Online Adaptive Scheme Research Articles

Dynamic Via-points and Improved Spatial Generalization for Online Trajectory Generation with Dynamic Movement Primitives

Dynamic Movement Primitives (DMP) have found remarkable applicability and success in various robotic tasks, which can be mainly attributed to their generalization, modulation and robustness properties. However, the spatial generalization of DMP can be problematic in some cases, leading to excessive overscaling and in turn large velocities and accelerations. While other DMP variants have been proposed in the literature to tackle this issue, they can also exhibit excessive overscaling as we show in this work. Moreover, incorporating intermediate points (via-points) for adjusting the DMP trajectory to account for the geometry of objects related to the task, or to avoid or push aside objects that obstruct a specific task, is not addressed by the current DMP literature. In this work we tackle these unresolved so far issues by proposing an improved online spatial generalization, that remedies the shortcomings of the classical DMP generalization, and moreover allows the incorporation of dynamic via-points. This is achieved by designing an online adaptation scheme for the DMP weights which is proved to minimize the distance from the demonstrated acceleration profile to retain the shape of the demonstration, subject to dynamic via-point and initial/final state constraints. Extensive comparative simulations with the classical and other DMP variants are conducted, while experimental results validate the practical usefulness and efficiency of the proposed method.

Multi-Stimulus Least-Squares Transformation With Online Adaptation Scheme to Reduce Calibration Effort for SSVEP-Based BCIs.

The proposed ms-LST-OA consists of two parts. Firstly, to improve the precision of the transformation matrices, we propose the multi-stimulus LST (ms-LST) using cross-stimulus learning scheme as the cross-subject data transformation method. The ms-LST uses the data from neighboring stimuli to construct a higher precision transformation matrix for each stimulus to reduce the differences between transformed data and real data. Secondly, to further optimize the constructed spatial filters and reference templates, we use an online adaptation scheme to learn more features of the EEG signals of the target subject through an iterative process trial-by-trial. ms-LST-OA performance was measured for three datasets (Benchmark Dataset, BETA Dataset, and UCSD Dataset). Using few calibration data, the ITR of ms-LST-OA achieved 210.01±10.10 bits/min, 172.31±7.26 bits/min, and 139.04±14.90 bits/min for all three datasets, respectively. Using ms-LST-OA can reduce calibration effort for SSVEP-based BCIs.

Infusing Model Predictive Control Into Meta-Reinforcement Learning for Mobile Robots in Dynamic Environments

The successful operation of mobile robots requires them to adapt rapidly to environmental changes. To develop an adaptive decision-making tool for mobile robots, we propose a novel algorithm that combines meta-reinforcement learning (meta-RL) with model predictive control (MPC). Our method employs an off-policy meta-RL algorithm as a baseline to train a policy using transition samples generated by MPC when the robot detects certain events that can be effectively handled by MPC, with its explicit use of robot dynamics. The key idea of our method is to switch between the meta-learned policy and the MPC controller in a randomized and event-triggered fashion to make up for suboptimal MPC actions caused by the limited prediction horizon. During meta-testing, the MPC module is deactivated to significantly reduce computation time in motion control. We further propose an online adaptation scheme that enables the robot to infer and adapt to a new task within a single trajectory. The performance of our method has been demonstrated through simulations using a nonlinear car-like vehicle model with <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"><tex-math notation="LaTeX">$(i)$</tex-math></inline-formula> synthetic movements of obstacles, and <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"><tex-math notation="LaTeX">$(ii)$</tex-math></inline-formula> real-world pedestrian motion data. The simulation results indicate that our method outperforms other algorithms in terms of learning efficiency and navigation quality.

Simplified artificial neural network based online adaptive control scheme for nonlinear systems

Simplified artificial neural network based online adaptive control scheme for nonlinear systems

Online Adaptation Boosts SSVEP-Based BCI Performance.

