Concurrent Learning Research Articles

A concurrent learning approach to monocular vision range regulation of leader/follower systems

This paper explores range and bearing angle regulation of a leader–follower using monocular vision. The main challenge is that monocular vision does not directly provide a range measurement. The contribution is a novel concurrent learning (CL) approach, called CL Subtended Angle and Bearing Estimator for Relative pose (CL-SABER), which achieves range regulation without communication, persistency of excitation or known geometry and is demonstrated on a physical, robot platform. A history stack estimates target size which augments the Kalman filter (KF) with a range pseudomeasurement. The target is followed to scale without drift, persistency of excitation requirements, prior knowledge, or additional measurements. Finite excitation is required to achieve parameter convergence and perform steady-state regulation using CL-SABER. Evaluation using simulation and mobile robot experiments in special Euclidean planar space (SE(2)) show that the new method provides stable and consistent range regulation, as demonstrated by the inter-rater reliability, including in noisy and high leader acceleration environments.

Deep neural network-based molecular dynamics simulations for AlxGa1-xN alloys and their thermal properties

Efficient heat dissipation is crucial for the performance and lifetime of high electron mobility transistors (HEMTs). The thermal conductivity of materials and interfacial thermal conductance (ITC) play significant roles in their heat dissipation. To predict the thermal properties of AlxGa1-xN and the ITC of GaN/AlxGa1-xN in HEMTs, a dataset with first-principles accuracy was constructed using concurrent learning method and trained to obtain an interatomic potential employing deep neural networks (DNN) method. Using obtained DNN interatomic potential, equilibrium molecular dynamics simulations were employed to calculate the thermal conductivity of AlxGa1-xN, which showed excellent consistent with experimental results. Additionally, the phonon density of states of AlxGa1-xN and the ITC of GaN/AlxGa1-xN were calculated. Our study revealed a decrease in the ITC of GaN/AlxGa1-xN with increasing x, and the insertion of 1nm-thick AlN at the interface significantly reduced the ITC. This work provided a high-fidelity DNN potential for molecular dynamics simulations of AlxGa1-xN, offering valuable guidance for exploring the thermal transport of complex alloy and heterostructure.&#xD.

Crossfeat: a transformer-based cross-feature learning model for predicting drug side effect frequency.

Safe drug treatment requires an understanding of the potential side effects. Identifying the frequency of drug side effects can reduce the risks associated with drug use. However, existing computational methods for predicting drug side effect frequencies heavily depend on known drug side effect frequency information. Consequently, these methods face challenges when predicting the side effect frequencies of new drugs. Although a few methods can predict the side effect frequencies of new drugs, they exhibit unreliable performance owing to the exclusion of drug-side effect relationships. This study proposed CrossFeat, a model based on convolutional neural network-transformer architecture with cross-feature learning that can predict the occurrence and frequency of drug side effects for new drugs, even in the absence of information regarding drug-side effect relationships. CrossFeat facilitates the concurrent learning of drugs and side effect information within its transformer architecture. This simultaneous exchange of information enables drugs to learn about their associated side effects, while side effects concurrently acquire information about the respective drugs. Such bidirectional learning allows for the comprehensive integration of drug and side effect knowledge. Our five-fold cross-validation experiments demonstrated that CrossFeat outperforms existing studies in predicting side effect frequencies for new drugs without prior knowledge. Our model offers a promising approach for predicting the drug side effect frequencies, particularly for new drugs where prior information is limited. CrossFeat's superior performance in cross-validation experiments, along with evidence from case studies and ablation experiments, highlights its effectiveness.

Is home environment associated with child fluid reasoning abilities in middle childhood in high-risk settings? findings from a cross-sectional study in Pakistan

BackgroundEvidence from low- and middle-income countries (LMIC) suggests that home environment is associated with early childhood development outcomes. However, studies from LMIC that have examined how the home environment during middle childhood is associated with intellectual abilities are scarce. The objective of the study was to explore the association between different aspects of the home environment at 7–8 years and fluid reasoning abilities in a rural, high-risk cohort in Pakistan.MethodsWe employed a cross-sectional research design to examine 1172 children between 7 and 8 years and their families, utilizing the Home Observation for Measurement of Environment for Middle Childhood (HOME-MC) to evaluate various aspects of the home environment and the Fluid Reasoning Index (FRI) of the Wechsler Intelligence for Children (WISC)-5th edition to assess the fluid reasoning abilities of the children. Multivariable regression analyses were used to examine the association between different components of HOME-MC (scored as indices) and FRI scores.FindingsLearning materials and opportunities (β = 1.74, 95% CI = 1.15, 2.33) and Responsivity (β = 1.73, 95% CI = 1.07, 2.38) indices had the strongest association with FRI score followed by Family companionship index (β = 1.27, 95% CI = 0.63, 1.90). The eight different indices of the HOME-DC explained 22% of the total variation in FRI scores.ConclusionWe conclude that concurrent learning opportunities, parental responsivity and family companionship at home are associated with fluid reasoning abilities during middle childhood which is comparable to what has been found in early childhood years.

