Closed-loop Strategy Research Articles

Emerging many-to-one weighted mapping in hippocampus-amygdala network underlies memory formation

Memories are crucial for daily life, yet the network-level organizing principles governing neural representations of experiences remain unknown. Employing dual-site in vivo recording in freely behaving male mice, here we show that hippocampal dorsal CA1 (dCA1) and basolateral amygdala (BLA) utilize distinct coding strategies for novel experiences. A small assembly of BLA neurons emerged active during memory acquisition and persisted through consolidation, whereas most dCA1 neurons were engaged in both processes. Machine learning decoding revealed that dCA1 population spikes predicted BLA assembly firing rate, suggesting that most dCA1 neurons concurrently index an episodic event by rapidly establishing weighted communication with a specific BLA assembly – a process we term “many-to-one weighted mapping.” We also found that dCA1 reactivations preceded BLA assembly activity preferably during elongated and enlarged dCA1 ripples. Using a closed-loop strategy, we demonstrated that suppressing BLA activity after large dCA1 ripples impaired memory. These findings highlight a many-to-one weighted mapping mechanism underlying both the acquisition and consolidation of new memories.

Optimized trajectory tracking control with disturbance resistance for wheeled mobile robot

When unavoidable disturbances exist in practical applications, the unicycle wheeled mobile robot (WMR) with non-holonomic constraint is challenging to be accurately controlled in finite time. An optimized dual closed-loop strategy is proposed in this paper to solve the trajectory tracking control problem of the unicycle WMR. The control strategy with fast time convergence and anti-disturbance properties consists of kinematic and dynamics controllers and an optimization algorithm. The kinematic controller is designed with an improved backstepping method to eliminate the non-holonomic constraints. The robust sliding mode control (SMC) method with fixed-time convergence is used to construct the dynamics controller. The optimization algorithm enhances the performance of the strategy and achieves accurate control. The global convergence and robustness of the strategy are theoretically demonstrated. The effectiveness of the strategy is verified by comparison in simulations.

Rethinking Pan-Sharpening in Closed-Loop Regularization.

It is generally known that pan-sharpening is fundamentally a PAN-guided multispectral (MS) image super-resolution problem that involves learning the nonlinear mapping from low-resolution (LR) to high-resolution (HR) MS images. Since an infinite number of HR-MS images can be downsampled to produce the same corresponding LR-MS image, learning the mapping from LR-MS to HR-MS image is typically ill-posed and the space of the possible pan-sharpening functions can be extremely large, making it difficult to estimate the optimal mapping solution. To address the above issue, we propose a closed-loop scheme that learns the two opposite mapping including the pan-sharpening and its corresponding degradation process simultaneously to regularize the solution space in a single pipeline. More specifically, an invertible neural network (INN) is introduced to perform a bidirectional closed-loop: the forward operation for LR-MS pan-sharpening and the backward operation for learning the corresponding HR-MS image degradation process. In addition, given the vital importance of high-frequency textures for the Pan-sharpened MS images, we further strengthen the INN by designing a specified multiscale high-frequency texture extraction module. Extensive experimental results demonstrate that the proposed algorithm performs favorably against state-of-the-art methods qualitatively and quantitatively with fewer parameters. Ablation studies also verify the effectiveness of the closed-loop mechanism in pan-sharpening. The source code is made publicly available at https://github.com/manman1995/pan-sharpening-Team-zhouman/.

In Vivo Feasibility Study: Evaluating Autonomous Data-Driven Robotic Needle Trajectory Correction in MRI-Guided Transperineal Procedures.

