuromorphic vision sensor, which is able to detect and measure the vehicle taillight signal robustly. To the best of our knowledge, it is for the first time the neuromorphic vision sensor is paid attention to for utilizing in the field of vehicle taillight signal measurement. The event-based neuromorphic vision sensor is a bioinspired sensor that records pixel-level intensity changes, called events, as well as the whole picture of the scene. The events naturally respond to illumination changes (such as the ON and OFF state of taillights) in the scene with very low latency. Moreover, the property of a higher dynamic range increases the sensor sensitivity and performance in poor lighting conditions. In this paper, we consider an event-driven solution to measure vehicle taillight signals. In contrast to most existing work that relies purely on standard frame-based cameras for the taillight signal measurement, the presented mixed event/frame system extracts the frequency domain features from the spatial and temporal signal of each taillight region and measures the taillight signal by combining the active-pixel sensor (APS) frames and dynamic vision sensor (DVS) events. A thresholding algorithm and a learned classifier are proposed to jointly achieve the brake-light and turn-light signal measurement. Experiments with real traffic scenes demonstrate the performance of measuring taillight signals under different traffic conditions with a single event-based neuromorphic vision sensor. The results show the high potential of the event-based neuromorphic vision sensor being used for optical signal measurement applications, especially in dynamic environments.

This paper proposes a novel framework for addressing the challenge of autonomous overtaking and obstacle avoidance, which incorporates the overtaking path planning into Gaussian Process-based model predictive control (GPMPC). Compared with conventional control strategies, this approach has two main advantages. Firstly, combining Gaussian Process (GP) regression with a nominal model allows for learning from model mismatch and unmodeled dynamics, which enhances a simple model and delivers significantly better results. Due to the approximation for propagating uncertainties, we can furthermore satisfy the constraints and thereby the safety of the vehicle is ensured. Secondly, we convert the geometric relationship between the ego vehicle and other obstacle vehicles into the constraints. Without relying on a higher-level path planner, this approach substantially reduces the computational burden. In addition, we transform the state constraints under the model predictive control (MPC) framework into a soft constraint and incorporate it as relaxed barrier function into the cost function, which makes the optimizer more efficient. Simulation results indicate that the proposed method can not only fulfill the overtaking tasks but also maintain safety at all times.

Rule-based traditional motion planning methods usually perform well with prior knowledge of the macro-scale environments but encounter challenges in unknown and uncertain environments. Deep reinforcement learning (DRL) is a solution that can effectively deal with micro-scale unknown and uncertain environments. Nevertheless, DRL is unstable and lacks interpretability. Therefore, it raises a new challenge: how to combine the effectiveness and overcome the drawbacks of the two methods while guaranteeing stability in uncertain environments. In this study, a multi-constraint and multi-scale motion planning method is proposed for automated driving with the use of constrained reinforcement learning (RL), named RLTT, and comprising RL, a topological reachability analysis used for vehicle path space (TPS), and a trajectory lane model (TLM). First, a dynamic model of vehicles is formulated; then, TLM is developed on the basis of the dynamic model, thus constraining RL action and state space. Second, macro-scale path planning is achieved through TPS, and in the micro-scale range, discrete routing points are achieved via RLTT. Third, the proposed motion planning method is designed by combining sophisticated rules, and a theoretical analysis is provided to guarantee the efficiency of our method. Finally, related experiments are conducted to evaluate the effectiveness of the proposed method; our method can reduce 19.9% of the distance cost in the experiments as compared to the traditional method. Experimental results indicate that the proposed method can help mitigate the gap between data-driven and traditional methods, provide better performance for automated driving, and facilitate the use of RL methods in more fields.