Adaptive Inverse Nonlinear Optimal Control Based on Finite-Time Concurrent Learning and Semidefinite Programming.

This article investigates the problem of inverse optimal control (IOC) for a class of nonlinear affine systems. An adaptive IOC approach is proposed to recover the cost functional using only the system state data, which integrates the finite-time concurrent learning (FTCL) technique and the semidefinite programming (SDP) technique. First, an identifier neural network (NN) is employed to approximate the unknown nonlinear control policy, and an FTCL-based update law is proposed to estimate the weights of the identifier NN online, which removes the traditional persistent excitation (PE) condition. Moreover, the finite-time convergence as well as the uniformly ultimately boundness (UUB) of estimation error of the identifier NN weights are analysed according to whether or not there exists the identifier NN approximation error. Then, with the help of a value NN for approximating the value function, an SDP problem with a quadratic objective function can be set up for determining the weighting matrices of the cost functional. Finally, simulation results are presented to validate the proposed method.

Concurrent learning for adaptive pontryagin's maximum principle of nonlinear systems with inequality constraints

AbstractIn this article, a finite‐horizon adaptive Pontryagin's maximum principle is presented for nonlinear systems with state inequality constraints. Concurrent learning (CL) technique is adopted to identify the unknown parameters of the dynamic systems. Based on the identification model, a novel adaptive iterative algorithm under the Pontryagin's framework is introduced to learn the finite‐horizon optimal control solution. Convergence analysis of the algorithm is provided by showing that the cost function sequence is monotonically decreasing. Furthermore, we extend the adaptive iterative algorithm to time‐varying nonlinear systems. The new algorithm overcomes the technical obstacles of the existing adaptive/approximate dynamic programming (ADP) approaches to deal with the time‐varying characteristic of Hamilton–Jacobi–Bellman (HJB) partial differential equation (PDE), especially when state constraints exist. Simulation examples are carried out to validate the effectiveness of the theoretical results.

Contribution of amygdala to dynamic model arbitration under uncertainty.

Intrinsic uncertainty in the reward environment requires the brain to run multiple models simultaneously to predict outcomes based on preceding cues or actions, commonly referred to as stimulus- and action-based learning. Ultimately, the brain also must adopt appropriate choice behavior using reliability of these models. Here, we combined multiple experimental and computational approaches to quantify concurrent learning in monkeys performing tasks with different levels of uncertainty about the model of the environment. By comparing behavior in control monkeys and monkeys with bilateral lesions to the amygdala or ventral striatum, we found evidence for dynamic, competitive interaction between stimulus-based and action-based learning, and for a distinct role of the amygdala. Specifically, we demonstrate that the amygdala adjusts the initial balance between the two learning systems, thereby altering the interaction between arbitration and learning that shapes the time course of both learning and choice behaviors. This novel role of the amygdala can account for existing contradictory observations and provides testable predictions for future studies into circuit-level mechanisms of flexible learning and choice under uncertainty.

Recurrent and Concurrent Prediction of Longitudinal Progression of Stargardt Atrophy and Geographic Atrophy towards Comparative Performance on Optical Coherence Tomography as on Fundus Autofluorescence