This study addresses the targeting challenges in MRI-guided transperineal needle placement for prostate cancer (PCa) diagnosis and treatment, a procedure where accuracy is crucial for effective outcomes. We introduce a parameter-agnostic trajectory correction approach incorporating a data-driven closed-loop strategy by radial displacement and an FBG-based shape sensing to enable autonomous needle steering. In an animal study designed to emulate clinical complexity and assess MRI compatibility through a PCa mock biopsy procedure, our approach demonstrated a significant improvement in targeting accuracy (p<0.05), with mean target error of only 2.2 ± 1.9 mm on first insertion attempts, without needle reinsertions. To the best of our knowledge, this work represents the first in vivo evaluation of robotic needle steering with FBG-sensor feedback, marking a significant step towards its clinical translation.

Closed-loop theranostic microgels for immune microenvironment modulation and microbiota remodeling in ulcerative colitis

Inflammatory bowel disease (IBD) is characterized by the upregulation of reactive oxygen species (ROS) and dysfunction of gut immune system, and microbiota. The conventional treatments mainly focus on symptom control with medication by overuse of drugs. There is an urgent need to develop a closed-loop strategy that combines in situ monitoring and precise treatment. Herein, we innovatively designed the ‘cluster munition structure’ theranostic microgels to realize the monitoring and therapy for ulcerative colitis (a subtype of IBD). The superoxide anion specific probe (tetraphenylethylene-coelenterazine, TPC) and ROS-responsive nanogels consisting of postbiotics urolithin A (UA) were loaded into alginate and ion-crosslinked to obtain the theranostic microgels. The theranostic microgels could be delivered to the inflammatory site, where the environment-triggered breakup of the microgels and release of the nanogels were achieved in sequence. The TPC-UA group had optimal results in reducing inflammation, repairing colonic epithelial tissue, and remodeling microbiota, leading to inflammation amelioration and recovery of tight junction between the colonic epithelium, and maintenance of gut microbiota. During the recovery process, the local chemiluminescence intensity, which is proportional to the degree of inflammation, was gradually inhibited. The cluster munition of theranostic microgels displayed promising outcomes in monitoring inflammation and precise therapy, and demonstrated the potential for inflammatory disease management.

Closed-loop transfer enables artificial intelligence to yield chemical knowledge.

Artificial intelligence-guided closed-loop experimentation has emerged as a promising method for optimization of objective functions1,2, but the substantial potential of this traditionally black-box approach to uncovering new chemical knowledge has remained largely untapped. Here we report the integration of closed-loop experiments with physics-based feature selection and supervised learning, denoted as closed-loop transfer (CLT), to yield chemical insights in parallel with optimization of objective functions. CLT was used to examine the factors dictating the photostability in solution of light-harvesting donor-acceptor molecules used in a variety of organic electronics applications, and showed fundamental insights including the importance of high-energy regions of the triplet state manifold. This was possible following automated modular synthesis and experimental characterization of only around 1.5% of the theoretical chemical space. This physics-informed model for photostability was strengthened using multiple experimental test sets and validated by tuning the triplet excited-state energy of the solvent to break out of the observed plateau in the closed-loop photostability optimization process. Further applications of CLT to additional materials systems support the generalizability of this strategy for augmenting closed-loop strategies. Broadly, these findings show that combining interpretable supervised learning models and physics-based features with closed-loop discovery processes can rapidly provide fundamental chemical insights.

Secure image communication based on two-layer dynamic feedback encryption and DWT information hiding.