The development of advanced autonomous driving applications is hindered by the complex temporal structure of sensory data, as well as by the limited computational and energy resources of their on-board systems. Currently, neuromorphic engineering is a rapidly growing field that aims to design information processing systems similar to the human brain by leveraging novel algorithms based on spiking neural networks (SNNs). These systems are well-suited to recognize temporal patterns in data while maintaining a low energy consumption and offering highly parallel architectures for fast computation. However, the lack of effective algorithms for SNNs impedes their wide usage in mobile robot applications. This paper addresses the problem of radar signal processing by introducing a novel SNN that substitutes the discrete Fourier transform and constant false-alarm rate algorithm for raw radar data, where the weights and architecture of the SNN are derived from the original algorithms. We demonstrate that our proposed SNN can achieve competitive results compared to that of the original algorithms in simulated driving scenarios while retaining its spike-based nature.

Vitreoretinal (VR) surgery is typical microsurgery with delicate and complex surgical procedures. The vision-based navigation for robot-assisted VR surgery has not been fully exploited because of the challenges that arise from illumination, high precision, and safety assessments. This paper presents a novel method to estimate the 6DOF needle pose specifically for the application of robotic intraocular needle navigation using optical coherence tomography (OCT) volumes. The key ingredients of the proposed method are (1) 3D needle point cloud segmentation in OCT volume and (2) needle point cloud 6DOF pose estimation using a modified iterative closest point (ICP) algorithm. To address the former, a voting mechanism with geometric features of the needle is utilized to robustly segment the needle in OCT volume. Afterward, the CAD model of the needle point cloud is matched with the segmented needle point cloud to estimate the 6DOF needle pose with a proposed shift-rotate ICP (SR-ICP). This method is evaluated by the existing ophthalmic robot on ex-vivo pig eyes. The quantitative and qualitative results are evaluated and presented for the proposed method.

The target-oriented spraying is an effective way to minimize chemical input in agricultural production and it is important to actualizing sustainable agriculture. This article focused on the design and optimization of the target spray platform. The spray platform consists of three parts: the vision system, the spray system, and the moving platform. All components were effectively connected and preliminarily evaluated especially regarding the response time and target spray accuracy. A simulation system was built considering the real crop geometric shape and nozzle spray pattern using the Monte Carlo method. The spray simulator was used to optimize the spray height objective function of spray deposition rate and coefficient of variance for the spray deposition. The spray process can be easily visualized and compared for different spray parameters. The indoor experiment setup was built to test and optimize the parameters of the overall system, which is flexible to verify the system. Afterward, the outdoor tractor-based equipment was designed to test the system for the field environment. The experimental result showed that 80% of the crop had a spray deviation from 0 mm to 28 mm and the proposed spraying system can reduce 46.8% usage of the chemical compared to the uniform spray method.

In this paper, we design a robust model predictive control (MPC) controller for vehicle subjected to bounded model uncertainties, norm-bounded external disturbances and bounded time-varying delay. A Lyapunov-Razumikhin function (LRF) is adopted to ensure that the vehicle system state enters in a robust positively invariant (RPI) set under the control law. A quadratic cost function is selected as the stage cost function, which yields the upper bound of the infinite horizon cost function. A Lyapunov-Krasovskii function (LKF) candidate related to time-varying delay is designed to obtain the upper bound of the infinite horizon cost function and minimize it at each step by using matrix inequalities technology. Then the robust MPC state feedback control law is obtained at each step. Simulation results show that the proposed vehicle dynamic controller can steer vehicle states into a very small region near the reference tracking signal even in the presence of external disturbances, model uncertainties and time-varying delay. The source code can be downloaded on https://github.com/wenjunliu999.

In this work, we experimentally measured the absolute mass sensitivity of quartz crystal microbalance (QCM) resonators with one ring electrode on the sensing side and compared it to standard QCM resonators with disc electrodes on both sides using electrodeposition. This method allows to compare the absolute mass sensitivity of a ring electrode QCM and standard QCM resonators. The results showed that the average absolute mass sensitivity of a QCM resonator with a ring electrode on one side and a disc electrode on the other side is larger than the one of standard resonators with disc electrodes on both sides. If the ring electrode is facing the electrolyte, the absolute mass sensitivity is 10.28% higher, and for the disc electrode side it is still 5.33% higher. This shows that the ring electrode geometry improves the absolute mass sensitivity in comparison to a standard electrode structure, and therefore reveals a path to improve QCM detection sensitivity in electrochemical research.

