Sreenatha G. Anavatti

Tanmoy Dam, Md Meftahul Ferdaus, Mahardhika Pratama et al.

Many real-world classification problems have imbalanced frequency of class labels; a well-known issue known as the "class imbalance" problem. Classic classification algorithms tend to be biased towards the majority class, leaving the classifier vulnerable to misclassification of the minority class. While the literature is rich with methods to fix this problem, as the dimensionality of the problem increases, many of these methods do not scale-up and the cost of running them become prohibitive. In this paper, we present an end-to-end deep generative classifier. We propose a domain-constraint autoencoder to preserve the latent-space as prior for a generator, which is then used to play an adversarial game with two other deep networks, a discriminator and a classifier. Extensive experiments are carried out on three different multi-class imbalanced problems and a comparison with state-of-the-art methods. Experimental results confirmed the superiority of our method over popular algorithms in handling high-dimensional imbalanced classification problems. Our code is available on https://github.com/TanmDL/SLPPL-GAN.

Harshita Boonlia, Tanmoy Dam, Md Meftahul Ferdaus et al.

In real world scenarios, out-of-distribution (OOD) datasets may have a large distributional shift from training datasets. This phenomena generally occurs when a trained classifier is deployed on varying dynamic environments, which causes a significant drop in performance. To tackle this issue, we are proposing an end-to-end deep multi-task network in this work. Observing a strong relationship between rotation prediction (self-supervised) accuracy and semantic classification accuracy on OOD tasks, we introduce an additional auxiliary classification head in our multi-task network along with semantic classification and rotation prediction head. To observe the influence of this addition classifier in improving the rotation prediction head, our proposed learning method is framed into bi-level optimisation problem where the upper-level is trained to update the parameters for semantic classification and rotation prediction head. In the lower-level optimisation, only the auxiliary classification head is updated through semantic classification head by fixing the parameters of the semantic classification head. The proposed method has been validated through three unseen OOD datasets where it exhibits a clear improvement in semantic classification accuracy than other two baseline methods. Our code is available on GitHub \url{https://github.com/harshita-555/OSSL}

MD. Meftahul Ferdaus, Mahardhika Pratama, Sreenatha G Anavatti et al.

At recent times, with the incremental demand of the fully autonomous system, a huge research interest is observed in learning machine based intelligent, self-organizing, and evolving controller. In this work, a new evolving and self-organizing controller namely Generic-controller, G-controller, is proposed. The G-controller that works in the fully online mode with very minor expert domain knowledge is developed by incorporating the sliding model control, SMC, theory based learning algorithm with an advanced incremental learning machine namely Generic Evolving Neuro-Fuzzy Inference System , GENEFIS. The controller starts operating from scratch with an empty set of fuzzy rules, and therefore, no offline training is required. To cope with the plant vulnerable behavior, the controller can add, or prune the rules on demand. Control law and adaptation laws for the consequents are derived from the SMC algorithm to establish a stable closed-loop system, where the stability of the G-controller is guaranteed using the Lyapunov function. The uniform asymptotic convergence of tracking error to zero is witnessed through the implication of an auxiliary robustifying control term. In addition, the implementation of the multivariate Gaussian function helps the controller to handle the non-axis parallel data from the plant and consequently enhances the robustness against the uncertainties and environmental perturbations. Finally, the controller performance has been evaluated by observing the tracking performance in controlling simulated plants of unmanned aerial vehicle namely bio-inspired flapping wing micro air vehicle BIFW MAV and hexacopter for a variety of trajectories.

Md Meftahul Ferdaus, Sreenatha G. Anavatti, Matthew A. Garratt et al.

Advanced and accurate modelling of a Flapping Wing Micro Air Vehicle (FW MAV) and its control is one of the recent research topics related to the field of autonomous Unmanned Aerial Vehicles (UAVs). In this work, a four wing Natureinspired (NI) FW MAV is modeled and controlled inspiring by its advanced features like quick flight, vertical take-off and landing, hovering, and fast turn, and enhanced manoeuvrability when contrasted with comparable-sized fixed and rotary wing UAVs. The Fuzzy C-Means (FCM) clustering algorithm is utilized to demonstrate the NIFW MAV model, which has points of interest over first principle based modelling since it does not depend on the system dynamics, rather based on data and can incorporate various uncertainties like sensor error. The same clustering strategy is used to develop an adaptive fuzzy controller. The controller is then utilized to control the altitude of the NIFW MAV, that can adapt with environmental disturbances by tuning the antecedent and consequent parameters of the fuzzy system.