A user-friendly steady-state visual evoked potential (SSVEP)-based brain-computer interface (BCI) prefers no calibration for its target recognition algorithm, however, the existing calibration-free schemes perform still far behind their calibration-based counterparts. To tackle this issue, learning online from the subject's unlabeled data is investigated as a potential approach to boost the performance of the calibration-free SSVEP-based BCIs. An online adaptation scheme is developed to tune the spatial filters using the online unlabeled data from previous trials, and then developing the online adaptive canonical correlation analysis (OACCA) method. A simulation study on two public SSVEP datasets (Dataset I and II) with a total of 105 subjects demonstrated that the proposed online adaptation scheme can boost the CCA's averaged information transfer rate (ITR) from 94.60 to 158.87 bits/min in Dataset I and from 85.80 to 123.91 bits/min in Dataset II. Furthermore, in our online experiment it boosted the CCA's ITR from 55.81 bits/min to 95.73 bits/min. More importantly, this online adaptation scheme can be easily combined with any spatial filtering-based algorithms to achieve online learning. By online adaptation, the proposed OACCA performed much better than the calibration-free CCA, and comparable to the calibration-based algorithms. This work provides a general way for the SSVEP-based BCIs to learn online from unlabeled data and thus avoid calibration.

Adaptive method for sensorless temperature estimation over the lifetime of lithium-ion batteries

Over the last decade, several impedance-based temperature estimation methods for lithium-ion cells have been proposed in the literature. However, the influence of cell degradation on these methods is rarely considered. In this paper, we therefore investigate the influence of aging on the temperature estimation method, presented in our previous work, by tracking the capacity fade and resistance change of a 6s1p module over 200 cycles. Both capacity fade and resistance change were found to affect the accuracy of the temperature estimation method, leading to a root mean square error (RMSE) of up to 15 K without adaptation to cell aging. Fitting the reference used for temperature estimation with linear operations and a nonlinear least-squares solver (NLS) to the aging data proved to be a valid method of compensating for the effects of aging. Derived from the fitting results, an online applicable aging adjustment scheme based on the checkup values is proposed to maintain a stable temperature estimation over battery lifetime. Using a simple resistance offset correction and an accurate state of charge and health estimation, the temperature estimation error stabilizes at an average RMSE of below 2 K for each cell in the module over its entire lifetime. • Sensorless method for resistance-based temperature estimation for lithium-ion batteries. • Investigation of the effects of cell aging on temperature estimation in a battery module. • Aging compensation with offset correction and accurate estimation of state of charge. • Stable temperature estimation over battery lifetime with online adaptation scheme.

Adaptive Scheme for Detecting Induction Motor Incipient Broken Bar Faults at Various Load and Inertia Conditions.

This paper introduces a novel online adaptive protection scheme to detect and diagnose broken bar faults (BBFs) in induction motors during steady-state conditions based on an analytical approach. The proposed scheme can detect precisely adjacent and non-adjacent BBFs in their incipient phases under different inertia, variable loading conditions, and noisy environments. The main idea of the proposed scheme is monitoring the variation in the phase angle of the main sideband frequency components by applying Fast Fourier Transform to only one phase of the stator current. The scheme does not need any predetermined settings but only one of the stator current signals during the commissioning phase. The threshold value is calculated adaptively to discriminate between healthy and faulty cases. Besides, an index is proposed to designate the fault severity. The performance of this scheme is verified using two simulated motors with different designs by applying the finite element method in addition to a real experimental dataset. The results show that the proposed scheme can effectively detect half, one, two, or three broken bars in adjacent/non-adjacent versions and also estimate their severity under different operating conditions and in a noisy environment, with accuracy reaching 100% independently from motor parameters.

Desired compensation adaptive robust repetitive control of a multi-DoFs industrial robot

In the presence of system coupling and dynamic uncertainties, extensive research has been conducted on the precise motion control of industrial manipulators with general reference trajectories. Since repetitive operations are common tasks in industrial applications, it is an essential and practical problem to further improve the control accuracy by taking advantage of the periodicity of the reference trajectory. In this paper, a desired compensation adaptive robust repetitive control is proposed for multi-DoFs industrial manipulators to perform repetitive tasks. Specifically, the link dynamics identified offline is compensated directly to decouple the system and capture the main characteristics of the link effect. Then, the uncertain friction is dealt with through an online adaptation scheme, in which the desired compensation is utilized to avoid measurement noise and chattering at low speed. And periodic disturbances are approximated by Fourier series expansion with unknown Fourier coefficients, which will be learned online. Finally, the robust feedback is designed to guarantee transient control accuracy and robustness against dynamic uncertainties. Comparative experiments on an industrial manipulator show that the proposed controller possesses better transient and steady-state control accuracy and error convergence rate.