Stargardt atrophy and geographic atrophy (GA) represent pivotal endpoints in FDA-approved clinical trials. Predicting atrophy progression is crucial for evaluating drug efficacy. Fundus autofluorescence (FAF), the standard 2D imaging modality in these trials, has limitations in patient comfort. In contrast, spectral-domain optical coherence tomography (SD-OCT), a 3D imaging modality, is more patient friendly but suffers from lower image quality. This study has two primary objectives: (1) develop an efficient predictive modeling for the generation of future FAF images and prediction of future Stargardt atrophic (as well as GA) regions and (2) develop an efficient predictive modeling with advanced 3D OCT features at ellipsoid zone (EZ) for the comparative performance in the generation of future enface EZ maps and prediction of future Stargardt atrophic regions on OCT as on FAF. To achieve these goals, we propose two deep neural networks (termed ReConNet and ReConNet-Ensemble) with recurrent learning units (long short-term memory, LSTM) integrating with a convolutional neural network (CNN) encoder–decoder architecture and concurrent learning units integrated by ensemble/multiple recurrent learning channels. The ReConNet, which incorporates LSTM connections with CNN, is developed for the first goal on longitudinal FAF. The ReConNet-Ensemble, which incorporates multiple recurrent learning channels based on enhanced EZ enface maps to capture higher-order inherent OCT EZ features, is developed for the second goal on longitudinal OCT. Using FAF images at months 0, 6, and 12 to predict atrophy at month 18, the ReConNet achieved mean (±standard deviation, SD) and median Dice coefficients of 0.895 (±0.086) and 0.922 for Stargardt atrophy and 0.864 (±0.113) and 0.893 for GA. Using SD-OCT images at months 0 and 6 to predict atrophy at month 12, the ReConNet-Ensemble achieved mean and median Dice coefficients of 0.882 (±0.101) and 0.906 for Stargardt atrophy. The prediction performance on OCT images is comparably good to that on FAF. These results underscore the potential of SD-OCT for efficient and practical assessment of atrophy progression in clinical trials and retina clinics, complementing or surpassing the widely used FAF imaging technique.

Dynamic Event-Triggered Safe Control for Nonlinear Game Systems With Asymmetric Input Saturation.

This article focuses on the Pareto optimal issues of nonlinear game systems with asymmetric input saturation under dynamic event-triggered mechanism (DETM). First, the safe control is guaranteed by transforming the system with safety constraints into the one without state constraints utilizing barrier function. The united cost function integrating nonquadratic utility function is constructed to provide the foundation to achieve the Pareto optimal solutions. Then, the adaptive dynamic programming method with concurrent learning is proposed to approximate the Pareto optimal strategies wherein both current and historical data are utilized. To further lessen the consumptions of computation/communication resources, the DETM is integrated into the adaptive algorithm framework which can avoid Zeno phenomena. All the signals of the closed-loop system are proved to be uniformly ultimately bounded. Finally, the simulation results are given to validate the effectiveness of the proposed method from several aspects.

Model-Based Online Adaptive Inverse Noncooperative Linear-Quadratic Differential Games via Finite-Time Concurrent Learning

Model-Based Online Adaptive Inverse Noncooperative Linear-Quadratic Differential Games via Finite-Time Concurrent Learning

A novel concurrent learning-based fixed-time convergent visual depth observer for weakly persistently exciting perspective dynamical systems

The problem of synthesizing a fixed-time depth observer based on monocular image feedback is considered in this study. The key challenge lies in the fact that the perspective dynamical system used to model visual motion is typically characterized as being weakly persistently exciting, which complicates observer synthesis. Furthermore, the key to achieving the task objective (safe obstacle avoidance, for instance) lies in the synthesis of a depth observer that achieves rapid convergence of the (static) obstacle depth estimate to the ground truth in a known fixed-time. To address these challenges, and in contrast with prior schemes that rely on a motion-restrictive persistency of excitation (PE) condition for ensuring exponential convergence, a novel adaptive observer framework is considered in this study that incorporates a concurrent learning (CL) term for ensuring fixed-time observer convergence. In particular, the use of concurrent learning allows for the synthesis of a relaxed finite-time excitation condition that relies on historical data recorded over a dynamic sliding window in the recent past that the proposed observer relies on to ensure fixed-time convergence. Thus, a continuous-time reduced-order observer formulation is presented that relies on camera motion data to achieve fixed-time convergence to a uniform ultimate bound for a suitably large choice of the observer gains. Experimental results are used to demonstrate the efficacy of the proposed scheme in the presence of significant measurement noise. A performance comparison study is also undertaken to demonstrate superior performance of the proposed scheme compared to leading alternative designs. Finally, the practical applicability of the proposed scheme is verified by incorporating the proposed scheme within a reactive navigation scheme to accomplish obstacle avoidance. By incorporating a suitably informative CL term within the observer framework, the proposed scheme eliminates the need to rely on a difficult-to-verify PE condition, thus rendering it more suitable for practical applications like visual target-tracking and visual servo control.