Xingshuai Dong, Matthew A. Garratt, Sreenatha G. Anavatti et al.

Monocular depth estimation is an important task that can be applied to many robotic applications. Existing methods focus on improving depth estimation accuracy via training increasingly deeper and wider networks, however these suffer from large computational complexity. Recent studies found that edge information are important cues for convolutional neural networks (CNNs) to estimate depth. Inspired by the above observations, we present a novel lightweight Edge Guided Depth Estimation Network (EGD-Net) in this study. In particular, we start out with a lightweight encoder-decoder architecture and embed an edge guidance branch which takes as input image gradients and multi-scale feature maps from the backbone to learn the edge attention features. In order to aggregate the context information and edge attention features, we design a transformer-based feature aggregation module (TRFA). TRFA captures the long-range dependencies between the context information and edge attention features through cross-attention mechanism. We perform extensive experiments on the NYU depth v2 dataset. Experimental results show that the proposed method runs about 96 fps on a Nvidia GTX 1080 GPU whilst achieving the state-of-the-art performance in terms of accuracy.

Tanmoy Dam, Mahardhika Pratama, MD Meftahul Ferdaus et al.

Adversarial continual learning is effective for continual learning problems because of the presence of feature alignment process generating task-invariant features having low susceptibility to the catastrophic forgetting problem. Nevertheless, the ACL method imposes considerable complexities because it relies on task-specific networks and discriminators. It also goes through an iterative training process which does not fit for online (one-epoch) continual learning problems. This paper proposes a scalable adversarial continual learning (SCALE) method putting forward a parameter generator transforming common features into task-specific features and a single discriminator in the adversarial game to induce common features. The training process is carried out in meta-learning fashions using a new combination of three loss functions. SCALE outperforms prominent baselines with noticeable margins in both accuracy and execution time.

Muhammad Anwar Ma'sum, MD Rasel Sarkar, Mahardhika Pratama et al.

A reliable long-term time-series forecaster is highly demanded in practice but comes across many challenges such as low computational and memory footprints as well as robustness against dynamic learning environments. This paper proposes Meta-Transformer Networks (MANTRA) to deal with the dynamic long-term time-series forecasting tasks. MANTRA relies on the concept of fast and slow learners where a collection of fast learners learns different aspects of data distributions while adapting quickly to changes. A slow learner tailors suitable representations to fast learners. Fast adaptations to dynamic environments are achieved using the universal representation transformer layers producing task-adapted representations with a small number of parameters. Our experiments using four datasets with different prediction lengths demonstrate the advantage of our approach with at least $3\%$ improvements over the baseline algorithms for both multivariate and univariate settings. Source codes of MANTRA are publicly available in \url{https://github.com/anwarmaxsum/MANTRA}.

Xingshuai Dong, Matthew A. Garratt, Sreenatha G. Anavatti et al.

As an essential component for many autonomous driving and robotic activities such as ego-motion estimation, obstacle avoidance and scene understanding, monocular depth estimation (MDE) has attracted great attention from the computer vision and robotics communities. Over the past decades, a large number of methods have been developed. To the best of our knowledge, however, there is not a comprehensive survey of MDE. This paper aims to bridge this gap by reviewing 197 relevant articles published between 1970 and 2021. In particular, we provide a comprehensive survey of MDE covering various methods, introduce the popular performance evaluation metrics and summarize publically available datasets. We also summarize available open-source implementations of some representative methods and compare their performances. Furthermore, we review the application of MDE in some important robotic tasks. Finally, we conclude this paper by presenting some promising directions for future research. This survey is expected to assist readers to navigate this research field.

Vu Phi Tran, Matthew A. Garratt, Kathryn Kasmarik et al.

This paper proposes a novel swarm-based control algorithm for exploration and coverage of unknown environments, while maintaining a formation that permits short-range communication. The algorithm combines two elements: swarm rules for maintaining a close-knit formation and frontier search for driving exploration and coverage. Inspired by natural systems in which large numbers of simple agents (e.g., schooling fish, flocking birds, swarming insects) perform complicated collective behaviors for efficiency and safety, the first element uses three simple rules to maintain a swarm formation. The second element provides a means to select promising regions to explore (and cover) by minimising a cost function involving robots' relative distance to frontier cells and the frontier's size. We tested the performance of our approach on heterogeneous and homogeneous groups of mobile robots in different environments. We measure both coverage performance and swarm formation statistics as indicators of the robots' ability to explore effectively while maintaining a formation conducive to short-range communication. Through a series of comparison experiments, we demonstrate that our proposed strategy has superior performance to recently presented map coverage methodologies and conventional swarming methods.

