Bipedal locomotion control is essential for humanoid robots to navigate complex, human-centric environments. While optimization-based control designs are popular for integrating sophisticated models of humanoid robots, they often require labor-intensive manual tuning. In this work, we address the challenges of parameter selection in bipedal locomotion control using DiffTune, a model-based autotuning method that leverages differential programming for efficient parameter learning. A major difficulty lies in balancing model fidelity with differentiability. We address this difficulty using a low-fidelity model for differentiability, enhanced by a Ground Reaction Force-and-Moment Network (GRFM-Net) to capture discrepancies between MPC commands and actual control effects. We validate the parameters learned by DiffTune with GRFM-Net in hardware experiments, which demonstrates the parameters’ optimality in a multi-objective setting compared with baseline parameters, reducing the total loss by up to 40.5% compared with the expert-tuned parameters. The results confirm the GRFM-Net’s effectiveness in mitigating the sim-to-real gap, improving the transferability of simulation-learned parameters to real hardware.

For the cascaded planning and control modules implemented for robot navigation, the frequency gap between the planner and controller has received limited attention. In this study, we introduce a novel B-spline parameterized optimization-based planner (BSPOP) designed to address the frequency gap challenge with limited onboard computational power in robots. The proposed planner generates continuous-time control inputs for low-level controllers running at arbitrary frequencies to track. Furthermore, when considering the convex control action sets, BSPOP uses the convex hull property to automatically constrain the continuous-time control inputs within the convex set. Consequently, compared with the discrete-time optimization-based planners, BSPOP reduces the number of decision variables and inequality constraints, which improves computational efficiency as a byproduct. Simulation results demonstrate that our approach can achieve a comparable planning performance to the high-frequency baseline optimization-based planners while demanding less computational power. Both simulation and experiment results show that the proposed method performs better in planning compared with baseline planners in the same frequency.

This paper introduces a novel numerical approach to achieving smooth lane-change trajectories in autonomous driving scenarios. Our trajectory generation approach leverages particle swarm optimization (PSO) techniques, incorporating Neural Network (NN) predictions for trajectory refinement. The generation of smooth and dynamically feasible trajectories for the lane change maneuver is facilitated by combining polynomial curve fitting with particle propagation, which can account for vehicle dynamics. The proposed planning algorithm is capable of determining feasible trajectories with real-time computation capability. We conduct comparative analyses with two baseline methods for lane changing, involving analytic solutions and heuristic techniques in numerical simulations. The simulation results validate the efficacy and effectiveness of our proposed approach.

Abstract Advances in deep learning have revolutionized cyber‐physical applications, including the development of autonomous vehicles. However, real‐world collisions involving autonomous control of vehicles have raised significant safety concerns regarding the use of deep neural networks (DNNs) in safety‐critical tasks, particularly perception. The inherent unverifiability of DNNs poses a key challenge in ensuring their safe and reliable operation. In this work, we propose perception simplex ( ), a fault‐tolerant application architecture designed for obstacle detection and collision avoidance. We analyse an existing LiDAR‐based classical obstacle detection algorithm to establish strict bounds on its capabilities and limitations. Such analysis and verification have not been possible for deep learning‐based perception systems yet. By employing verifiable obstacle detection algorithms, identifies obstacle existence detection faults in the output of unverifiable DNN‐based object detectors. When faults with potential collision risks are detected, appropriate corrective actions are initiated. Through extensive analysis and software‐in‐the‐loop simulations, we demonstrate that provides deterministic fault tolerance against obstacle existence detection faults, establishing a robust safety guarantee.

This article studies social system inference from a single noisy trajectory of public evolving opinions, wherein observation noise leads to the statistical dependence of samples on time and coordinates. We first propose a cyber-social system that comprises individuals in a social network and a set of information sources in a cyber layer, whose opinion dynamics explicitly takes the asymmetric cognitive bias including confirmation bias and negativity bias and the process noise into account. Based on the proposed cyber-social model, we then study the sample complexity of least-square auto-regressive model estimation, which governs the length of a single observed trajectory that is sufficient for the identified model to achieve the prescribed levels of accuracy and confidence (PAC). Building on the identified social model, we then investigate social inference, with a particular focus on the weighted network topology and the model parameters of asymmetric cognitive bias. Finally, the theoretical results and the effectiveness of the proposed inference framework are validated by the U.S. Senate Member Ideology data.

