Intelligent Beetle Antennae Search for UAV Sensing and Avoidance of Obstacles.

Based on a bio-heuristic algorithm, this paper proposes a novel path planner called obstacle avoidance beetle antennae search (OABAS) algorithm, which is applied to the global path planning of unmanned aerial vehicles (UAVs). Compared with the previous bio-heuristic algorithms, the algorithm proposed in this paper has advantages of a wide search range and breakneck search speed, which resolves the contradictory requirements of the high computational complexity of the bio-heuristic algorithm and real-time path planning of UAVs. Besides, the constraints used by the proposed algorithm satisfy various characteristics of the path, such as shorter path length, maximum allowed turning angle, and obstacle avoidance. Ignoring the z-axis optimization by combining with the minimum threat surface (MTS), the resultant path meets the requirements of efficiency and safety. The effectiveness of the algorithm is substantiated by applying the proposed path planning algorithm on the UAVs. Moreover, comparisons with other existing algorithms further demonstrate the superiority of the proposed OABAS algorithm.

Discrete-Time Impedance Control for Dynamic Response Regulation of Parallel Soft Robots.

Accurately controlling the dynamic response and suppression of undesirable dynamics such as overshoots and vibrations is a vital requirement for soft robots operating in industrial environments. Pneumatically actuated soft robots usually undergo large overshoots and significant vibrations when deactuated because of their highly flexible bodies. These large vibrations not only decrease the reliability and accuracy of the soft robot but also introduce undesirable characteristics in the system. For example, it increases the settling time and damages the body of the soft robot, compromising its structural integrity. The dynamic behavior of the soft robots on deactuation needs to be accurately controlled to increase their utility in real-world applications. The literature on pneumatic soft robots still does not sufficiently address the issue of suppressing undesirable vibrations. To address this issue, we propose the use of impedance control to regulate the dynamic response of pneumatic soft robots since the superiority of impedance control is already established for rigid robots. The soft robots are highly nonlinear systems; therefore, we formulated a nonlinear discrete sliding mode impedance controller to control the pneumatic soft robots. The formulation of the controller in discrete-time allows efficient implementation for a high-order system model without the need for state-observers. The simplification and efficiency of the proposed controller enable fast implementation of an embedded system. Unlike other works on pneumatic soft robots, the proposed controller does not require manual tuning of the controller parameters and automatically calculates the parameters based on the impedance value. To demonstrate the efficacy of the proposed controller, we used a 6-chambered parallel soft robot as an experimental platform. We presented the comparative results with an existing state-of-the-art controller in SMC control of pneumatic soft robots. The experiment results indicate that the proposed controller can effectively limit the amplitude of the undesirable vibrations.

Beetle Antennae Search: Using Biomimetic Foraging Behaviour of Beetles to Fool a Well-Trained Neuro-Intelligent System.

Deep Convolutional Neural Networks (CNNs) represent the state-of-the-art artificially intelligent computing models for image classification. The advanced cognition and pattern recognition abilities possessed by humans are ascribed to the intricate and complex neurological connection in human brains. CNNs are inspired by the neurological structure of the human brain and show performance at par with humans in image recognition and classification tasks. On the lower extreme of the neurological complexity spectrum lie small organisms such as insects and worms, with simple brain structures and limited cognition abilities, pattern recognition, and intelligent decision-making abilities. However, billions of years of evolution guided by natural selection have imparted basic survival instincts, which appear as an "intelligent behavior". In this paper, we put forward the evidence that a simple algorithm inspired by the behavior of a beetle (an insect) can fool CNNs in image classification tasks by just perturbing a single pixel. The proposed algorithm accomplishes this in a computationally efficient manner as compared to the other adversarial attacking algorithms proposed in the literature. The novel feature of the proposed algorithm as compared to other metaheuristics approaches for fooling a neural network, is that it mimics the behavior of a single beetle and requires fewer search particles. On the contrary, other metaheuristic algorithms rely on the social or swarming behavior of the organisms, requiring a large population of search particles. We evaluated the performance of the proposed algorithm on LeNet-5 and ResNet architecture using the CIFAR-10 dataset. The results show a high success rate for the proposed algorithms. The proposed strategy raises a concern about the robustness and security aspects of artificially intelligent learning systems.

Utility of MRI in assessment of pituitary iron overload.

Beta thalassemia is highly prevalent in Pakistan with a carrier rate of 5-8%. The main complication of beta thalassemia major is iron overload, especially in reticuloendothelial system, heart, joints and endocrine glands. Pituitary siderosis leads to hypogonadotropic hypogonadism and growth hormone deficiency. Measures of plasma ferritin levels and hepatic iron level are used for assessing body iron overload but these are limited for various reasons particularly in case of pituitary siderosis. Magnetic Resonance Imaging (MRI) is a reliable, non invasive and easily available utility for assessing tissue siderosis. We assessed a 20 year old female beta thalassemic diagnosed with hypogonadotropic hypogonadism and pituitary siderosis using routine spin echo (SE) T1 and T2 weighted sequences of MRI and special Gradient Recalled Echo (GRE) sequence of MRI. We found MRI signal intensity to be decreased on all three sequences but most so on GRE suggesting its greatest sensitivity to pituitary iron deposition. MRI signal hypo-intensity due to paramagnetic effects of iron has been validated for liver siderosis but is still under investigation for pituitary siderosis. Our findings suggest that MRI especially GRE sequence can be used in conjunction with laboratory data to evaluate pituitary siderosis and to prevent further pituitary dysfunction.