Xingshuai Dong, Matthew A. Garratt, Sreenatha G. Anavatti et al.

Depth is a vital piece of information for autonomous vehicles to perceive obstacles. Due to the relatively low price and small size of monocular cameras, depth estimation from a single RGB image has attracted great interest in the research community. In recent years, the application of Deep Neural Networks (DNNs) has significantly boosted the accuracy of monocular depth estimation (MDE). State-of-the-art methods are usually designed on top of complex and extremely deep network architectures, which require more computational resources and cannot run in real-time without using high-end GPUs. Although some researchers tried to accelerate the running speed, the accuracy of depth estimation is degraded because the compressed model does not represent images well. In addition, the inherent characteristic of the feature extractor used by the existing approaches results in severe spatial information loss in the produced feature maps, which also impairs the accuracy of depth estimation on small sized images. In this study, we are motivated to design a novel and efficient Convolutional Neural Network (CNN) that assembles two shallow encoder-decoder style subnetworks in succession to address these problems. In particular, we place our emphasis on the trade-off between the accuracy and speed of MDE. Extensive experiments have been conducted on the NYU depth v2, KITTI, Make3D and Unreal data sets. Compared with the state-of-the-art approaches which have an extremely deep and complex architecture, the proposed network not only achieves comparable performance but also runs at a much faster speed on a single, less powerful GPU.

Tanmoy Dam, Nidhi Swami, Sreenatha G. Anavatti et al.

This paper presents a novel multi-fake evolutionary generative adversarial network(MFEGAN) for handling imbalance hyperspectral image classification. It is an end-to-end approach in which different generative objective losses are considered in the generator network to improve the classification performance of the discriminator network. Thus, the same discriminator network has been used as a standard classifier by embedding the classifier network on top of the discriminating function. The effectiveness of the proposed method has been validated through two hyperspectral spatial-spectral data sets. The same generative and discriminator architectures have been utilized with two different GAN objectives for a fair performance comparison with the proposed method. It is observed from the experimental validations that the proposed method outperforms the state-of-the-art methods with better classification performance.

Tanmoy Dam, Md Meftahul Ferdaus, Sreenatha G. Anavatti et al.

Traditional oversampling methods are generally employed to handle class imbalance in datasets. This oversampling approach is independent of the classifier; thus, it does not offer an end-to-end solution. To overcome this, we propose a three-player adversarial game-based end-to-end method, where a domain-constraints mixture of generators, a discriminator, and a multi-class classifier are used. Rather than adversarial minority oversampling, we propose an adversarial oversampling (AO) and a data-space oversampling (DO) approach. In AO, the generator updates by fooling both the classifier and discriminator, however, in DO, it updates by favoring the classifier and fooling the discriminator. While updating the classifier, it considers both the real and synthetically generated samples in AO. But, in DO, it favors the real samples and fools the subset class-specific generated samples. To mitigate the biases of a classifier towards the majority class, minority samples are over-sampled at a fractional rate. Such implementation is shown to provide more robust classification boundaries. The effectiveness of our proposed method has been validated with high-dimensional, highly imbalanced and large-scale multi-class tabular datasets. The results as measured by average class specific accuracy (ACSA) clearly indicate that the proposed method provides better classification accuracy (improvement in the range of 0.7% to 49.27%) as compared to the baseline classifier.

Tanmoy Dam, Sreenatha G. Anavatti, Hussein A. Abbass

Since their introduction in the last few years, conditional generative models have seen remarkable achievements. However, they often need the use of large amounts of labelled information. By using unsupervised conditional generation in conjunction with a clustering inference network, ClusterGAN has recently been able to achieve impressive clustering results. Since the real conditional distribution of data is ignored, the clustering inference network can only achieve inferior clustering performance by considering only uniform prior based generative samples. However, the true distribution is not necessarily balanced. Consequently, ClusterGAN fails to produce all modes, which results in sub-optimal clustering inference network performance. So, it is important to learn the prior, which tries to match the real distribution in an unsupervised way. In this paper, we propose self-augmentation information maximization improved ClusterGAN (SIMI-ClusterGAN) to learn the distinctive priors from the data directly. The proposed SIMI-ClusterGAN consists of four deep neural networks: self-augmentation prior network, generator, discriminator and clustering inference network. The proposed method has been validated using seven benchmark data sets and has shown improved performance over state-of-the art methods. To demonstrate the superiority of SIMI-ClusterGAN performance on imbalanced dataset, we have discussed two imbalanced conditions on MNIST datasets with one-class imbalance and three classes imbalanced cases. The results highlight the advantages of SIMI-ClusterGAN.