This article investigates the cost function learning in social information networks, wherein human memory and cognitive bias are explicitly taken into account. We first propose a model for social information-diffusion dynamics, with a focus on the systematic modeling of asymmetric cognitive bias represented by confirmation bias and novelty bias. Building on the dynamics model, we then propose the M3IRL—a memorized model and maximum-entropy-based inverse reinforcement learning—for learning cost functions. Compared with the existing model-free IRLs, the characteristics of M3IRL are significantly different here: no dependence on the Markov decision process principle, the need for only a single finite-time trajectory sample, and bounded decision variables. Finally, the effectiveness of the proposed social information-diffusion model and the M3IRL algorithm is validated by the online social media data.

This article examines how people respond to the presence of a flying robot under various operating conditions using traditional human physiological measures and a novel head movement measurement. A central issue to the integration of flying robotic systems into human-populated environments is how to improve the level of comfort and safety for people around them. Traditional motion control algorithms in robotics tend to focus on the actual safety of collision avoidance. However, people's perceived safety is not necessarily equivalent to the actual safety of the vehicle. Therefore flight control systems must account for people's perception of safety beyond the actual safety of the aerial vehicles in order to allow for successful interaction between humans and the unmanned aerial vehicles (UAVs). Across three experiments participants passively observed quadrotor trajectories in a simulated virtual reality environment. Quadrotor flight characteristics were manipulated in terms of speed, altitude, and audibility to examine their effect on physiological arousal and head motion kinematics. Physiological arousal was greater when the quadrotor was flying with the audio on than off, and at eye-height than overhead, and decreased over repeated exposure. In addition, head acceleration away from the UAVs indicating defensive behavior was stronger for faster speed and audible UAVs. These data suggest head acceleration can serve as a new index specific for measuring perceived safety. Applications intended for human comfort need to consider constraints from specific measures of perceived safety in addition to traditional measures of general physiological arousal.

The performance of robots in high-level tasks depends on the quality of their lower level controller, which requires fine-tuning. However, the intrinsically nonlinear dynamics and controllers make tuning a challenging task when it is done by hand. In this article, we present DiffTune, a novel, gradient-based automatic tuning framework. We formulate the controller tuning as a parameter optimization problem. Our method unrolls the dynamical system and controller as a computational graph and updates the controller parameters through gradient-based optimization. The gradient is obtained using sensitivity propagation, which is the only method for gradient computation when tuning for a physical system instead of its simulated counterpart. Furthermore, we use$\mathcal {L}_{1}$adaptive control to compensate for the uncertainties (that unavoidably exist in a physical system) such that the gradient is not biased by the unmodeled uncertainties. We validate the DiffTune on a Dubin's car and a quadrotor in challenging simulation environments. In comparison with state-of-the-art autotuning methods, DiffTune achieves the best performance in a more efficient manner owing to its effective usage of the first-order information of the system. Experiments on tuning a nonlinear controller for quadrotor show promising results, where DiffTune achieves 3.5× tracking error reduction on an aggressive trajectory in only ten trials over a 12-D controller parameter space.

Classifying and segmenting patterns from a limited number of examples is a significant challenge in remote sensing and earth observation due to the difficulty in acquiring accurately labeled data in large quantities. Previous studies have shown that meta-learning, which involves episodic training on query and support sets, is a promising approach. However, there has been little attention paid to direct fine-tuning techniques. This paper repurposes contrastive learning as a pre-training method for few-shot learning for classification and semantic segmentation tasks. Specifically, we introduce a generator-based contrastive learning framework (GenCo) that pre-trains backbones and simultaneously explores variants of feature samples. In fine-tuning, the auxiliary generator can be used to enrich limited labeled data samples in feature space. We demonstrate the effectiveness of our method in improving few-shot learning performance on two key remote sensing datasets: Agriculture-Vision and EuroSAT. Empirically, our approach outperforms purely supervised training on the nearly 95,000 images in Agriculture-Vision for both classification and semantic segmentation tasks. Similarly, the proposed few-shot method achieves better results on the land-cover classification task on EuroSAT compared to the results obtained from fully supervised model training on the dataset.