Visual-guided locomotion for snake-like robots is a challenging task, since it involves not only the complex body undulation with many joints, but also a joint pipeline that connects the vision and the locomotion. Meanwhile, it is usually difficult to jointly coordinate these two separate sub-tasks as this requires time-consuming and trial-and-error tuning. In this paper, we introduce a novel approach for solving target tracking tasks for a snake-like robot as a whole using a model-free reinforcement learning (RL) algorithm. This RL-based controller directly maps the visual observations to the joint positions of the snake-like robot in an end-to-end fashion instead of dividing the process into a series of sub-tasks. With a novel customized reward function, our RL controller is trained in a dynamically changing track scenario. The controller is evaluated in four different tracking scenarios and the results show excellent adaptive locomotion ability to the unpredictable behavior of the target. Meanwhile, the results also prove that the RL-based controller outperforms the traditional model-based controller in terms of tracking accuracy.

Aiming at the problem that unmanned surface vehicle (USV) motion planning is disturbed by effects of wind and current, a USV motion planning method based on regularization-trajectory cells is proposed. First, a USV motion mathematical model is established while considering the influence of wind and current, and the motion trajectory is analyzed. Second, a regularization-trajectory cell library under the influence of wind and current is constructed, and the influence of wind and current on the weight of the search cost is analyzed. Finally, derived from the regularization-trajectory cell and the search algorithm, a motion planning method for a USV that considers wind and current effects is provided. The experimental results indicate that the motion planning is closer to the actual trajectory of a USV in complex environments and that our method is highly practicable.

A practical method for calculating the mass sensitivity of quartz crystal microbalance (QCM) resonators with ring-shaped Au electrodes on one side based on electrodeposition is presented in this communication. While for standard QCMs, an average mass sensitivity can be calculated despite its approximately Gaussian distribution, the mass sensitivity of QCMs with an asymmetrical electrode structure is difficult to calculate. However, non-standard electrode geometries might be beneficial for sensor applications especially in the area of electrochemistry. By measuring the resonance frequency change of a quartz crystal during deposition and applying Faraday’s law, we determined the mass sensitivity of QCM resonators with a ring electrode. We also studied the influence of the gold electrode thicknesses on the mass sensitivity of the ring-shaped and disc shaped electrodes. The experimental results showed that the mass sensitivity of the ring-shaped electrodes was 5%∼20% higher than those of the disc shaped electrodes. This method is practical and convenient for determining the mass sensitivity of the QCM with ring electrode, and it can be extended to measure QCMs with symmetrical and asymmetrical electrode structures. Such resonators with modified electrode structures may be of interest for studying electrochemical processes where a higher mass sensitivity is desirable.

Due to the complex visual environment and incomplete display of parking slots on around-view images, vision-based parking slot detection is a major challenge. Previous studies in this field mostly use the existing models to solve the problem, the steps of which are cumbersome. In this paper, we propose a parking slot detection method that uses directional entrance line regression and classification based on a deep convolutional neural network (DCNN) to make it robust and simple. For parking slots with different shapes and observed from different angles, we represent the parking slot as a directional entrance line. Subsequently, we design a DCNN detector to simultaneously obtain the type, position, length, and direction of the entrance line. After that, the complete parking slot can be easily inferred using the detection results and prior geometric information. To verify our method, we conduct experiments on the public ps2.0 dataset and self-annotated parking slot dataset with 2,135 images. The results show that our method not only outperforms state-of-the-art competitors with a precision rate of 99.68% and a recall rate of 99.41% on the ps2.0 dataset but also performs a satisfying generalization on the self-annotated dataset. Moreover, it achieves a real-time detection speed of 13 ms per frame on Titan Xp. By converting the parking slot into a directional entrance line, the specially designed DCNN detector can quickly and effectively detect various types of parking slots.