AC Microgrids Protection: A Digital Coordinated Adaptive Scheme

A significant challenge for designing a coordinated and effective protection architecture of a microgrid (MG) is the aim of an efficient, reliable, and fast protection scheme for both the grid-connected and islanded modes of operation. To this end, bidirectional power flow, varying short-circuit power, low voltage ride-through (LVRT) capability, and the plug-and-play characteristics of distributed generation units (DGUs), which are key issues in a MG system must be considered; otherwise, a mal-operation of protection devices (PDs) may occur. In this sense, a conventional protection system with a single threshold/setting may not be able to fully protect an MG system. To tackle this challenge, this work presents a comprehensive coordinated adaptive protection scheme for AC MGs that can tune their protection setting according to the system states and the operation mode, and is able to switch the PDs’ setting. In the first step of the proposed adaptive algorithm, an offline setting will be adopted for selective and sensitive fault detection, isolation, and coordination among proposed protective modules. As any change in the system is detected by the proposed algorithm in the online step, a new set of setting for proposed modules will be performed to adapt the settings accordingly. In this way, a new set of settings are adapted to maintain a fast and reliable operation, which covers selective, sensitive, and adaptive requirements. The pickup current (Ip) and time multiple settings (TMS) of directional over-current relays (DOCR), as well as coordinated time delays for the proposed protection scheme for both of the grid-connected and islanded modes of operation, are calculated offline. Then, an online adaptive protection scheme is proposed to detect different fault types in different locations. The simulation results show that the proposed method provides a coordinated reliable solution, which can detect and isolate fault conditions in a fast, selective and coordinated adaptive pattern.

Intelligent adaptive learning and control for discrete-time nonlinear uncertain systems in multiple environments

This paper focuses on an adaptive learning and control problem for a class of discrete-time nonlinear uncertain systems operating under multiple environments. A novel intelligent learning control framework is proposed by using a combination of offline and online learning methods. Specifically, in the offline learning mode, a deterministic learning (DL) based adaptive dynamics learning approach is first proposed to achieve locally-accurate identification of associated nonlinear uncertain system dynamics under each anticipated individual environment, and the learned knowledge is obtained and stored in a set of constant radial basis function neural network models. Then, with the learned knowledge, an online adaptive learning control scheme is further developed, which consists of: (i) an online adaptive learning control mechanism composed of multiple experience-based controllers and a DL-based adaptive learning controller, aiming to provide desired control performance for the plant operating under each individual environment; and (ii) a learning-based recognition mechanism composed of multiple recognition estimators and a DL-based identifier, aiming to recognize the active environment and schedule appropriate control strategies in real time. To guarantee the system stability during environment transition, a robust quasi-sliding-mode controller is further developed and embedded in the overall controller architecture. With this new intelligent adaptive learning control framework, the overall system is capable of adapting not only to any anticipated (pre-defined) environment by re-utilizing the knowledge obtained from both offline and online learning, but also to unanticipated (new) environments by actively acquiring new knowledge online. Simulation studies are conducted to verify the effectiveness and advantages of this new framework.

Adaptive scheme protecting renewable‐dominated micro‐grids against usual topology‐change events

Miscoordination and faulty operation are the two main protection challenges of renewable Distributed Generations (DGs) in Distribution Networks (DNs) and Micro-Grids (MGs). Although various approaches have already been presented in the literature, none of them has proposed a solution for simultaneous impact of DN/MG reconfigurations and DGs’ protection challenges. Topology-change being a usual method in decreasing power loss or voltage deviations, it would be preferable to have an online adaptive scheme considering all protection challenges together. Hence, the ordinary overcurrent relays using the IEC 61850 protocol capabilities are utilized in an algorithm capable of definitely assigning which relays are responsible for the on-going fault and which ones are not. That is, the algorithm is applied on a peer-mode multi-agent system (MAS) structure. First, the relay agents are classified into radial and loop Virtual Local Area Networks (VLANs). When a relay detects the fault, the MAS will find the responsible VLAN and instantly isolate other VLANs, including their agents. Next, the main and backup relays using the proposed communication map are assigned within the responsible VLAN. Last, a suitable protection algorithm is applied on the selected relays, according to direction of fault current.