Contrastive learning models based on Siamese structure have demonstrated remarkable performance in self-supervised learning. Such a success of contrastive learning relies on two conditions, a sufficient number of positive pairs and adequate variations between them. If the conditions are not met, these frameworks will lack semantic contrast and be fragile on overfitting. To address these two issues, we propose Hallucinator that could efficiently generate additional positive samples for further contrast. The Hallucinator is differentiable and creates new data in the feature space. Thus, it is optimized directly with the pre-training task and introduces nearly negligible computation. Moreover, we reduce the mutual information of hallucinated pairs and smooth them through non-linear operations. This process helps avoid over-confident contrastive learning models during the training and achieves more transformation-invariant feature embeddings. Remarkably, we empirically prove that the proposed Hallucinator generalizes well to various contrastive learning models, including MoCoV1&V2, SimCLR and SimSiam. Under the linear classification protocol, a stable accuracy gain is achieved, ranging from 0.3% to 3.0% on CIFAR10&100, Tiny ImageNet, STL-10 and ImageNet. The improvement is also observed in transferring pre-train encoders to the downstream tasks, including object detection and segmentation.

Crop management has a significant impact on crop yield, economic profit, and the environment. Although management guidelines exist, finding the optimal management practices is challenging. Previous work used reinforcement learning (RL) and crop simulators to solve the problem, but the trained policies either have limited performance or are not deployable in the real world. In this paper, we present an intelligent crop management system that optimizes nitrogen fertilization and irrigation simultaneously via RL, imitation learning (IL), and crop simulations using the Decision Support System for Agrotechnology Transfer (DSSAT). We first use deep RL, in particular, deep Q-network, to train management policies that require a large number of state variables from the simulator as observations (denoted as full observation). We then invoke IL to train management policies that only need a few state variables that can be easily obtained or measured in the real world (denoted as partial observation) by mimicking the actions of the RL policies trained under full observation. Simulation experiments using the maize crop in Florida (US) and Zaragoza (Spain) demonstrate that the trained policies from both RL and IL techniques achieved more than 45\% improvement in economic profit while causing less environmental impact compared with a baseline method. Most importantly, the IL-trained management policies are directly deployable in the real world as they use readily available information.

Over the past few years, there has been growing interest in developing larger and deeper neural networks, including deep generative models like generative adversarial networks (GANs). However, GANs typically come with high computational complexity, leading researchers to explore methods for reducing the training and inference costs. One such approach gaining popularity in supervised learning is dynamic sparse training (DST), which maintains good performance while enjoying excellent training efficiency. Despite its potential benefits, applying DST to GANs presents challenges due to the adversarial nature of the training process. In this paper, we propose a novel metric called the balance ratio (BR) to study the balance between the sparse generator and discriminator. We also introduce a new method called balanced dynamic sparse training (ADAPT), which seeks to control the BR during GAN training to achieve a good trade-off between performance and computational cost. Our proposed method shows promising results on multiple datasets, demonstrating its effectiveness.

This article proposes a novel extension of the Simplex architecture with model switching and model learning to achieve safe velocity regulation of self-driving vehicles in dynamic and unforeseen environments. To guarantee the reliability of autonomous vehicles, an ℒ 1 adaptive controller that compensates for uncertainties and disturbances is employed by the Simplex architecture as a verified high-assurance controller (HAC) to tolerate concurrent software and physical failures. Meanwhile, the safe switching controller is incorporated into the HAC for safe velocity regulation in the dynamic (prepared) environments, through the integration of the traction control system and anti-lock braking system. Due to the high dependence of vehicle dynamics on the driving environments, the HAC leverages the finite-time model learning to timely learn and update the vehicle model for ℒ 1 adaptive controller, when any deviation from the safety envelope or the uncertainty measurement threshold occurs in the unforeseen driving environments. With the integration of ℒ 1 adaptive controller, safe switching controller and finite-time model learning, the vehicle’s angular and longitudinal velocities can asymptotically track the provided references in the dynamic and unforeseen driving environments, while the wheel slips are restricted to safety envelopes to prevent slipping and sliding. Finally, the effectiveness of the proposed Simplex architecture for safe velocity regulation is validated by the AutoRally platform.

This paper introduces an$L$1adaptive control aug-mentation for geometric tracking control of quadrotors. In the proposed design, the$L$1augmentation handles nonlinear (time-and state-dependent) uncertainties in the quadrotor dynamics without assuming or enforcing parametric structures, while the baseline geometric controller achieves stabilization of the known nonlinear model of the system dynamics. The$L$1augmentation applies to both the rotational and the translational dynamics. Experimental results demonstrate that the augmented geomet-ric controller shows consistent and (on average five times) smaller trajectory tracking errors compared with the geometric controller alone when tested for different trajectories and under various types of uncertainties/disturbances.