In response to the vulnerability of image encryption techniques to chosen plaintext attacks, this paper proposes a secure image communication scheme based on two-layer dynamic feedback encryption and discrete wavelet transform (DWT) information hiding. The proposed scheme employs a plaintext correlation and intermediate ciphertext feedback mechanism, and combines chaotic systems, bit-level permutation, bilateral diffusion, and dynamic confusion to ensure the security and confidentiality of transmitted images. Firstly, a dynamically chaotic encryption sequence associated with a secure plaintext hash value is generated and utilized for the first round of bit-level permutation, bilateral diffusion, and dynamic confusion, resulting in an intermediate ciphertext image. Similarly, the characteristic values of the intermediate ciphertext image are used to generate dynamically chaotic encryption sequences associated with them. These sequences are then employed for the second round of bit-level permutation, bilateral diffusion, and dynamic confusion to gain the final ciphertext image. The ciphertext image hidden by DWT also provides efficient encryption, higher level of security and robustness to attacks. This technology offers indiscernible secret data insertion, rendering it challenging for assailants to spot or extract concealed information. By combining the proposed dynamic closed-loop feedback secure image encryption scheme based on the 2D-SLMM chaotic system with DWT-based hiding, a comprehensive and robust image encryption approach can be achieved. According to the results of theoretical research and experimental simulation, our encryption scheme has dynamic encryption effect and reliable security performance. The scheme is highly sensitive to key and plaintext, and can effectively resist various common encryption attacks and maintain good robustness. Therefore, our proposed encryption algorithm is an ideal digital image privacy protection technology, which has a wide range of practical application prospects.

A comprehensive analysis and closed-loop control of a non-isolated boost three-port converter for stand-alone PV system

This study critically investigates analysis and control of non-isolated boost three-port DC to DC converter (TPC) forstandalone PV system. The converter is controlled such that regulates flow of power from PV array to load and batteries as storage devices.According to PV power, there are four operating modes of operation of converter. Simple reduced-order dynamic models of the converter in various modes of operation are obtained using state-space averaging and small-signal techniques. In this work, the controllers of the closed-loop scheme are designed and only two controllers are used to achieve output voltage regulation, and to extract maximum power from PV array under different operating conditions. Closed-loop system simulation is studied to verify the operation of converter with the designed controllers in different modes. Transition between modes is presented with solar radiation variation and change of connected loads. Experimental verification of control systems at different modes of operation is investigated. The experimental results show that the controllers can regulate the power flow between TPC three ports and regulate output voltage under PV irradiance variation and load changing. The controller shows good performance measures such as maximum settling time of 0.06 s, maximum steady-state ripples of ±0.8 %, and 99.3 % power efficiency.

Vagus nerve electroneurogram-based detection of acute kainic acid induced seizures.

Seizures produce autonomic symptoms, mainly sympathetic but also parasympathetic in origin. Within this context, the vagus nerve is a key player as it carries information from the different organs to the brain and vice versa. Hence, exploiting vagal neural traffic for seizure detection might be a promising tool to improve the efficacy of closed-loop Vagus Nerve Stimulation. This study developed a VENG detection algorithm that effectively detects seizures by emphasizing the loss of spontaneous rhythmicity associated with respiration in acute intrahippocampal Kainic Acid rat model. Among 20 induced seizures in six anesthetized rats, 13 were detected (sensitivity: 65%, accuracy: 92.86%), with a mean VENG-detection delay of 25.3 ± 13.5 s after EEG-based seizure onset. Despite variations in detection parameters, 7 out of 20 seizures exhibited no ictal VENG modifications and remained undetected. Statistical analysis highlighted a significant difference in Delta, Theta and Beta band evolution between detected and undetected seizures, in addition to variations in the magnitude of HR changes. Binomial logistic regression analysis confirmed that an increase in delta and theta band activity was associated with a decreased likelihood of seizure detection. This results suggest the possibility of distinct seizure spreading patterns between the two groups which may results in differential activation of the autonomic central network. Despite notable progress, limitations, particularly the absence of respiration recording, underscore areas for future exploration and refinement in closed-loop stimulation strategies for epilepsy management. This study constitutes the initial phase of a longitudinal investigation, which will subsequently involve reproducing these experiments in awake conditions with spontaneous recurrent seizures.

Influence of Carboxylic Acid Structure on the Kinetics of Polyurethane Foam Acidolysis to Recycled Polyol.