An Adaptive Correction Scheme for Offset-Free Asymptotic Performance in Deep Learning-based Economic MPC

Abstract There has been an increasing interest in explicit and cheap-to-evaluate control policies that approximate (computationally expensive) control laws such as model predictive control (MPC). However, approximate control policies are subject to approximation errors, leading to asymptotic performance losses. The contribution of this paper is three-fold: (i) a closed-loop training scheme is presented for deep neural network approximation of economic MPC; (ii) an online adaptive correction scheme is presented to account for the performance losses induced by approximation errors; and (iii) an offline performance verification scheme is presented to ensure that the approximate control policy converges to an equilibrium point of the system. The proposed approach is illustrated using a Williams-Otto reactor problem.

Learning to Demodulate From Few Pilots via Offline and Online Meta-Learning

This paper considers an Internet-of-Things (IoT) scenario in which devices sporadically transmit short packets with few pilot symbols over a fading channel. Devices are characterized by unique transmission non-idealities, such as I/Q imbalance. The number of pilots is generally insufficient to obtain an accurate estimate of the end-to-end channel, which includes the effects of fading and of the transmission-side distortion. This paper proposes to tackle this problem by using meta-learning. Accordingly, pilots from previous IoT transmissions are used as meta-training data in order to train a demodulator that is able to quickly adapt to new end-to-end channel conditions from few pilots. Various state-of-the-art meta-learning schemes are adapted to the problem at hand and evaluated, including Model-Agnostic Meta-Learning (MAML), First-Order MAML (FOMAML), REPTILE, and fast Context Adaptation VIA meta-learning (CAVIA). Both offline and online solutions are developed. In the latter case, an integrated online meta-learning and adaptive pilot number selection scheme is proposed. Numerical results validate the advantages of meta-learning as compared to training schemes that either do not leverage prior transmissions or apply a standard joint learning algorithms on previously received data.

An Adaptive Fault-Tolerant Sliding Mode Control Allocation Scheme for Multirotor Helicopter Subject to Simultaneous Actuator Faults

This paper proposes a novel adaptive sliding-mode-based control allocation scheme for accommodating simultaneous actuator faults. The proposed control scheme includes two separate control modules with virtual control part and control allocation part, respectively. As a low-level control module, the control allocation/reallocation scheme is used to distribute/redistribute virtual control signals among the available actuators under fault-free or faulty conditions, respectively. In the case of simultaneous actuator faults, the control allocation and reallocation module may fail to meet the required virtual control signal, which will degrade the overall system stability. The proposed online adaptive scheme can seamlessly adjust the control gains for the high-level sliding mode control module and reconfigure the distribution of control signals to eliminate the effect of the virtual control error and maintain the stability of the closed-loop system. In addition, with the help of the boundary layer for constructing the adaptation law, the overestimation of control gains is avoided, and the adaptation ceases once the sliding variable is within the boundary layer. A significant feature of this study is that the stability of the closed-loop system is guaranteed theoretically in the presence of simultaneous actuator faults. The effectiveness of the proposed control scheme is demonstrated by experimental results based on a modified unmanned multirotor helicopter under both single and simultaneous actuator faults conditions with comparison to a conventional sliding mode controller and a linear quadratic regulator scheme.

Echo state kernel recursive least squares algorithm for machine condition prediction

Abstract Kernel adaptive filter (KAF) has been widely utilized for time series prediction due to its online adaptation scheme, universal approximation capability and convexity. Nevertheless, KAF’s ability to handle temporal tasks is limited, because it is essentially a feed-forward neural network that lacks dynamic characteristics. Traditionally, a sliding widow that contains consecutive data points is constructed to deal with the temporal dependency between data points at neighboring time steps, but the restricted widow length may be incapable of capturing temporal patterns on a larger time scale. To manage this issue, a novel sequential learning approach called echo state KRLS (ES-KRLS) algorithm is proposed by incorporating a dynamic reservoir into kernel recursive least squares (KRLS) algorithm. The reservoir, consisting of a large number of sparsely interconnected hidden units, is treated as a temporal function that transforms the history of the time series into a high-dimensional reservoir state space. Subsequently, the spatial relationship between the reservoir state and the target output is effectively approximated by KRLS algorithm. With the utilization of the fixed reservoir, our novel method not only maintains the simplicity of the learning process but also leads to a significant improvement in the capability of modeling dynamic systems. Numerical results on benchmark tasks demonstrate the excellent performance of the novel method with respect to long-term prediction. Finally, an online prognostic method that combines ES-KRLS and a Bayesian technique is developed for tracking the health status of a degraded system and predicting remaining useful life (RUL). This prognostic method is applied to a turbofan engine degradation dataset to demonstrate its effectiveness.