Perception of obstacles remains a critical safety concern for autonomous vehicles. Real-world collisions have shown that the autonomy faults leading to fatal collisions originate from obstacle existence detection. Open source autonomous driving implementations show a perception pipeline with complex interdependent Deep Neural Networks. These networks are not fully verifiable, making them unsuitable for safety-critical tasks. In this work, we present a safety verification of an existing LiDAR based classical obstacle detection algorithm. We establish strict bounds on the capabilities of this obstacle detection algorithm. Given safety standards, such bounds allow for determining LiDAR sensor properties that would reliably satisfy the standards. Such analysis has as yet been unattainable for neural network based perception systems. We provide a rigorous analysis of the obstacle detection system with empirical results based on real-world sensor data.

Early, precise detection of nutrient deficiency stress (NDS) has key economic as well as environmental impact; precision application of chemicals in place of blanket application reduces operational costs for the growers while reducing the amount of chemicals which may enter the environment unnecessarily. Furthermore, earlier treatment reduces the amount of loss and therefore boosts crop production during a given season. With this in mind, we collect sequences of high-resolution aerial imagery and construct semantic segmentation models to detect and predict NDS across the field. Our work sits at the intersection of agriculture, remote sensing, and modern computer vision and deep learning. First, we establish a baseline for full-field detection of NDS and quantify the impact of pretraining, backbone architecture, input representation, and sampling strategy. We then quantify the amount of information available at different points in the season by building a single-timestamp model based on a UNet. Next, we construct our proposed spatiotemporal architecture, which combines a UNet with a convolutional LSTM layer, to accurately detect regions of the field showing NDS; this approach has an impressive IOU score of 0.53. Finally, we show that this architecture can be trained to predict regions of the field which are expected to show NDS in a later flight -- potentially more than three weeks in the future -- maintaining an IOU score of 0.47-0.51 depending on how far in advance the prediction is made. We will also release a dataset which we believe will benefit the computer vision, remote sensing, as well as agriculture fields. This work contributes to the recent developments in deep learning for remote sensing and agriculture, while addressing a key social challenge with implications for economics and sustainability.

The success of deep learning in visual recognition tasks has driven advancements in multiple fields of research. Particularly, increasing attention has been drawn towards its application in agriculture. Nevertheless, while visual pattern recognition on farmlands carries enormous economic values, little progress has been made to merge computer vision and crop sciences due to the lack of suitable agricultural image datasets. Meanwhile, problems in agriculture also pose new challenges in computer vision. For example, semantic segmentation of aerial farmland images requires inference over extremely large-size images with extreme annotation sparsity. These challenges are not present in most of the common object datasets, and we show that they are more challenging than many other aerial image datasets. To encourage research in computer vision for agriculture, we present Agriculture-Vision: a large-scale aerial farmland image dataset for semantic segmentation of agricultural patterns. We collected 94,986 high-quality aerial images from 3,432 farmlands across the US, where each image consists of RGB and Near-infrared (NIR) channels with resolution as high as 10 cm per pixel. We annotate nine types of field anomaly patterns that are most important to farmers. As a pilot study of aerial agricultural semantic segmentation, we perform comprehensive experiments using popular semantic segmentation models; we also propose an effective model designed for aerial agricultural pattern recognition. Our experiments demonstrate several challenges Agriculture-Vision poses to both the computer vision and agriculture communities. Future versions of this dataset will include even more aerial images, anomaly patterns and image channels.

This paper presents a multirotor control architecture, where Model Predictive Path Integral Control (MPPI) and ℒ1adaptive control are combined to achieve both fast model predictive trajectory planning and robust trajectory tracking. MPPI provides a framework to solve nonlinear MPC with complex cost functions in real-time. However, it often lacks robustness, especially when the simulated dynamics are different from the true dynamics. We show that the ℒ1adaptive controller robustifies the architecture, allowing the overall system to behave similar to the nominal system simulated with MPPI. The architecture is validated in a simulated multirotor racing environment.