Closed-loop recycling of plastics is needed to bridge the gap between the material demands imposed by a growing global population and the depletion of nonrenewable petroleum feedstocks. Here, we examine chemical recycling of polyurethane foams (PUFs), the sixth most produced polymer in the world, through PUF acidolysis via dicarboxylic acids (DCAs) to release recyclable polyols. Acidolysis enables recycling of the polyol component of PUFs to high-quality materials, and while the influence of DCA structure on recycled PUF quality has been reported, there are no reports that examine the influence of DCA structure on the kinetics of polyol release. Here, we develop quantitative relationships between DCA structure and PUF acidolysis function for ∼10 different DCA reagents. PUF acidolysis kinetics were quantified with ∼1 s time resolution using the rate of carbon dioxide (CO2) gas generation, which is shown to occur concomitantly with polyol release. Pseudo-zeroth-order rate constants were measured as a function of DCA composition, reaction temperature, and DCA concentration, and apparent activation barriers were extracted. Our findings demonstrate that DCA carboxyl group proximity and phase of transport are descriptors of PUF acidolysis rates, rather than expected descriptors like pK a. DCAs with closer proximity acid groups exhibited faster PUF acidolysis rate constants. Furthermore, a shrinking core mechanism effectively describes the kinetic functional form of the kinetics of PUF acidolysis by DCAs. Measurements of acidolysis kinetics for model PUF (M-PUF) and end-of-life PUF (EOL PUF) confirm the applicability of our analysis to postconsumer materials. This work provides insights into the physical and chemical mechanisms controlling acidolysis, which can facilitate the development of efficient closed-loop PUF chemical recycling schemes.

Twin-in-the-loop state estimation for vehicle dynamics control: Theory and experiments

In vehicle dynamics control, many variables of interest cannot be directly measured, as sensors might be costly, fragile or even not available. Therefore, real-time estimation techniques need to be used. The previous approach suffers from two main drawbacks: (i) the approximations due to model mismatch might jeopardize the performance of the final estimation-based control; (ii) each new estimator requires the calibration from scratch of a dedicated model. In this paper, we propose a twin-in-the-loop scheme, where the ad-hoc model is replaced by an accurate full-fledged simulator of the vehicle, typically available to vehicles manufacturers and suitable for the estimation of any on-board variable, coupled with a compensator within a closed-loop observer scheme. Given the black-box nature of the digital twin, a data-driven methodology for observer tuning is developed, based on Bayesian optimization. The effectiveness of the proposed estimation method for the estimation of vehicle states and forces, as compared to traditional model-based Kalman filtering, is experimentally shown on a dataset collected with a sport car. In summary, the proposed approach achieves, in the most aggressive driving scenarios, an average improvement of 0.5° for the side-slip angle estimation, and of more than 500 N for the front lateral forces estimation.

Recycle of spent LiFePO4 batteries: An eco-friendly closed-loop technique based on less solvent solid state reaction

Lithium iron phosphate (LFP) batteries have become one of the most popular batteries due to their high safety and low cost. However, the lifespan of LFP batteries is limited, making effective recycling processes crucial for environmental protection, resource conservation, and economic benefits. Less solvent solid state reaction (LSR) is reactions of solids with the help of a little solvent, which has advantage of almost 100% conversion of reactants and no waste generation. Herein, LFP (S-LFP) from spent batteries was first entirely decomposed to produce FePO4 and LiH2PO4 in H3PO4-H2O2 leaching systems using the LSR method. Then, battery-grade Li2CO3 was prepared by adding CaCl2 and Na2CO3 to LiH2PO4. As a result, the battery of regenerated LiFePO4 (R-LFP) using recycled FePO4 and Li2CO3 exhibits superior electrochemical performance compared to those with unused LiFePO4, including a higher discharge specific capacity (140.7 mAhg−1 at 0.1C) and excellent cycle life, with a capacity retention of 98.6% over 500cycles at 1.0C. The LSR method provides a green and sustainable closed-loop recovery strategy for S-LFP cathode materials, which reduces the number of processing steps and chemical consumption, promotes resource conservation and environmental protection, and facilitates the sustainable industrial development of S-LFP batteries.

