Adaptive Adjustment Research Articles

Reinforcement Learning in AI-Driven Assessments : Enhancing Continuous Learning and Accessibility

This article explores the transformative potential of Reinforcement Learning (RL) in AI-driven assessments, examining its impact on personalized learning experiences and continuous skill development. We investigate how RL algorithms enable adaptive learning systems to create dynamic, individualized learning paths, provide real-time feedback, and optimize long-term educational outcomes. The article delves into key aspects such as personalized learning trajectories, adaptive difficulty adjustments, and the integration of gamification elements to enhance engagement. We discuss the application of these technologies in various contexts, from traditional educational settings to professional development and certification preparation. The article also addresses the challenges and limitations of implementing RL in educational technology, including concerns about algorithmic bias and the complexity of modeling human learning processes. By analyzing current research and potential future directions, this paper provides a comprehensive overview of how RL is reshaping the landscape of education and assessment, offering insights into the future of adaptive learning systems and their role in fostering lifelong learning in an increasingly digital world.

Node classification based on Attribute Fuse Edge Features and Label Adaptive Adjustment

Most of existing graph representation learning methods only extract information from nodes and ignore the hidden information of edges. Nodes carry weak structural information thus affecting the specificity of node embeddings.To solve these problems, this paper proposes a node classification algorithm based on Attribute Fuse Edge Features and Label Adaptive Adjustment (AFEF_LAA).Firstly, Intimate-Relationship-Attribute of node is designed based on edge embeddings.Rz-Cos rule is constructed to perform the similarity metric between nodes and their neighbors to select intimate neighbor nodes.After that Reverse-TransE is constructed to encode embedding vectors of the edges connected to intimate neighborhood nodes.Secondly, a multi-fusion method based on smoothed neighborhood information is constructed.Each node in the original graph is smoothed together with its neighbor nodes.The smoothed original graph is multi-fused with multiple twin graphs. Finally, a strategy of label adaptive adjustment is proposed to select the label embedding vectors for input to the next-generation trainer by comparing accuracy.This strategy can improve the quality of graph embeddings while effectively avoiding the overfitting problem when processing high-dimensional data.AFEF_LAA is compared with the state-of-the-art algorithms on six graph datasets.Experimental results show that AFEF_LAA can achieve higher node classification accuracy.

PB-Trajectron: Physics bounded neural network for generalized trajectory prediction

Vehicle trajectory prediction is a critical technology in autonomous driving systems, as the quality of prediction directly affects downstream path planning and vehicle control. Although recent studies have shown that models combining kinematic rules with data-driven methods exhibit better interpretability in trajectory prediction, these models often adopt fixed constraint strengths, limiting their generalization ability in diverse traffic scenarios. This fixed constraint strength design restricts the model’s adaptability to different traffic environments.To address this issue, we propose PB-Trajectron, a dynamic integration mechanism that enhances the model’s prediction performance and generalization capability. PB-Trajectron is a dynamic integration mechanism that combines vehicle kinematic rules with deep learning prediction models for generalized vehicle trajectory prediction. The model integrates physics-based motion models and Deep Neural Networks (DNNs) to provide reasonable physical explanations for predicting vehicle trajectories at different speeds. First, we establish two vehicle kinematic constraints applicable to different prediction scenarios, enabling the agent to switch between these constraints based on the causal relationships between vehicle motion states to avoid generating non-physical trajectory results. Second, we propose a kinematic constraint decision framework based on velocity thresholds, which demonstrates adaptive adjustment, allowing the agent to switch tasks according to real-time state conditions and adaptively adjust the contribution of different physical constraints based on actual vehicle speeds. Finally, we investigate the advantages of PB-Trajectron in Out-of-Domain(OOD) generalization.Cross-scenario experiments on the nuScenes dataset show that, compared to previous methods, PB-Trajectron reduces the final displacement error by 7.69% when the prediction step length is 4. Furthermore, out-of-domain generalization tests on the INTERACTION dataset demonstrate that PB-Trajectron achieves a 12.23% reduction in average prediction error on datasets from different countries and scenarios compared to previous methods. The proposed mechanism can better adapt to complex and diverse traffic scenarios, laying the foundation for explainable and robust autonomous driving systems.