This paper introduces the f-divergence variational inference (f-VI) that generalizes variational inference to all f-divergences. Initiated from minimizing a crafty surrogate f-divergence that shares the statistical consistency with the f-divergence, the f-VI framework not only unifies a number of existing VI methods, e.g. Kullback–Leibler VI, Renyi's alpha-VI, and chi-VI, but offers a standardized toolkit for VI subject to arbitrary divergences from f-divergence family. A general f-variational bound is derived and provides a sandwich estimate of marginal likelihood (or evidence). The development of the f-VI unfolds with a stochastic optimization scheme that utilizes the reparameterization trick, importance weighting and Monte Carlo approximation; a mean-field approximation scheme that generalizes the well-known coordinate ascent variational inference (CAVI) is also proposed for f-VI. Empirical examples, including variational autoencoders and Bayesian neural networks, are provided to demonstrate the effectiveness and the wide applicability of f-VI.

Multi-spectral sensors consisting of a standard (visible-light) camera and a long-wave infrared camera can simultaneously provide both visible and thermal images. Since thermal images are independent from environmental illumination, they can help to overcome certain limitations of standard cameras under complicated illumination conditions. However, due to the difference in the information source of the two types of cameras, their images usually share very low texture similarity. Hence, traditional texture-based feature matching methods cannot be directly applied to obtain stereo correspondences. To tackle this problem, a multi-spectral visual odometry method without explicit stereo matching is proposed in this paper. Bundle adjustment of multi-view stereo is performed on the visible and the thermal images using direct image alignment. Scale drift can be avoided by additional temporal observations of map points with the fixed-baseline stereo. Experimental results indicate that the proposed method can provide accurate visual odometry results with recovered metric scale. Moreover, the proposed method can also provide a metric 3D reconstruction in semi-dense density with multi-spectral information, which is not available from existing multi-spectral methods.

In this article, we present a preliminary motion planning framework for a cyber-physical system consisting of a human and a flying robot in vicinity. The motion planning of the flying robot takes into account the human’s safety perception. We aim to determine a parametric model for the human’s safety perception based on test data. We use virtual reality as a safe testing environment to collect safety perception data reflected on galvanic skin response (GSR) from the test subjects experiencing a flying robot in their vicinity. The GSR signal contains both meaningful information driven by the interaction with the robot and also disturbances from unknown factors. To address the issue, we use two parametric models to approximate the GSR data: (1) a function of the robot’s position and velocity and (2) a random distribution. Intuitively, we need to choose the more likely model given the data. When GSR is statistically independent of the flying robot, then the random distribution should be selected instead of the function of the robot’s position and velocity. We implement the intuitive idea under the framework of hidden Markov model (HMM) estimation. As a result, the proposed HMM-based model improves the likelihood compared to the Gaussian noise model, which does not make a distinction between relevant and irrelevant samples due to unknown factors. We also present a numerical optimal path planning method that considers the safety perception model while ensuring spatial separation from the obstacle despite the time discretization. Optimal paths generated using the proposed model result in a reasonably safe distance from the human. In contrast, the trajectories generated by the standard regression model with the Gaussian noise assumption, without consideration of unknown factors, have undesirable shapes.

Kim and Winfree have synthesized a well-known network of transcriptional oscillators in vitro using a modular architecture of synthetic gene analogues and a few enzymes that, in turn, could be used to drive a variety of downstream circuits and nanodevices. However, these oscillators are sensitive to initial conditions and downstream load processes. Furthermore, the oscillations are not sustained since the inherently closed design suffers from enzyme deactivation, NTP fuel exhaustion, and waste product build up. Recently, we had shown that a partially open architecture in which a continuous-time L1adaptive controller, implemented inside an in silico computer that resides outside the wet-lab apparatus, can ensure sustained tunable oscillations in two specific designs of the Kim-Winfree oscillator networks. Here, we present its discrete-time version. As before, we consider two broad cases of operation: (1) the oscillator network operating in isolation, and (2) the oscillator network driving a DNA tweezer subject to a variable load. In both scenarios, our simulation results show a significant improvement in the tunability and robustness of these oscillator networks. Our approach can be easily adopted to improve the loading capacity of a wide range of synthetic biological devices.