Locomotion control in mammals has been hypothesized to be governed by a central pattern generator (CPG) located in the circuitry of the spinal cord. The most common model of the CPG is the half center model, where two pools of neurons generate alternating, oscillatory activity. In this model, the pools reciprocally inhibit each other ensuring alternating activity. There is experimental support for reciprocal inhibition. However another crucial part of the half center model is a self inhibitory mechanism which prevents the neurons of each individual pool from infinite firing. Self-inhibition is hence necessary to obtain alternating activity. But critical parts of the experimental bases for the proposed mechanisms for self-inhibition were obtained in vitro, in preparations of juvenile animals. The commonly used adaptation of spike firing does not appear to be present in adult animals in vivo. We therefore modeled several possible self inhibitory mechanisms for locomotor control. Based on currently published data, previously proposed hypotheses of the self inhibitory mechanism, necessary to support the CPG hypothesis, seems to be put into question by functional evaluation tests or by in vivo data. This opens for alternative explanations of how locomotion activity patterns in the adult mammal could be generated.

Spiking neural networks (SNNs) offer many advantages over traditional artificial neural networks (ANNs) such as biological plausibility, fast information processing, and energy efficiency. Although SNNs have been used to solve a variety of control tasks using the Spike-Timing-Dependent Plasticity (STDP) learning rule, existing solutions usually involve hard-coded network architectures solving specific tasks rather than solving different kinds of tasks generally. This results in neglecting one of the biggest advantages of ANNs, i.e., being general-purpose and easy-to-use due to their simple network architecture, which usually consists of an input layer, one or multiple hidden layers and an output layer. This paper addresses the problem by introducing an end-to-end learning approach of spiking neural networks constructed with one hidden layer and reward-modulated Spike-Timing-Dependent Plasticity (R-STDP) synapses in an all-to-all fashion. We use the supervised reward-modulated Spike-Timing-Dependent-Plasticity learning rule to train two different SNN-based sub-controllers to replicate a desired obstacle avoiding and goal approaching behavior, provided by pre-generated datasets. Together they make up a target-reaching controller, which is used to control a simulated mobile robot to reach a target area while avoiding obstacles in its path. We demonstrate the performance and effectiveness of our trained SNNs to achieve target reaching tasks in different unknown scenarios.

This paper proposes a framework for uncertainty prediction in complex fusion networks, where signals become available sporadically. Assuming there is no information of the sensor characteristics available, a surrogated model of the sensor uncertainty is yielded directly from data through artificial neural networks. The strategy developed is applied to autonomous vehicle localization through odometry sensors (speed and orientation), so as to determine the location uncertainty in the trajectory. The results obtained allow for fusion of autonomous vehicle location measurements, and effective correction of the accumulated odometry error in most scenarios. The neural networks applicability and generalization capacity are proven, evidencing the suitability of the presented methodology for uncertainty estimation in non-linear and intractable processes.

Vision based-target tracking ability is crucial to bio-inspired snake robots for exploring unknown environments. However, it is difficult for the traditional vision modules of snake robots to overcome the image blur resulting from periodic swings. A promising approach is to use a neuromorphic vision sensor (NVS), which mimics the biological retina to detect a target at a higher temporal frequency and in a wider dynamic range. In this study, an NVS and a spiking neural network (SNN) were performed on a snake robot for the first time to achieve pipe-like object tracking. An SNN based on Hough Transform was designed to detect a target with an asynchronous event stream fed by the NVS. Combining the state of snake motion analyzed by the joint position sensors, a tracking framework was proposed. The experimental results obtained from the simulator demonstrated the validity of our framework and the autonomous locomotion ability of our snake robot. Comparing the performances of the SNN model on CPUs and on GPUs, respectively, the SNN model showed the best performance on a GPU under a simplified and synchronous update rule while it possessed higher precision on a CPU in an asynchronous way.