A multi-objective physiological control system for continuous-flow left ventricular assist device with non-invasive physiological feedback

In order to enable continuous-flow left ventricular assist device (CFLVAD) to adjust pump speed adaptively in response to changes in ventricular load, we developed a multi-objective physiological control system for CFLVAD with non-invasive physiological feedback mechanism, and proposed a multi-objective hierarchical control (MOHC) strategy to coordinate three controllers. A model-based estimation method was utilized to gain the physiological feedback variables. Suction prevention controller, regurgitation prevention controller, and physiological pulsatility controller were developed and applied to achieve the objectives: preventing left ventricular suction, preventing pump regurgitation, pump flow adaptive adjustment, and enhancing vascular pulsatility. The constraint conditions of feedback variables and controller priority were used to implement multi-objective hierarchical control. The preload and afterload were increased or decreased to simulate the scenarios of the sharp increase in left ventricular flow, the sharp decrease in left ventricular flow, and the rest-exercise-rest. The performance of MOHC was evaluated by subjecting it to three scenarios and compared with that of constant speed control (CSC) and pulsatile varying speed control (PVSC). The simulation results show that the linear correlation between the filtered and actual feedback variables was as high as 99.9%. Compared with CSC and PVSC, MOHC can avoid ventricular suction and pump regurgitation when the left ventricular flow changed rapidly. During rest or exercise, MOHC provided more adequate physiological perfusion and enhances greater vascular pulsatility than CSC and PVSC. MOHC can adjust the CFLVAD pump speed in response to changes in ventricular load.

Dynamic collaborative learning with heterogeneous knowledge transfer for long-tailed visual recognition

Solving the long-tailed visual recognition with deep convolutional neural networks is still a challenging task. As a mainstream method, multi-experts models achieve SOTA accurary for tackling this problem, but the uncertainty in network learning and the complexity in fusion inference constrain the performance and practicality of the multi-experts models. To remedy this, we propose a novel dynamic collaborative learning with heterogeneous knowledge transfer model (DCHKT) in this paper, in which experts with different expertise collaborate to make predictions. DCHKT consists of two core components: dynamic adaptive weight adjustment and heterogeneous knowledge transfer learning. First, the dynamic adaptive weight adjustment is designed to shift the focus of model training between the global expert and domain experts via dynamic adaptive weight. By modulating the trade-off between the learning of features and classifier, the dynamic adaptive weight adjustment can enhance the discriminative ability of each expert and alleviate the uncertainty of model learning. Then, heterogeneous knowledge transfer learning, which measures the distribution differences between the fusion logits of multiple experts and the predicted logits of each expert with different specialties, can achieve message passing between experts and enhance the consistency of ensemble prediction in model training and inference to promote their collaborations. Finally, extensive experimental results on public long-tailed datasets: CIFAR-LT, ImageNet-LT, Place-LT and iNaturalist2018, demonstrate the effectiveness and superiority of our DCHKT.

Adaptive denitrification adjustment by marimo for enhanced nitrate nitrogen removal in lake restoration

This work investigated the effectiveness of marimo in restoring lake ecosystems, with a focus on its capacity for adaptive denitrification. Observations revealed a significant increase in granule size, benefiting its settling capability and thereby facilitating substantial reductions in nitrate levels and overall lake water purification. Notably, nitrate nitrogen was identified as pivotal in the nitrogen cycle, exhibiting a strong coupling relationship with denitrification processes. Marimo autonomously adjusted its denitrification in response to environmental nitrate levels, enhancing its nitrogen removal efficiency. Furthermore, Rhodobacteraceae was found to play an important role in nitrogen metabolism, with competitive interactions between Proteobacteria and Bacteroidota, influencing the overall efficiency of nitrogen removal. It was found that at first, the accumulation of nitrate enhanced denitrification, while afterwards, the decrease in nitrate concentration weakened denitrification. In addition, assimilatory nitrate reduction showed an upward trend throughout the entire process. Analysis of metabolic pathways further supported the adaptive denitrification adjustment mechanism of marimo. These findings highlight the potential of marimo as a natural solution for water quality improvement in lake ecosystems.