As the complexity of Cyber-Physical Systems (CPS) increases, it becomes increasingly challenging to ensure CPS reliability, especially in the presence of software and/or physical failures. The Simplex architecture is shown to be an efficient tool to address software failures in such systems. When physical failures exist, however, Simplex may not function correctly because physical failures could change system dynamics and the original Simplex design may not work for the new faulty system. To address concurrent software and physical failures, this article presents the RSimplex architecture, which integrates Robust Fault-Tolerant Control (RFTC) techniques into the Simplex architecture. It includes the uncertainty monitor, the High-Performance Controller (HPC), the Robust High-Assurance Controller (RHAC), and the decision logic that triggers the switch of the controllers. Based on the output of the uncertainty monitor, we introduce a monitor-based switching rule in the decision logic in addition to the traditional envelope-based rule. The RHAC is designed based on RFTCs. We show that RSimplex can efficiently handle a class of software and physical failures.

This paper tackles the problem of coordinated vision-based tracking of a ground target by a fleet of multiple UAVs that exchange information over a supporting time-varying network. The objective of this work is to formulate decentralized control algorithms that enable multiple vehicles to follow a target while coordinating their phase separation. A typical scenario involves multiple aerial surveillance UAVs which are required to monitor a moving ground object (target tracking), while maintaining a desired inter-vehicle separation (coordination). To solve the tracking problem, the yaw rate of each vehicle is used as control input, while the ground speeds are adjusted to achieve coordination. It is assumed that the UAVs are equipped with an internal autopilot, which is able to track yaw rate and ground speed commands. The performance of the coordinated vision-based tracking algorithm is evaluated as a function of target's velocity, tracking performance of the onboard autopilot, and the quality of service of the communication network.

This paper addresses the problem of time-coordination of a team of cooperating multirotor unmanned aerial vehicles that exchange information over a supporting time-varying network. A distributed control law is developed to ensure that the vehicles meet the desired temporal assignments of the mission, while flying along predefined collision-free paths, even in the presence of faulty communication networks, temporary link losses, and switching topologies. In this paper, the coordination task is solved by reaching consensus on a suitably defined coordination state. Conditions are derived under which the coordination errors converge to a neighborhood of zero. Simulation and flight test results are presented to validate the theoretical findings. Note to Practitioners-This paper presents an approach which enables a fleet of multirotor UAVs to follow a set of desired trajectories and coordinate along them, thus satisfying specific spatial and temporal assignments. The proposed solution can be employed in applications in which multiple vehicles are tasked to execute cooperative, collision-free maneuvers, and accomplish a common goal in a safely manner. An example is sequential monitoring, in which the UAVs have to visit and monitor a set of points of interest, while maintaining a desired temporal separation between each other. In this paper, we also simulate a scenario in which the vehicles, positioned in a square room, are required to exchange position with each other. It is shown that the proposed control algorithm not only ensures that the UAVs arrive at the final destinations at the same time, but also guarantees safety, i.e., the vehicles avoid collision with each other at all times.

In this paper, a neuroadaptive control framework for continuous- and discrete-time nonlinear uncertain dynamical systems with input-to-state stable internal dynamics is developed. The proposed framework is Lyapunov based and unlike standard neural network (NN) controllers guaranteeing ultimate boundedness, the framework guarantees partial asymptotic stability of the closed-loop system, that is, asymptotic stability with respect to part of the closed-loop system states associated with the system plant states. The neuroadaptive controllers are constructed without requiring explicit knowledge of the system dynamics other than the assumption that the plant dynamics are continuously differentiable and that the approximation error of uncertain system nonlinearities lie in a small gain-type norm bounded conic sector. This allows us to merge robust control synthesis tools with NN adaptive control tools to guarantee system stability. Finally, two illustrative numerical examples are provided to demonstrate the efficacy of the proposed approach.

This paper presents a full state feedback adaptive dynamic inversion method for uncertain systems that depend nonlinearly upon the control input. Using a specialized set of basis functions that respect the monotonic property of the system nonlinearities with respect to control input, a state predictor is defined for derivation of the adaptive laws. The adaptive dynamic inversion controller is defined as a solution of a fast dynamical equation, which achieves time-scale separation between the state predictor and the controller dynamics. Lyapunov-based adaptive laws ensure that the predictor tracks the state of the nonlinear system with bounded errors. As a result, the system state tracks the desired reference model with bounded errors. Benefits of the proposed design method are demonstrated using Van der Pol dynamics with nonlinear control input.