Neural network-based adaptive optimal tracking control for hypersonic morphing aircraft with appointed-time prescribed performance

In this paper, an adaptive optimal attitude tracking controller for hypersonic morphing aircraft with appointed-time prescribed performance is presented. A proper error transformation methodology is developed to ensure the performance constraints are met without knowing initial tracking conditions. Subsequently, an adaptive composite control scheme is devised for the transformed system, comprising a feedforward neuro-backstepping controller and a feedback optimal controller. The former is employed to convert the optimal tracking problem into an equivalent optimal regulation problem, while the latter is constructed using adaptive dynamic programming (ADP) with a single critic network to achieve optimality. A novel weight-tuning law for the critic network is introduced, incorporating a stability indicator and the concurrent learning technique. This approach relaxes the underlying restrictive conditions in ADP, improving the robustness and availability of the system. The stability of the closed-loop system is analyzed using the Lyapunov direct method. Finally, the effectiveness and improved performance of the proposed control scheme are validated through numerical simulations.

Distributed Optimal Attitude Synchronization Control of Multiple QUAVs via Adaptive Dynamic Programming.

This article proposes a distributed optimal attitude synchronization control strategy for multiple quadrotor unmanned aerial vehicles (QUAVs) through the adaptive dynamic programming (ADP) algorithm. The attitude systems of QUAVs are modeled as affine nominal systems subject to parameter uncertainties and external disturbances. Considering attitude constraints in complex flying environments, a one-to-one mapping technique is utilized to transform the constrained systems into equivalent unconstrained systems. An improved nonquadratic cost function is constructed for each QUAV, which reflects the requirements of robustness and the constraints of control input simultaneously. To overcome the issue that the persistence of excitation (PE) condition is difficult to meet, a novel tuning rule of critic neural network (NN) weights is developed via the concurrent learning (CL) technique. In terms of the Lyapunov stability theorem, the stability of the closed-loop system and the convergence of critic NN weights are proved. Finally, simulation results on multiple QUAVs show the effectiveness of the proposed control strategy.

An IOV Spectrum Sharing Approach based on Multi-Agent Deep Reinforcement Learning

Highly dynamic Internet of Vehicles spectrum sharing can share spectrum owned by vehicle-to-infrastructure links through multiple workshop links to achieve efficient resource allocation. Aiming at the problem that the rapid variations in channel states in highly dynamic vehicular environments can make it challenging for base stations to gather and manage information about instantaneous channel states, we present a multi-agent deep reinforcement learning-based V2X spectrum access algorithm. The algorithm is designed to optimize the throughput of V2I user under V2V user delay and reliability constraints, and uses the experience gained from interacting with the communication environment to update the Q network to improve spectrum and power allocation strategies. Implicit collaborative agents are trained through an improved DQN model combined with dueling network architecture and long short-term memory network layers and public rewards. With lagged Q-learning and concurrent experience replay trajectories, the training process was stabilized and the non-stationarity problem caused by concurrent learning of multiple agents was resolved. Simulation results demonstrate that our presented algorithm achieves a mean successful payload delivery rate of 95.89%, which is 16.48% greater than that of the randomized baseline algorithm. Our algorithm obtains approximately the optimal value and shows performance close to the centralized brute force algorithm, which provides a better strategy for further minimizing the signaling overhead of the Internet of Vehicles communication system.

Concurrent analysis of electronic and ionic nanopore signals: blockade mean and height

Electronic and ionic current signals detected concurrently by 2D molybdenum disulfide nanopores are analysed in view of detecting (bio)molecules electrophoretically driven through these nanopores. The passage of the molecules, giving rise to translocation events in the nanopores, can be assigned to specific drops in the current signals, the blockades. Such blockades are observed in both the electronic and the ionic signals. In this work, we analyze both signals separately and together by choosing specific features and applying both unsupervised and supervised learning. Two blockade features, the height and the mean, are found to strongly influence the clustering and the classification of the nanopore data, respectively. At the same time, the concurrent learning of both the electronic and ionic signatures enhance the predictability of the learning models, i.e. the nanopore read-out efficiency. The interpretation of these findings provides an intuitive understanding in optimizing the read-out schemes for enhancing the accuracy of nanopore sequencers in view of an error-free biomolecular sensing.