Adaptive positioning of large-scale aircraft components using a simplified image-based visual servoing via online measurement of ball-head center

In digital alignment systems, ensuring fast and accurate alignment between the ball head on large aircraft components and the ball socket of the positioner is the key to aircraft assembly efficiency and quality. Image-based visual servoing is one of the most advanced techniques with high efficiency and positioning accuracy, but it does not account for measuring the ball-head position. Moreover, variable target positions, similar feature interference, and poor lighting conditions pose great challenges to the fast and robust visual measurement of ball-head position. Hence, an online visual measurement method is introduced to measure the absolute position of the ball head in real time. An adaptive region of interest extraction algorithm and an improved edge following method are introduced to extract the elliptical contour from the ball-head image, and ellipse detection is achieved through a simple triplet selection algorithm. A geometric model based on the perspective projection of the sphere is established for estimating the ball-head center. Then, the simplified image-based visual servoing method is developed by constantizing the image Jacobian matrix. Next, an adaptive positioning method of large-scale aircraft components with multiple ball heads is proposed from a holistic perspective. Finally, experiments show that the final positioning accuracy of each ball head in the X/Y plane is less than ± 0.05 mm, with an efficiency almost ten times that of the conventional method. After adaptive adjustment, the position and angle errors of the simulated component are reduced within 0.6 mm and 0.3°, respectively.

Adaptive linear active disturbance-rejection control strategy reduces the impulse current of compressed air energy storage connected to the grid

The merits of compressed air energy storage (CAES) include large power generation capacity, long service life, and environmental safety. When a CAES plant is switched to the grid-connected mode and participates in grid regulation, using the traditional control mode with low accuracy can result in excess grid-connected impulse current and junction voltage. This occurs because the CAES output voltage does not match the frequency, amplitude, and phase of the power grid voltage. Therefore, an adaptive linear active disturbance-rejection control (A-LADRC) strategy was proposed. Based on the LADRC strategy, which is more accurate than the traditional proportional integral controller, the proposed controller is enhanced to allow adaptive adjustment of bandwidth parameters, resulting in improved accuracy and response speed. The problem of large impulse current when CAES is switched to the grid-connected mode is addressed, and the frequency fluctuation is reduced. Finally, the effectiveness of the proposed strategy in reducing the impact of CAES on the grid connection was verified using a hardware-in-the-loop simulation platform. The influence of the k value in the adaptive- adjustment formula on the A-LADRC was analyzed through simulation. The anti-interference performance of the control was verified by increasing and decreasing the load during the presynchronization process.

An Improved NSGA-III with a Comprehensive Adaptive Penalty Scheme for Many-Objective Optimization

Pareto dominance-based algorithms face a significant challenge in handling many-objective optimization problems. As the number of objectives increases, the sharp rise in non-dominated individuals makes it challenging for the algorithm to differentiate their quality, resulting in a loss of selection pressure. The application of the penalty-based boundary intersection (PBI) method can balance convergence and diversity in algorithms. The PBI method guides the evolution of individuals by integrating the parallel and perpendicular distances between individuals and reference vectors, where the penalty factor is crucial for balancing these two distances and significantly affects algorithm performance. Therefore, a comprehensive adaptive penalty scheme was proposed and applied to NSGA-III, named caps-NSGA-III, to achieve balance and symmetry between convergence and diversity. Initially, each reference vector’s penalty factor is computed based on its own characteristic. Then, during the iteration process, the penalty factor is adaptively adjusted according to the evolutionary state of the individuals associated with the corresponding reference vector. Finally, a monitoring strategy is designed to oversee the penalty factor, ensuring that adaptive adjustments align with the algorithm’s needs at different stages. Through a comparison involving benchmark experiments and two real-world problems, the competitiveness of caps-NSGA-III was demonstrated.