Hung The Nguyen, Tung Duy Nguyen, Vu Phi Tran et al.

The control and guidance of multi-robots (swarm) is a non-trivial problem due to the complexity inherent in the coupled interaction among the group. Whether the swarm is cooperative or non-cooperative, lessons can be learnt from sheepdogs herding sheep. Biomimicry of shepherding offers computational methods for swarm control with the potential to generalize and scale in different environments. However, learning to shepherd is complex due to the large search space that a machine learner is faced with. We present a deep hierarchical reinforcement learning approach for shepherding, whereby an unmanned aerial vehicle (UAV) learns to act as an aerial sheepdog to control and guide a swarm of unmanned ground vehicles (UGVs). The approach extends our previous work on machine education to decompose the search space into a hierarchically organized curriculum. Each lesson in the curriculum is learnt by a deep reinforcement learning model. The hierarchy is formed by fusing the outputs of the model. The approach is demonstrated first in a high-fidelity robotic-operating-system (ROS)-based simulation environment, then with physical UGVs and a UAV in an in-door testing facility. We investigate the ability of the method to generalize as the models move from simulation to the real-world and as the models move from one scale to another.

Huanneng Qiu, Matthew Garratt, David Howard et al.

Spiking Neural Networks are powerful computational modelling tools that have attracted much interest because of the bioinspired modelling of synaptic interactions between neurons. Most of the research employing spiking neurons has been non-behavioural and discontinuous. Comparatively, this paper presents a recurrent spiking controller that is capable of solving nonlinear control problems in continuous domains using a popular topology evolution algorithm as the learning mechanism. We propose two mechanisms necessary to the decoding of continuous signals from discrete spike transmission: (i) a background current component to maintain frequency sufficiency for spike rate decoding, and (ii) a general network structure that derives strength from topology evolution. We demonstrate that the proposed spiking controller can learn significantly faster to discover functional solutions than sigmoidal neural networks in solving a classic nonlinear control problem.

Md Meftahul Ferdaus, Mahardhika Pratama, Sreenatha G. Anavatti et al.

There exists an increasing demand for a flexible and computationally efficient controller for micro aerial vehicles (MAVs) due to a high degree of environmental perturbations. In this work, an evolving neuro-fuzzy controller, namely Parsimonious Controller (PAC) is proposed. It features fewer network parameters than conventional approaches due to the absence of rule premise parameters. PAC is built upon a recently developed evolving neuro-fuzzy system known as parsimonious learning machine (PALM) and adopts new rule growing and pruning modules derived from the approximation of bias and variance. These rule adaptation methods have no reliance on user-defined thresholds, thereby increasing the PAC's autonomy for real-time deployment. PAC adapts the consequent parameters with the sliding mode control (SMC) theory in the single-pass fashion. The boundedness and convergence of the closed-loop control system's tracking error and the controller's consequent parameters are confirmed by utilizing the LaSalle-Yoshizawa theorem. Lastly, the controller's efficacy is evaluated by observing various trajectory tracking performance from a bio-inspired flapping-wing micro aerial vehicle (BI-FWMAV) and a rotary wing micro aerial vehicle called hexacopter. Furthermore, it is compared to three distinctive controllers. Our PAC outperforms the linear PID controller and feed-forward neural network (FFNN) based nonlinear adaptive controller. Compared to its predecessor, G-controller, the tracking accuracy is comparable, but the PAC incurs significantly fewer parameters to attain similar or better performance than the G-controller.

Hung Nguyen, Vu Tran, Tung Nguyen et al.

In apprenticeship learning (AL), agents learn by watching or acquiring human demonstrations on some tasks of interest. However, the lack of human demonstrations in novel tasks where they may not be a human expert yet, or when it is too expensive and/or time consuming to acquire human demonstrations motivated a new algorithm: Apprenticeship bootstrapping (ABS). The basic idea is to learn from demonstrations on sub-tasks then autonomously bootstrap a model on the main, more complex, task. The original ABS used inverse reinforcement learning (ABS-IRL). However, the approach is not suitable for continuous action spaces. In this paper, we propose ABS via Deep learning (ABS-DL). It is first validated in a simulation environment on an aerial and ground coordination scenario, where an Unmanned Aerial Vehicle (UAV) is required to maintain three Unmanned Ground Vehicles (UGVs) within a field of view of the UAV 's camera (FoV). Moving a machine learning algorithm from a simulation environment to an actual physical platform is challenging because `mistakes' made by the algorithm while learning could lead to the damage of the platform. We then take this extra step to test the algorithm in a physical environment. We propose a safety-net as a protection layer to ensure that the autonomy of the algorithm in learning does not compromise the safety of the platform. The tests of ABS-DL in the real environment can guarantee a damage-free, collision avoidance behaviour of autonomous bodies. The results show that performance of the proposed approach is comparable to that of a human, and competitive to the traditional approach using expert demonstrations performed on the composite task. The proposed safety-net approach demonstrates its advantages when it enables the UAV to operate more safely under the control of the ABS-DL algorithm.