In this paper, we present a novel neural network (NN) adaptive control architecture with guaranteed transient performance. With this new architecture, both input and output signals of an uncertain nonlinear system follow a desired linear system during the transient phase, in addition to stable tracking. This new architecture uses a low-pass filter in the feedback loop, which consequently enables to enforce the desired transient performance by increasing the adaptation gain. For the guaranteed transient performance of both input and output signals of the uncertain nonlinear system, the L1 gain of a cascaded system, comprised of the low-pass filter and the closed-loop desired reference model, is required to be less than the inverse of the Lipschitz constant of the unknown nonlinearities in the system. The tools from this paper can be used to develop a theoretically justified verification and validation framework for NN adaptive controllers. Simulation results illustrate the theoretical findings.

The potential applications of neural adaptive control for pharmacology, in general, and anesthesia and critical care unit medicine, in particular, are clearly apparent. Specifically, monitoring and controlling the depth of anesthesia in surgery is of particular importance. Nonnegative and compartmental models provide a broad framework for biological and physiological systems, including clinical pharmacology, and are well suited for developing models for closed-loop control of drug administration. In this paper, we develop a neural adaptive output feedback control framework for nonlinear uncertain nonnegative and compartmental systems with nonnegative control inputs. The proposed framework is Lyapunov-based and guarantees ultimate boundedness of the error signals. In addition, the neural adaptive controller guarantees that the physical system states remain in the nonnegative orthant of the state space. Finally, the proposed approach is used to control the infusion of the anesthetic drug propofol for maintaining a desired constant level of depth of anesthesia for noncardiac surgery.

This paper presents a robust adaptive observer design methodology for a class of uncertain nonlinear systems in the presence of time-varying unknown parameters with absolutely integrable derivatives, and nonvanishing disturbances. Using the universal approximation property of radial basis function (RBF) neural networks and the adaptive bounding technique, the developed observer achieves asymptotic convergence of state estimation error to zero, while ensuring boundedness of parameter errors. A comparative simulation study is presented by the end.

The potential clinical applications of adaptive neural network control for pharmacology in general, and anesthesia and critical care unit medicine in particular, are clearly apparent. Specifically, monitoring and controlling the depth of anesthesia in surgery is of particular importance. Nonnegative and compartmental models provide a broad framework for biological and physiological systems, including clinical pharmacology, and are well suited for developing models for closed-loop control of drug administration. In this paper, we develop a neural adaptive output feedback control framework for adaptive set-point regulation of nonlinear uncertain nonnegative and compartmental systems. The proposed framework is Lyapunov-based and guarantees ultimate boundedness of the error signals corresponding to the physical system states and the neural network weighting gains. The approach is applicable to nonlinear nonnegative systems with unmodeled dynamics of unknown dimension and guarantees that the physical system states remain in the nonnegatiye orthant of the state-space for nonnegative initial conditions. Finally, a numerical example involving the infusion of the anesthetic drug midazolam for maintaining a desired constant level of depth of anesthesia for noncardiac surgery is provided to demonstrate the efficacy of the proposed approach.

Nonnegative and compartmental dynamical system models are derived from mass and energy balance considerations that involve dynamic states whose values are nonnegative. These models are widespread in engineering and life sciences and typically involve the exchange of nonnegative quantities between subsystems or compartments wherein each compartment is assumed to be kinetically homogeneous. In this paper, we develop a full-state feedback neural adaptive control framework for adaptive set-point regulation of nonlinear uncertain nonnegative and compartmental systems. The proposed framework is Lyapunov-based and guarantees ultimate boundedness of the error signals corresponding to the physical system states and the neural network weighting gains. In addition, the neural adaptive controller guarantees that the physical system states remain in the nonnegative orthant of the state-space for nonnegative initial conditions.

A decentralized adaptive output feedback control design is proposed for large-scale interconnected systems. It is assumed that all the controllers share prior information about the system reference models. Based on that information, a linearly parameterized neural network is introduced for each subsystem to partially cancel the effect of the interconnections on tracking performance. Boundedness of error signals is shown through Lyapunov's direct method.

We consider adaptive output feedback control of uncertain nonlinear systems, in which both the dynamics and the dimension of the regulated system may be unknown. However, the relative degree of the regulated output is assumed to be known. Given a smooth reference trajectory, the problem is to design a controller that forces the system measurement to track it with bounded errors. The classical approach requires a state observer. Finding a good observer for an uncertain nonlinear system is not an obvious task. We argue that it is sufficient to build an observer for the output tracking error. Ultimate boundedness of the error signals is shown through Lyapunov's direct method. The theoretical results are illustrated in the design of a controller for a fourth-order nonlinear system of relative degree two and a high-bandwidth attitude command system for a model R-50 helicopter.