Adaptive Synaptic Adjustment Mechanism to Improve Learning Performances of Spiking Neural Networks

ABSTRACTSpiking Neural Networks (SNNs) are currently attracting researchers' attention due to their efficiencies in various tasks. Spike‐timing‐dependent plasticity (STDP) is an unsupervised learning process that utilizes bio‐plausibility based on the relative timing of pre/post‐synaptic spikes of neurons. Integrated with STDP, SNNs perform well consuming less energy. However, it is hard to ensure that synaptic weights always converge to values guaranteeing accurate prediction because STDP does not change synaptic weights with supervision. To address this limitation, researchers have proposed mechanisms for inducing STDP to converge synaptic weights on the proper values referring to current synaptic weights. Thus, if the current weights fail to describe proper synaptic connections, they cannot induce STDP to update synaptic weights properly. To solve this problem, we propose an adaptive mechanism that helps STDP to converge synaptic weights directly based on input data features: Adaptive synaptic template (AST). AST leads synaptic weights to describe synaptic connections according to the data features. It prevents STDP from changing synaptic weights based on abnormal weights that fail to describe the proper synaptic connections. This is because it does not use the current synaptic weights that can disturb proper weight convergence. We integrate AST with an SNN and conduct experiments to compare it with a baseline (the SNN without AST) and benchmarks (previous works to improve STDP). Our experimental results show that the SNN using AST classifies various data sets with 6%–39% higher accuracy than the baseline and benchmarks.

Multi-Strategy Enhanced Crested Porcupine Optimizer: CAPCPO

Metaheuristic algorithms are widely used in engineering problems due to their high efficiency and simplicity. However, engineering challenges often involve multiple control variables, which present significant obstacles for metaheuristic algorithms. The Crested Porcupine Optimizer (CPO) is a metaheuristic algorithm designed to address engineering problems, but it faces issues such as falling into a local optimum. To address these limitations, this article proposes three new strategies: composite Cauchy mutation strategy, adaptive dynamic adjustment strategy, and population mutation strategy. The three proposed strategies are then introduced into CPO to enhance its optimization capabilities. On three well-known test suites, the improved CPO (CAPCPO) outperforms 11 metaheuristic algorithms. Finally, comparative experiments on seven real-world engineering optimization problems demonstrate the advantages and potential of CAPCPO in solving complex problems. The multifaceted experimental results indicate that CAPCPO consistently achieves superior solutions in most cases.

Re-configurable digital bandwidth interleaved sampling system based on fast spectrum sensing.

The complexity of systems with parallel acquisition architectures has increased sharply with the continuous growth of signal bandwidth, and sampling precision has been greatly challenged. Considering that the signal to be measured usually exhibits sparsity in the frequency domain, this paper proposes a re-configurable bandwidth interleaved acquisition architecture to maximize test flexibility and accuracy. The sampling process is divided into two stages: sensing and re-configurable acquisition. In the sensing stage, the signal spectrum distribution is roughly understood using a sparse Fourier transform. Based on the spectrum sensing results, the subband selection and the adaptive adjustment of the mixing local oscillator in the acquisition system are performed. Ultimately, these steps enhance sampling accuracy. This paper verifies the effectiveness of this method on a 10GHz acquisition system, demonstrating that it can significantly reduce data redundancy. In addition, it improves acquisition accuracy compared to traditional bandwidth interleaved systems. The experimental results indicate that re-configurable sampling can significantly improve the quality of sampling results. This is evidenced by a signal-to-noise ratio improvement of over 7.4 dB and a spurious-free dynamic range improvement of over 4.7 dB compared to traditional sampling results.