Closed-Loop Direct Upcycling of Spent Ni-Rich Layered Cathodes into High-Voltage Cathode Materials.

Facing the resource and environmental pressures brought by the retiring wave of lithium-ion batteries (LIBs), direct recycling methods are considered to be the next generation's solution. However, the contradiction between limited battery life and the demand for rapidly iterating technology forces the direct recovery paradigm to shift toward "direct upcycling." Herein, a closed-loop direct upcycling strategy that converts waste current collector debris into dopants is proposed, and a highly inclusive eutectic molten salt system is utilized to repair structural defects in degraded polycrystalline LiNi0.83Co0.12Mn0.05O2 cathodes while achieving single-crystallization transformation and introducing Al/Cu dual-doping. Upcycled materials can effectively overcome the two key challenges at high voltages: strain accumulation and lattice oxygen evolution. It exhibits comprehensive electrochemical performance far superior to commercial materials at 4.6V, especially its fast charging capability at 15C, and an impressive 91.1% capacity retention after 200 cycles in a 1.2Ah pouch cell. Importantly, this approach demonstrates broad applicability to various spent layered cathodes, particularly showcasing its value in the recycling of mixed spent cathodes. This work effectively bridges the gap between waste management and material performance enhancement, offering a sustainable path for the recycling of spent LIBs and the production of next-generation high-voltage cathodes.

SUIVI DE LA QUALITÉ DE PUISSANCE MAXIMALE D'UN GÉNÉRATEUR D'INDUCTION À DOUBLE ALIMENTATION BASÉ SUR UN CONTRÔLEUR DE RÉSEAU NEURONAL ARTIFICIEL POUR SYSTÈME DE CONVERSION D'ÉNERGIE ÉOLIENNE

Renewable energy sources are playing a crucial role in satisfying the upcoming energy source needs for the world. The current power system is power electronics converter based, with several non-linear loads and spotted generations of renewable energy sources, resulting in many power quality issues. Most existing research analyzed MATLAB simulations and presented a high Total Harmonics Distortion (THD) level. This research work proposed an artificial neural network (ANN) control technique for a doubly fed induction generator (DFIG) based wind energy conversion systems (WECSs). To decrease chattering phenomena during the excitation arrangement, an advanced controller works for adaptive modification of the irregular power gain, even preserving the strength of the closed-loop scheme. The proposed PI controller one step forward improves reliability and tracks maximum voltage from the pulse width modulation rectifier. At primary, the modeling of the DFIG was presented. Then, using the proposed ANN controller, the rotor magnitude was tuned to recognize vector control of active and reactive power. The converter intends to activate at unity power factor and provide input currents with adequate harmonic content. The interface between the power’s electronic converter and the DFIG pulls out the most real power potential. The proposed prototype hardware model and simulation results are verified.

A pH-sensitive closed-loop nanomachine to control hyperexcitability at the single neuron level

Epilepsy affects 1% of the general population and 30% of patients are resistant to antiepileptic drugs. Although optogenetics is an efficient antiepileptic strategy, the difficulty of illuminating deep brain areas poses translational challenges. Thus, the search of alternative light sources is strongly needed. Here, we develop pH-sensitive inhibitory luminopsin (pHIL), a closed-loop chemo-optogenetic nanomachine composed of a luciferase-based light generator, a fluorescent sensor of intracellular pH (E2GFP), and an optogenetic actuator (halorhodopsin) for silencing neuronal activity. Stimulated by coelenterazine, pHIL experiences bioluminescence resonance energy transfer between luciferase and E2GFP which, under conditions of acidic pH, activates halorhodopsin. In primary neurons, pHIL senses the intracellular pH drop associated with hyperactivity and optogenetically aborts paroxysmal activity elicited by the administration of convulsants. The expression of pHIL in hippocampal pyramidal neurons is effective in decreasing duration and increasing latency of pilocarpine-induced tonic-clonic seizures upon in vivo coelenterazine administration, without affecting higher brain functions. The same treatment is effective in markedly decreasing seizure manifestations in a murine model of genetic epilepsy. The results indicate that pHIL represents a potentially promising closed-loop chemo-optogenetic strategy to treat drug-refractory epilepsy.