Md Meftahul Ferdaus, Sreenatha G. Anavatti, Matthew A. Garratt et al.

Controlling of a flapping flight is one of the recent research topics related to the field of Flapping Wing Micro Air Vehicle (FW MAV). In this work, an adaptive control system for a four-wing FW MAV is proposed, inspired by its advanced features like quick flight, vertical take-off and landing, hovering, and fast turn, and enhanced manoeuvrability. Sliding Mode Control (SMC) theory has been used to develop the adaptation laws for the proposed adaptive fuzzy controller. The SMC theory confirms the closed-loop stability of the controller. The controller is utilized to control the altitude of the FW MAV, that can adapt to environmental disturbances by tuning the antecedent and consequent parameters of the fuzzy system.

Ahmad Jobran Al-Mahasneh, Sreenatha G. Anavatti, Matthew A. Garratt

This paper depicts a brief revision of Generalized Regression Neural Networks (GRNN) applications in system identification and control of dynamic systems. In addition, a comparison study between the performance of back-propagation neural networks and GRNN is presented for system identification problems. The results of the comparison confirm that GRNN has shorter training time and higher accuracy than the counterpart back-propagation neural networks.

Md Meftahul Ferdaus, Mahardhika Pratama, Sreenatha G. Anavatti et al.

Data stream has been the underlying challenge in the age of big data because it calls for real-time data processing with the absence of a retraining process and/or an iterative learning approach. In realm of fuzzy system community, data stream is handled by algorithmic development of self-adaptive neurofuzzy systems (SANFS) characterized by the single-pass learning mode and the open structure property which enables effective handling of fast and rapidly changing natures of data streams. The underlying bottleneck of SANFSs lies in its design principle which involves a high number of free parameters (rule premise and rule consequent) to be adapted in the training process. This figure can even double in the case of type-2 fuzzy system. In this work, a novel SANFS, namely parsimonious learning machine (PALM), is proposed. PALM features utilization of a new type of fuzzy rule based on the concept of hyperplane clustering which significantly reduces the number of network parameters because it has no rule premise parameters. PALM is proposed in both type-1 and type-2 fuzzy systems where all of which characterize a fully dynamic rule-based system. That is, it is capable of automatically generating, merging and tuning the hyperplane-based fuzzy rule in the single pass manner. Moreover, an extension of PALM, namely recurrent PALM (rPALM), is proposed and adopts the concept of teacher-forcing mechanism in the deep learning literature. The efficacy of PALM has been evaluated through numerical study with six real-world and synthetic data streams from public database and our own real-world project of autonomous vehicles. The proposed model showcases significant improvements in terms of computational complexity and number of required parameters against several renowned SANFSs, while attaining comparable and often better predictive accuracy.

Md Meftahul Ferdaus, Mahardhika Pratama, Sreenatha G. Anavatti et al.

Nowadays, the application of fully autonomous system like rotary wing unmanned air vehicles (UAVs) is increasing sharply. Due to the complex nonlinear dynamics, a huge research interest is witnessed in developing learning machine based intelligent, self-organizing evolving controller for these vehicles notably to address the system's dynamic characteristics. In this work, such an evolving controller namely Generic-controller (G-controller) is proposed to control the altitude of a rotary wing UAV namely hexacopter. This controller can work with very minor expert domain knowledge. The evolving architecture of this controller is based on an advanced incremental learning algorithm namely Generic Evolving Neuro-Fuzzy Inference System (GENEFIS). The controller does not require any offline training, since it starts operating from scratch with an empty set of fuzzy rules, and then add or delete rules on demand. The adaptation laws for the consequent parameters are derived from the sliding mode control (SMC) theory. The Lyapunov theory is used to guarantee the stability of the proposed controller. In addition, an auxiliary robustifying control term is implemented to obtain a uniform asymptotic convergence of tracking error to zero. Finally, the G-controller's performance evaluation is observed through the altitude tracking of a UAV namely hexacopter for various trajectories.