A Novel Reinforcement Learning-Based Particle Swarm Optimization Algorithm for Better Symmetry between Convergence Speed and Diversity

This paper introduces a novel Particle Swarm Optimization (RLPSO) algorithm based on reinforcement learning, embodying a fundamental symmetry between global and local search processes. This symmetry aims at addressing the trade-off issue between convergence speed and diversity in traditional algorithms. Traditional Particle Swarm Optimization (PSO) algorithms often struggle to maintain good convergence speed and particle diversity when solving multi-modal function problems. To tackle this challenge, we propose a new algorithm that incorporates the principles of reinforcement learning, enabling particles to intelligently learn and adjust their behavior for better convergence speed and richer exploration of the search space. This algorithm guides particle learning behavior through online updating of a Q-table, allowing particles to selectively learn effective information from other particles and dynamically adjust their strategies during the learning process, thus finding a better balance between convergence speed and diversity. The results demonstrate the superior performance of this algorithm on 16 benchmark functions of the CEC2005 test suite compared to three other algorithms. The RLPSO algorithm can find all global optimum solutions within a certain error range on all 16 benchmark functions, exhibiting outstanding performance and better robustness. Additionally, the algorithm’s performance was tested on 13 benchmark functions from CEC2017, where it outperformed six other algorithms by achieving the minimum value on 11 benchmark functions. Overall, the RLPSO algorithm shows significant improvements and advantages over traditional PSO algorithms in aspects such as local search strategy, parameter adaptive adjustment, convergence speed, and multi-modal problem handling, resulting in better performance and robustness in solving optimization problems. This study provides new insights and methods for the further development of Particle Swarm Optimization algorithms.

Robust ELM-PID tracing control on autonomous mobile robot via transformer-based pavement crack segmentation

Pavement crack tracing is paramount to missions encompassing automated crack sealing for road maintenance. However, existing methods still face several challenges, including the incapability to precisely extract crack trajectories and the challenge of tuning control parameters within intricate backgrounds. To address these limitations, the ViT-S2T network and the ELM-PID control system are proposed for crack tracing. Specifically, the ViT-S2T consists of two branches. The transformer-based feature extraction module (TFEM) integrates multi-head attention mechanism and multi-layer perceptron to capture global contextual crack semantic features. The incoherent segmentation masks (ISM) employs a binary classifier to predict the coarsest irrelevant mask and further performs up-sampling fusion of higher-resolution features. Moreover, the Neural-PID control method is designed to track crack trajectories, combining Extreme Learning Machines (ELM) and Proportional Integral Derivative (PID). The ELM-PID controller utilizes a three-layer backpropagation neural network and proposes the ELM model for adaptive adjustment by predicting the tuning parameters of PID. This framework is applied to real-time visual tracing for edge AI. Extensive tests performed on three arduous datasets of DeepCrack, CFD, and S2TCrack, achieving a precision of 82.76% and mAP@0.5 of 75.63% and speed of 0.0513 m/s, demonstrating the superior and robust nature of our approach in pavement crack tracing.

A robust adaptive error state Kalman filter for MEMS IMU attitude estimation under dynamic acceleration