A New Convex Hull, Sliding Window Based Online Adaptation Method

In any online adaptation scheme, two important phenomena should be taken into consideration; parameter shadowing and parameter interference. To alleviate these problems, in this paper a convex hull, sliding window based online adaptation method for fixed-structure Neural Networks is proposed. The method is capable of dealing with the two phenomena, presenting better results than known alternatives. An analysis of the real-time run time and memory consumption of the algorithm demonstrates that it can be used for real-time applications.

Fault-Tolerant Adaptive Control Allocation for Unmanned Multirotor Helicopter

This paper proposes an adaptive sliding mode control allocation scheme for accommodating simultaneous actuator fault/failure. A control allocation and re-allocation scheme is synthesized to redistribute the control signals among the working actuators. In the case of the desired virtual control not being achieved, the proposed on-line adaptive scheme can seamlessly adjust the control gain to stabilize the overall system. The effectiveness of the proposed algorithm is demonstrated by the simulation results based on a modified unmanned multirotor helicopter under simultaneous actuator fault/failure conditions.

Minimizing the impact of distributed generation of a weak distribution network with an artificial intelligence technique

Integration of renewable energy sources directly into the distribution network become a common practice nowadays, the contribution of renewable energy sources to the distribution network predominate by weather conditions which change short circuit level capability for the electric network. This change in the network configuration could influence the operation of the protective devices in the distribution network. In this study, an online adaptive protection scheme base on adaptive fuzzy algorithm proposed to update and optimize the protection coordination when network topology has been changed. The online algorithm depends on different parameters such as the status of main feeder circuit breaker and the prefault power flow in the network. The simplified network represents a portion of the Eastern Libyan Electric Network implemented in ETAP package.

Improving of entropy adaptive on-line compression

Since energy efficiency, high bandwidth, and low transmission delay are challenging issues in mobile networks, due to resource constraints, there is a great importance in designing of new communication methods. In particular, lossless data compression may provide high performance under constrained resources. In this paper we present a novel on-line and entropy adaptive compression scheme for streaming unbounded length inputs. The scheme extends the window dictionary Lempel–Ziv compression and is adaptive and tailored to compress on-line non entropy stationary inputs. Specifically, the window dictionary size is changed in an adaptive manner to fit the current best compression rate for the input. On-line entropy adaptive compression scheme (EAC), introduced and analyzed in this paper, examines all possible sliding window sizes over the next input portion to choose the optimal window size for this portion; a size that implies the best compression ratio. The size found is then used in the actual compression of this portion. We suggest an adaptive encoding scheme, which optimizes the parameters block by block, and base the compression performance on the optimality proof of LZ77 when applied to blocks (Ziv in IEEE Trans Inf Theory 55(5):1941–1944, 2009). This adaptivity can be useful for many communication tasks. In particular, providing efficient utilization of energy consuming wireless devices by data compression. Due to the dynamic and non-uniform structure of multimedia data, adaptive approaches for data processing are of special interest. The EAC scheme was tested on different types of files (docx, ppt, jpeg, xls) and over synthesized files that were generated as segments of homogeneous Markov Chains. Our experiments demonstrate that the EAC scheme typically provides a higher compression ratio than LZ77 does, when examined in the scope of on-line per-block compression of transmitted (or compressed) files. We propose techniques intended to control the adaptive on-line compression process by estimating relative entropy between two sequential blocks of data. This approach may enhance performance of the mobile networks.

Online Estimation and Compensation of Friction in Industrial Cable Robot Manipulation

This work deal with on-line estimation and compensation of friction in industrial cable robot manipulation. First, a parametric model is developed for a classical friction model. Then, a recursive least squares on-line friction estimator is presented. Next, a Lyapunov based adaptive controller based on Backstepping scheme is designed to compensate for friction in actuator unit. Finally, we implement the simulation for this design. The simulation results show on-line parameter estimation algorithm and adaptive control scheme have generally achieved desired performance.