Neuromorphic vision sensors are bio-inspired cameras that naturally capture the dynamics of a scene with ultra-low latency, filtering out redundant information with low power consumption. Few works are addressing the object detection with this sensor. In this work, we propose to develop pedestrian detectors that unlock the potential of the event data by leveraging multi-cue information and different fusion strategies. To make the best out of the event data, we introduce three different event-stream encoding methods based on Frequency, Surface of Active Event (SAE) and Leaky Integrate-and-Fire (LIF). We further integrate them into the state-of-the-art neural network architectures with two fusion approaches: the channel-level fusion of the raw feature space and decision-level fusion with the probability assignments. We present a qualitative and quantitative explanation why different encoding methods are chosen to evaluate the pedestrian detection and which method performs the best. We demonstrate the advantages of the decision-level fusion via leveraging multi-cue event information and show that our approach performs well on a self-annotated event-based pedestrian dataset with 8,736 event frames. This work paves the way of more fascinating perception applications with neuromorphic vision sensors.

Recent advancements in deep neural networks for graph-structured data have led to state-of-the-art performance in recommender system benchmarks. Adapting these methods to pharmacy product cross-selling recommendation tasks with a million products and hundreds of millions of sales remains a challenge, due to the intricate medical and legal properties of pharmaceutical data. To tackle this challenge, we developed a graph convolutional network (GCN) algorithm called PharmaSage, which uses graph convolutions to generate embeddings for pharmacy products, which are then used in a downstream recommendation task. In the underlying graph, we incorporate both cross-sales information from the sales transaction within the graph structure, as well as product information as node features. Via modifications to the sampling involved in the network optimization process, we address a common phenomenon in recommender systems, the so-called popularity bias: popular products are frequently recommended, while less popular items are often neglected and recommended seldomly or not at all. We deployed PharmaSage using real-world sales data and trained it on 700,000 articles represented as nodes in a graph with edges between nodes representing approximately 100 million sales transactions. By exploiting the pharmaceutical product properties, such as their indications, ingredients, and adverse effects, and combining these with large sales histories, we achieved better results than with a purely statistics based approach. To our knowledge, this is the first application of deep graph embeddings for pharmacy product cross-selling recommendation at this scale to date.

Neuromorphic vision sensor is a new passive sensing modality and a frameless sensor with a number of advantages over traditional cameras. Instead of wastefully sending entire images at fixed frame rate, neuromorphic vision sensor only transmits the local pixel-level changes caused by the movement in a scene at the time they occur. This results in advantageous characteristics, in terms of low energy consumption, high dynamic range, sparse event stream, and low response latency, which can be very useful in intelligent perception systems for modern intelligent transportation system (ITS) that requires efficient wireless data communication and low power embedded computing resources. In this paper, we propose the first neuromorphic vision based multivehicle detection and tracking system in ITS. The performance of the system is evaluated with a dataset recorded by a neuromorphic vision sensor mounted on a highway bridge. We performed a preliminary multivehicle tracking-by-clustering study using three classical clustering approaches and four tracking approaches. Our experiment results indicate that, by making full use of the low latency and sparse event stream, we could easily integrate an online tracking-by-clustering system running at a high frame rate, which far exceeds the real-time capabilities of traditional frame-based cameras. If the accuracy is prioritized, the tracking task can also be performed robustly at a relatively high rate with different combinations of algorithms. We also provide our dataset and evaluation approaches serving as the first neuromorphic benchmark in ITS and hopefully can motivate further research on neuromorphic vision sensors for ITS solutions.

So far no qualifiable automatic code generators (ACGs) are available for Modelica. Hence, digital control applications can be modeled and simulated in Modelica, but require tedious additional efforts (e.g., manual reprogramming) to produce qualifiable target system production code. In order to more fully leverage the potential of a model-based development (MBD) process in Modelica, a qualifiable automatic code generator is needed. Typical Modelica code generation is a fairly complex process which imposes a huge development burden to any efforts of tool qualification. This work aims at mapping a Modelica subset for digital control function development to a well-understood synchronous data-flow kernel language. This kernel language allows to resort to established compilation techniques for data-flow languages which are understood enough to be accepted by certification authorities. The mapping is established by providing a translational semantics from the Modelica subset to the synchronous data-flow kernel language. However, this translation turned out to be more intricate than initially expected and has given rise to several interesting issues that require suitable design decisions regarding the mapping and the language subset.