Toward the Circular Economy in the Aquaculture Sector: Bibliometric, Network and Content Analyses

This paper offers an overview of circular economy strategies applied to the aquaculture sector. The growing challenges imposed on the sector by the strategies of the Green Deal impose new growth strategies in the name of sustainability. The scalability of these strategies is increasingly hampered by regulatory voids and by the absence of a universally accepted assessment method for measuring the impacts of current aquaculture systems. More than ever, a review of knowledge in the circular economy field is required to comprehend where the aquaculture sector is heading, and in order to make the required transition. The present review proposes a bibliometric analysis, a network analysis and a content analysis, which highlight a very new and expanding field of research. The studies were firstly analyzed from a micro (animal metabolism) to a macro perspective (policies, markets and society), emphasizing where research is still lacking. Furthermore, a second level of classification concerns the type of circularity approach proposed for the aquaculture system, which can be divided into open-loop or closed-loop strategies. Regarding the open-loop-related studies, the focus of the evaluation is devoted to the different bioeconomic values of the circularity strategies proposed for the biological flows entering and exiting the aquaculture system. The literature review offered insights into the identification of research threads that are developing around the aquaculture sector.

Mechanics and thermal analyses of microfluidic nerve-cooler system

Recent advances in microelectronics and biomedical technology has led to capabilities for integrating programmable cooling mechanisms into bioelectronic devices for pain management and other important applications in human health. However, achieving localized and precise targeted cooling remains a challenge due to the influence of tissue mechanics during device placement/operation, viscous effects in the flow of coolants, and critical physical parameters that locally affect tissue temperature and mechanical responses. Recent studies demonstrate that bioelectronic devices can be equipped with microfluidic structures designed to support phase-change cooling mechanisms, with cooling power adjustable by control of fluid flow rates. When operated in closed-loop feedback schemes based on measurements of temperature at the tissue interface, these platforms can achieve precise temperature control of regions of peripheral nerves involved in pain signaling. Establishing a theoretical model to understand the effects of these devices on the underlying soft and deformable tissues, along with microfluidic deformations that can alter the heat transfer cooling process in viscous flow, is critical for optimized design and operation. To address this, a theoretical model is developed to describe the influence of remote strain in the tissue and to quantify the spatial temperature distribution of tissue cooled by fluid phase change in deformable microfluidic channels. A scaling law is derived to quantify the steady-state temperature distribution in the tissue under physiologically relevant mechanical loads, fluid viscosity, flow rates, and thermal conductivities, enabling the prediction of liquid and gas flux based on expected temperature changes and saturated vapor pressure in the deformed tissue and microchannel. These findings reveal that within a reasonable physiological range, the influence of fluid viscosity on temperature changes can be neglected, and the ratio of fluid to tissue thermal conductivity minimally impacts the temperature change at relatively high flow rates. Additionally, the model suggests a limit to tissue cooling for a given fluid, which may not necessarily increase with higher fluid volumes.

A digital twin for advancing battery fast charging based on a Bayesian optimization-based method