Intent inferring based human-machine game control strategy for spacecraft rendezvous

In this paper, we propose a game control method for a machine-controlled spacecraft to cooperate with a human-controlled spacecraft in near-circular orbit for a rendezvous mission. Inspired by the cooperative game theory, the two-spacecraft rendezvous process is formulated as a cooperative differential game (DG) with a common cost function. A challenging problem is that the intent of the human-controlled spacecraft represented by the weighting matrix in the cost function is not available to the machine-controlled spacecraft. To complete the rendezvous mission optimally, an intent inferring based game control algorithm is developed for the machine-controlled spacecraft. Specifically, an adaptive approach is proposed for the machine-controlled spacecraft to identify the feedback gain matrix of the human-controlled spacecraft online based on the system state alone with the concurrent learning (CL) technique; furthermore, the unknown weighting matrix representing the intent of the human-controlled spacecraft in the cost function is retrieved by an inverse differential game (IDG) method. Accordingly, the control law of the machine-controlled spacecraft is updated in real-time. The control strategies of the spacecraft converge to near the Nash equilibrium. Finally, the simulation result is presented to illustrate the effectiveness of the approach.

Concurrent Learning Robust Adaptive Fault Tolerant Boundary Regulation of Hyperbolic Distributed Parameter Systems.

This article develops a robust adaptive boundary output regulation approach for a class of complex anticollocated hyperbolic partial differential equations subjected to multiplicative unknown faults in both the boundary sensor and actuator. The regulator design is based on the internal model principle, which amounts to stabilize a coupled cascade system, which consists of a finite-dimensional internal model driven by a hyperbolic distributed parameter system (DPS). To this end, a systematic sliding mode equipped with a backstepping approach is developed such that the robust state feedback control can be realized. Moreover, since the available information is a faulty boundary measurement at the right side point, state estimation is required. However, due to the presence of boundary unknown faults, we need to solve an issue of joint fault-state estimation. Restrictive persistent excitation conditions are usually required to guarantee the exact estimation of faults but are unrealistic in practice. To this end, a novel concurrent learning (CL) adaptive observer is proposed so that exponential convergence is obtained. It is the first time that the spirit of CL is introduced to the field of DPSs. Consequently, the observer-based adaptive boundary fault tolerant control scheme is developed, and rigorous theoretical analysis is given such that the exponential output regulation can be achieved. Finally, the effectiveness of the proposed methodology is demonstrated via comparative simulations.

Integral Concurrent Learning Control Lyapunov Functions and High Order Control Barrier Functions and Application to Adaptive Cruise Control

Integral Concurrent Learning Control Lyapunov Functions and High Order Control Barrier Functions and Application to Adaptive Cruise Control

Model-free anti-disturbance tracking control for high-order discrete-time nonlinear system based on concurrent learning extended state observer

The research objective of this paper is to address the tracking control problem of high-order discrete-time nonlinear systems in the presence of completely unknown internal uncertainties, unknown external disturbances, and unknown control input gain. To address this challenge, the paper proposes a high-order discrete-time model-free anti-disturbance tracking control method without relying on prior knowledge of system parameters. The core of the approach is the development of a data-driven concurrent learning extended state observer. The uniqueness of this observer lies in its ability to estimate unknown control input gains without the persistent excitation and ensure the convergence of the estimates. Based on the concurrent learning extended state observer, a high-order discrete-time tracking control law is designed to precisely track the reference signal, ensuring the stability of the nonlinear closed-loop system. The effectiveness of this method was verified by applying simulation verification to the heading tracking control of surface automatic vehicles.

Adaptive control of A class of nonlinear systems with guaranteed parameter estimation: A concurrent learning based approach

AbstractRecent advances in concurrent learning based adaptive controllers have relaxed the persistency of excitation condition required to achieve exponential tracking and parameter estimation error convergence. This was made possible via the use of additional concurrent learning stacks in the parameter estimation algorithm. However, the proposed concurrent learning components, that is, the history stacks, needed to be filled with “selected” values dependent on the actual system states. Therefore, the previously proposed concurrent learning adaptive controllers required the system to be stable initially for a finite time so that the corresponding history stacks can be filled (finite excitation condition). In this work, motivated to remove the finite excitation condition, a novel desired system state based concurrent learning adaptive controller is proposed. In order to remove the system state dependencies in the controller and estimation algorithms, a filtered version of the dynamics and a novel prediction error formulation have been designed. The overall exponential stability, parameter error convergence and boundedness of the system states during closed loop operations are ensured via Lyapunov based arguments. The main advantages of the proposed method are its dependence on the desired system states and the overall stability results that paved the way in removing the need for finite excitation condition. Numerical studies performed on a two link robotic device are also presented to illustrate the feasibility of the proposed method.