Autonomous Object Recognition Research Articles

Intelligent Soft Quasi‐Organism Equipped with Sensor‐Driven Integrated Tentacles

AbstractIntegration of soft electronic system components is critical to create a closed‐loop system that seamlessly integrates sensing, driving, processing, and autonomous control capabilities. However, the existence of these components, particularly sensors and actuators, in isolated or discrete forms complicates the endeavor to achieve seamless interface matching and in situ integration, no more than the autonomic system. Here, an intelligent soft quasi‐organism (SQO) equipped with sensor‐driven integrated tentacles is demonstrated, featuring real‐time state recognition and autonomous object recognition inspired by the sea anemones. By employing a heterogeneous mechanisms homotopic integration (HMHI) strategy, the tentacles of the SQO possess the unique ability to simultaneously perceive state changes and flexibly drive motions, utilizing the same material and structure. The sea anemone‐shaped SQO exhibits real‐time autonomous state identification capabilities through the integration of machine learning and customized circuits, attaining 100% recognition accuracy across sixteen states. With a neuromuscular system that facilitates active autonomous perception, the anemone‐shaped SQO can recognize and intelligently grasp static objects with an accuracy of 80.7%, surpassing that of a human hand (74.7%). The SQO provides a promising approach for realizing artificial neuromuscular systems, with great potential for applications in crucial areas such as intelligent soft robotics and in vivo therapy.

Workload-Aware Scheduling Using Markov Decision Process for Infrastructure-Assisted Learning-Based Multi-UAV Surveillance Networks

In modern networking research, infrastructure-assisted unmanned autonomous vehicles (UAVs) are actively considered for real-time learning-based surveillance and aerial data-delivery under unexpected 3D free mobility and coordination. In this system model, it is essential to consider the power limitation in UAVs and autonomous object recognition (for abnormal behavior detection) deep learning model performance in infrastructure/towers. To overcome the power limitation of UAVs, this paper proposes a novel aerial scheduling algorithm between multi-UAVs and multi-towers where the towers conduct wireless power transfer toward UAVs. In addition, to take care of the high-performance learning model training in towers, the training data from UAVs should be fairly delivered to towers because larger data delivery will make huge computation overhead whereas the less data delivery will introduce overfitting. Therefore, fair data distribution from UAVs to their associated towers is essentially required. Therefore, this paper proposes a novel workload-aware scheduling algorithm between multi-towers and multi-UAVs for joint power-charging from towers to their associated UAVs and training data delivery from UAVs to their associated towers. For computing the workload-aware optimal scheduling decisions in each unit time, our solution approach for the given scheduling problem is designed based on Markov decision process (MDP) to deal with (i) time-varying low-complexity computation and (ii) pseudo-polynomial optimality. As shown in performance evaluation results, our proposed algorithm ensures (i) sufficient times for resource exchanges between towers and UAVs, (ii) the most even and uniform data collection during the processes compared to the other algorithms, and (iii) the performance of all towers converges to optimal levels.

A Data‐Driven and Biologically Inspired Preprocessing Scheme to Improve Visual Object Recognition

Autonomous object recognition in images is one of the most critical topics in security and commercial applications. Due to recent advances in visual neuroscience, the researchers tend to extend biologically plausible schemes to improve the accuracy of object recognition. Preprocessing is one part of the visual recognition system that has received much less attention. In this paper, we propose a new, simple, and biologically inspired pre processing technique by using the data‐driven mechanism of visual attention. In this part, the responses of Retinal Ganglion Cells (RGCs) are simulated. After obtaining these responses, an efficient threshold is selected. Then, the points of the raw image with the most information are extracted according to it. Then, the new images with these points are created, and finally, by combining these images with entropy coefficients, the most salient object is located. After extracting appropriate features, the classifier categorizes the initial image into one of the predefined object categories. Our system was evaluated on the Caltech‐101 dataset. Experimental results demonstrate the efficacy and effectiveness of this novel method of preprocessing.

A Multimodal Intention Detection Sensor Suite for Shared Autonomy of Upper-Limb Robotic Prostheses

Neurorobotic augmentation (e.g., robotic assist) is now in regular use to support individuals suffering from impaired motor functions. A major unresolved challenge, however, is the excessive cognitive load necessary for the human–machine interface (HMI). Grasp control remains one of the most challenging HMI tasks, demanding simultaneous, agile, and precise control of multiple degrees-of-freedom (DoFs) while following a specific timing pattern in the joint and human–robot task spaces. Most commercially available systems use either an indirect mode-switching configuration or a limited sequential control strategy, limiting activation to one DoF at a time. To address this challenge, we introduce a shared autonomy framework centred around a low-cost multi-modal sensor suite fusing: (a) mechanomyography (MMG) to estimate the intended muscle activation, (b) camera-based visual information for integrated autonomous object recognition, and (c) inertial measurement to enhance intention prediction based on the grasping trajectory. The complete system predicts user intent for grasp based on measured dynamical features during natural motions. A total of 84 motion features were extracted from the sensor suite, and tests were conducted on 10 able-bodied and 1 amputee participants for grasping common household objects with a robotic hand. Real-time grasp classification accuracy using visual and motion features obtained 100%, 82.5%, and 88.9% across all participants for detecting and executing grasping actions for a bottle, lid, and box, respectively. The proposed multimodal sensor suite is a novel approach for predicting different grasp strategies and automating task performance using a commercial upper-limb prosthetic device. The system also shows potential to improve the usability of modern neurorobotic systems due to the intuitive control design.

A neuromorphic system for visual object recognition

Abstract Autonomous object recognition in images and videos is a topic of emerging importance in commercial and defense applications. Recent advances in the field of visual neuroscience are increasingly being leveraged to develop biologically-plausible models and algorithms for visual cognition with the ultimate goal of improving object recognition accuracy, speed, and robustness. In this paper, we describe our feasibility attempt at building one such end-to-end neuromorphic visual object recognition architecture and system that is inspired by neuroscience theories of human visual attention and recognition. Our system, called the NVRS (Neuromorphic Visual Recognition System), processes images and videos to first detect and localize objects and then classify them into one of several pre-defined object classes. The NVRS uses modularized algorithms inspired by the Form-and-Color-and-Depth (FACADE) and Laminar-ART (LAMINART) models of human visual attention, search, and object recognition. The NVRS is primarily composed of two encapsulated modules: attention and object recognition. The system was evaluated on simulated scenes, Caltech-101 and COIL-100 datasets, and aerial imagery, with results that demonstrate the efficacy of the NVRS. Lessons learnt from the NVRS can be useful in building practical autonomous visual systems for real-world applications and towards addressing longer-term BICA challenges.

Determination of face position and pose with a learned representation based on labelled graphs

We present a new system for the automatic determination of the position, size and pose of the head of a human figure in a camera image. The system is an extension of the well-known face recognition system [15] to pose estimation. The pose estimation system is characterized by a certain reliability and speed. We improve this performance and speed with the help of statistical estimation methods. In order to make these applicable, we reduce the originally very high dimensionality of our system with the help of a number of a priori principles. We discuss a possible extension of the learning algorithm aiming an autonomous object recognition system at the end of the paper.