The optimization of fast charging protocols is regarded as a key technology for promoting the use of electric vehicles because it can balance battery charging time and health. Optimizing such charging protocols through electrochemical models is a mainstream approach and can demonstrate high accuracy in simulating battery characteristics. However, the high complexity of the corresponding models makes the calculation and optimization processes difficult to perform in real time. To address this problem, this study presents an online closed-loop fast charging strategy optimization scheme that combines a battery digital twin model (BDTM) and Bayesian optimization (BO). Because the BO can quickly find a near-optimal solution in a few iterations, the optimization time is shortened, thereby reducing the computational burden incurred by highly complex models. To further improve the efficiency of the online optimization, a parallel multichannel optimization strategy is proposed, which further accelerates the process of finding the optimal protocol by simultaneously executing multiple optimization algorithms. Additionally, we analysed the effects of ageing parameters and ambient temperature on the optimization results. The results show that BO can obtain relatively stable optimization and has the highest efficiency when using four parallel channels. Specifically, the number of convergence evaluations for single-channel optimization is 2.5 times that of the four-channel optimization. Compared with the reference charging protocol, charging using the protocol optimized based on the Doyle-Fuller-Newman (DFN) model can effectively suppress the loss of lithium inventory (LLI) by up to 4.76 % within 90 cycles.

A mild and efficient closed-loop recycling strategy for spent lithium-ion battery

As lithium metal resource supply and demand stabilize and prices decrease, the efficient recovery of valuable metals other than lithium from spent lithium-ion batteries is receiving increasing attention. Currently, challenges remain in the selective lithium recovery efficiency and the high cost of regenerating valuable metal slag after lithium extraction, particularly for spent ternary cathode materials. To address these challenges, this study introduces a closed-loop recovery process for spent ternary cathode materials, employing sulfur-assisted roasting to achieve efficient lithium extraction and high-value direct regeneration of ternary leaching residues. At moderate temperatures (500 ℃), LiNixCoyMn1−x-yO2 (NCM) materials undergo a directional transformation of lithium to Li2SO4 in synergy with sulfur and oxygen, achieving a lithium leaching extraction rate of 98.91 %. Additionally, the relatively mild reaction conditions preserve the secondary spherical morphology and uniform distribution of NiCoMn-based oxide residue without introducing adverse impurities, ensuring the successful regeneration of high-value NCM cathode materials (R-NCM). The R-NCM material exhibits good discharge capacity (144.3 mA·h/g at 1 C) and relatively stable cycling performance, with a capacity retention rate of 80 % after 150 cycles. This work provides a viable pathway for the efficient and environmental-friendly pyrometallurgical closed-loop recovery of spent lithium-ion batteries.

Reinforcement learning for closed-loop regulation of cardiovascular system with vagus nerve stimulation: a computational study

Objective. Vagus nerve stimulation (VNS) is being investigated as a potential therapy for cardiovascular diseases including heart failure, cardiac arrhythmia, and hypertension. The lack of a systematic approach for controlling and tuning the VNS parameters poses a significant challenge. Closed-loop VNS strategies combined with artificial intelligence (AI) approaches offer a framework for systematically learning and adapting the optimal stimulation parameters. In this study, we presented an interactive AI framework using reinforcement learning (RL) for automated data-driven design of closed-loop VNS control systems in a computational study. Approach. Multiple simulation environments with a standard application programming interface were developed to facilitate the design and evaluation of the automated data-driven closed-loop VNS control systems. These environments simulate the hemodynamic response to multi-location VNS using biophysics-based computational models of healthy and hypertensive rat cardiovascular systems in resting and exercise states. We designed and implemented the RL-based closed-loop VNS control frameworks in the context of controlling the heart rate and the mean arterial pressure for a set point tracking task. Our experimental design included two approaches; a general policy using deep RL algorithms and a sample-efficient adaptive policy using probabilistic inference for learning and control. Main results. Our simulation results demonstrated the capabilities of the closed-loop RL-based approaches to learn optimal VNS control policies and to adapt to variations in the target set points and the underlying dynamics of the cardiovascular system. Our findings highlighted the trade-off between sample-efficiency and generalizability, providing insights for proper algorithm selection. Finally, we demonstrated that transfer learning improves the sample efficiency of deep RL algorithms allowing the development of more efficient and personalized closed-loop VNS systems. Significance. We demonstrated the capability of RL-based closed-loop VNS systems. Our approach provided a systematic adaptable framework for learning control strategies without requiring prior knowledge about the underlying dynamics.