Accurate estimation of attitude (pitch, roll) is a prerequisite for ensuring safe navigation during vehicle control execution. In dynamic environments, the presence of acceleration often degrades the accuracy and robustness of attitude estimation using traditional algorithms with Micro-Electro-Mechanical Systems (MEMS) Inertial Measurement Unit (IMU). This paper proposes a robust adaptive error state Kalman filter (RAESKF) algorithm for attitude estimation of MEMS IMU under dynamic acceleration conditions. The RAESKF algorithm decomposes the true attitude Direction Cosine Matrix (DCM) into nominal and error components. An error state Kalman filter is utilized to fuse real-time measurements from MEMS gyroscope and accelerometer, estimating the error component, which is then used to correct the nominal attitude DCM. Furthermore, within the error state Kalman filtering framework, a dynamic acceleration robust adaptive adjustment strategy is implemented. This strategy relies on real-time data monitoring, threshold-based decision-making, and switching mechanisms. It adaptively selects between dynamic acceleration model compensation and online adjustment of the measurement noise covariance matrix. The primary objective of this strategy is to mitigate the impact of disturbance induced by dynamic acceleration on attitude estimation, thereby enhancing the accuracy and robustness. Laboratory rotation experiments have demonstrated that the algorithm improved pitch and roll measurement accuracy by at least 8.81% and 11.69%, respectively, under rotational conditions. In dynamic acceleration conditions, pitch and roll measurement accuracy improved by at least 42.76% and 67.21%, respectively.

Self-Adhesive and Self-Sustainable Bioelectronic Patch for Physiological Feedback Electronic Modulation of Soft Organs.

Bionic electrical stimulation (Bio-ES) aims to achieve personalized therapy and proprioceptive adaptation by mimicking natural neural signatures of the body, while current Bio-ES devices are reliant on complex sensing and computational simulation systems, thus often limited by the low-fidelity of simulated electrical signals, and failure of interface information interaction due to the mechanical mismatch between soft tissues and rigid electrodes. Here, the study presents a flexible and ultrathin self-sustainable bioelectronic patch (Bio-patch), which can self-adhere to the lesion area of organs and generate bionic electrical signals synchronized vagal nerve envelope in situ to implement Bio-ES. It allows adaptive adjustment of intensity, frequency, and waveform of the Bio-ES to fully meet personalized needs of tissue regeneration based on real-time feedback from the vagal neural controlled organs. With this foundation, the Bio-patch can effectively intervene with excessive fibrosis and microvascular stasis during the natural healing process by regulating the polarization time of macrophages, promoting the reconstruction of the tissue-engineered structure, and accelerating the repair of damaged liver and kidney. This work develops a practical approach to realize biomimetic electronic modulation of the growth and development of soft organs only using a multifunctional Bio-patch, which establishes a new paradigm for precise bioelectronic medicine.

The Path to Improvement of China's Professional Cultivation in the Perspective of Legal Clinics

Since its inception in the United States in the 1960s, the legal clinic has developed rapidly in the United Kingdom, Finland and other countries due to its characteristics of significantly improving students' practical ability. China has also joined this trend. Since 2000, seven universities, including Peking University and Tsinghua University, have taken the lead in introducing legal clinics, and other universities have followed suit. Although the application of legal clinic in major universities has been quite mature, its application has been limited to general undergraduate courses rather than vocational undergraduate courses. Therefore, the legal clinic has been in a blank state in vocational undergraduate courses which train practical talents. Based on the blank phenomenon of legal clinic in vocational undergraduate, this paper aims to explore the path of improvement of vocational training in the perspective of legal clinic. Through the research, it seeks to put forward practical suggestions to promote the effective use of legal clinic in vocational undergraduate, in order to better cultivate practical talents. The literature review method and comparative method are used to conduct an exhaustive research on the development history of legal clinics in the international arena and in China. By comparatively analysing the application of legal clinics in general and vocational undergraduate courses, the applicability and development path of legal clinics in vocational undergraduate courses are explored. The research found that although legal clinics have achieved remarkable results in general undergraduate courses, there is a gap in the field of vocational undergraduate courses. Through comparative analyses, a path for the improvement of the law clinic in vocational undergraduate is proposed, including suggestions for adaptive adjustment of the clinic model, broadening the field of cooperation, and strengthening cooperation with the industry. This research fills the research gap of legal clinics in the field of vocational undergraduate, and provides new perspectives and paths for colleges and universities in cultivating the practical ability of vocational undergraduate students. By promoting the application of legal clinic in vocational undergraduate, it can better meet the needs of the actual legal profession and provide substantial support for the cultivation of more comprehensive legal professionals.

Distributed adaptive event-triggered finite-time fault-tolerant containment control for multi-UAVs with input constraints and actuator failures

This article investigates the distributed adaptive finite-time containment control problem for multi-UAVs with input constraints, actuator failures, communication limitations, and external disturbances. First, a new smoothing function is used to smooth the asymmetric input constraint signals so that the input constraint and actuator fault control problem can be transformed into a variable gain control problem. Subsequently, a new Nussbaum function is proposed to solve the variable gain control problem. A new adaptive event-triggered strategy is designed to solve the communication limitation problem, and the trigger threshold has the characteristic of adaptive adjustment that can be dynamically decreased. In response to external disturbances, an adaptive law is designed to estimate and compensate for the boundaries of disturbances. It follows from the analysis based on Lyapunov theory that under the proposed controller, the followers will converge to the convex envelope formed by the leaders in a finite time, and Zeno-free is achieved. Simulation results are provided to verify the effectiveness of the developed adaptive event-triggered finite-time fault-tolerant containment control laws.

ASLAM-FD: a multi-sensor adaptive collaborative fusion SLAM framework based on degradation detection and deep reinforcement learning

Abstract Aiming at the difficulty in ensuring accuracy and performance of existing Simultaneous Localization And Mapping (SLAM) technology based on multi-sensor fusion in complex dynamic environments, a multi-sensor adaptive fusion SLAM framework based on degradation detection and deep reinforcement learning (ASLAM-FD) is proposed. This framework can achieve adaptive collaborative precise adjustment of fusion weights (FWs) based on the real-time self-degradation states and relative degradation states quantified by each sensor, and can adapt to different tightly coupled SLAM algorithms based on FWs. In addition, within this framework, the continuous quantification models for the degradation states of internal/external sensors with certain versatility (we refer to them as EX-DM and IN-DM) is proposed. These quantitative models can achieve continuous quantification of degradation states of various mainstream internal/external sensors. Based on the above sensor degradation state quantification models, this paper further proposes a deep reinforcement learning (DRL) network suitable for adaptive collaborative adjustment of FWs. This network focuses more on the temporal nature of sensor observation data and degradation states, making it more suitable for modeling relationships between data with temporal features. In the experimental section, we adapted the proposed ASLAM-FD to different multi-sensor fusion SLAM algorithms on multiple datasets, and compared it with multiple advanced fusion SLAM algorithms. We found that adapting ASLAM-FD can effectively improve the accuracy and performance of fusion SLAM in complex dynamic environments.

Compact Laser-Induced Fluorescence Detector with Adjustable Laser Focal Spot for Multiple Purposes.

In many research fields, the demand for miniaturized laser-induced fluorescence (LIF) detection systems has been increasing. This work has developed a compact LIF detector, employing a laser diode as the excitation source and a photodiode as the photodetector with an adjustable laser focal spot, to meet the diverse requirements of various observation targets, such as capillaries, PCR tubes, and microfluidic chips. It features the functionalities of background fluorescence correction, the adaptive adjustment of the dynamic range, and constant power control for the laser. The influence of the excitation power on the detection limit was studied through experiments, and the configuration results for LED/LD as light sources and 487/450 nm wavelengths were compared and optimized. A fully integrated, compact, modular epifluorescence LIF detector was subsequently constructed, measuring 40 × 22 × 38 mm3 in total size, with a cost of USD 320, and achieving a detection limit of 0.4 nM for fluorescein sodium. Finally, the detector was integrated into a nucleic acid detection system with a microfluidic chip on the Chinese Space Station (CSS) and was also tested with PCR tubes and capillaries, proving its broad practicality and adaptability to various analytical systems.