Search Results (821)

Visual Question Answering (VQA) models fail catastrophically on questions related to the reading of text-carrying images. However, TextVQA aims to answer questions by understanding the scene texts in an image–question context, such as the brand name of a product or the time on a clock from an image. Most TextVQA approaches focus on objects and scene text detection, which are then integrated with the words in a question by a simple transformer encoder. The focus of these approaches is to use shared weights during the training of a multi-modal dataset, but it fails to capture the semantic relations between an image and a question. In this paper, we proposed a Scene Graph-Based Co-Attention Network (SceneGATE) for TextVQA, which reveals the semantic relations among the objects, the Optical Character Recognition (OCR) tokens and the question words. It is achieved by a TextVQA-based scene graph that discovers the underlying semantics of an image. We create a guided-attention module to capture the intra-modal interplay between the language and the vision as a guidance for inter-modal interactions. To permit explicit teaching of the relations between the two modalities, we propose and integrate two attention modules, namely a scene graph-based semantic relation-aware attention and a positional relation-aware attention. We conduct extensive experiments on two widely used benchmark datasets, Text-VQA and ST-VQA. It is shown that our SceneGATE method outperforms existing ones because of the scene graph and its attention modules. Full article

For visually impaired people, orientation and mobility are challenging and require a great deal of concentration. Especially unfamiliar routes are difficult to follow. This paper presents a navigation algorithm based on a geographic information system that can be optimally adapted to the needs of this user group. A three-stage process is being developed for this purpose. The first step is to check the map against ISO 19157, followed by map augmentation and the generation of a navigable graph. Finally, a new cost function for an A* algorithm is developed to make the best use of the modified map data and adapt it to the user’s needs. It is shown that map data from the geographic information system OpenStreetMap is well suited to the task, although the map data needs to be verified and augmented with additional information before being used. Finally, we compare the presented solution with a standard A* algorithm. Full article

This paper addresses the problem of relative position-based formation planning for a leader–follower multi-robot setup, where the robots adjust the formation parameters, such as size and three-dimensional orientation, to avoid collisions and progress toward their goal. Specifically, we develop a virtual sub-target-based obstacle avoidance method, which involves a transitional virtual sub-target that guides the robots to avoid obstacles according to obstacle information, target, and boundary. Moreover, we develop a changing formation strategy to determine the necessity to avoid collisions and a priority-based model to determine which robots move, thus dynamically adjusting the relative distance between the followers and the leader. The backstepping-based sliding motion controller guarantees that the trajectory and velocity tracking errors converge to zero. The proposed robot navigation method can be employed in various environments and types of obstacles, allowing for a formation change. Furthermore, it is efficient and scalable under various numbers of robots. The approach is experimentally verified using three real mobile robots and up to five mobile robots in simulated scenarios. Full article

Three decades ago, telepresence was presented as an idea in the context of remote work and manipulation. Since then, it has evolved into a field combining different technologies and allowing users to have more or less realistic perceptions of immersion in remote environments. This paper reviews telepresence and its recent advances. While not covering all the work conducted in telepresence, this paper provides an array of applications for which telepresence can be envisioned, providing a clear view of the differences between components and functionalities of robotic platforms conceived for telepresence and pointing to the dependence of telepresence on several technological areas. Furthermore, challenges faced by telepresence technologies are shown, with consideration of user experiences. We consider telepresence from different perspectives, focusing on specific parts, making it possible to foresee future directions of research and applications. This review will be useful for researchers working in telepresence and related fields. Full article

As we look towards the future of healthcare, integrating Care Robots (CRs) into health systems is a practical approach to address challenges such as an ageing population and caregiver shortages. However, ethical discussions about the impact of CRs on patients, caregivers, healthcare systems, and society are crucial. This normative research seeks to define an integrative and comprehensive ethical framework for CRs, encompassing a wide range of AI-related issues in healthcare. To build the framework, we combine principles of beneficence, non-maleficence, autonomy, justice, and explainability by integrating the AI4People framework for a Good AI Society and the traditional bioethics perspective. Using the integrated framework, we conduct an ethical assessment of CRs. Next, we identify three key ethical trade-offs and propose remediation strategies for the technology. Finally, we offer design recommendations for responsible development and usage of CRs. In conclusion, our research highlights the critical need for sector-specific ethical discussions in healthcare to fully grasp the potential implications of integrating AI technology. Full article

This paper develops a three-degree-of-freedom sagittal-plane hybrid dynamical systems model of a Groucho-style bounding quadrupedal run. Simple within-stance controls using a modular architecture yield a closed-form expression for a family of hybrid limit cycles that represent bounding behavior over a range of user-selected fore-aft speeds as a function of the model’s kinematic and dynamical parameters. Controls acting on the hybrid transitions are structured so as to achieve a cascade composition of in-place bounding driving the fore-aft degree of freedom, thereby decoupling the linearized dynamics of an approximation to the stride map. Careful selection of the feedback channels used to implement these controls affords infinitesimal deadbeat stability, which is relatively robust against parameter mismatch. Experiments with a physical quadruped reasonably closely match the bounding behavior predicted by the hybrid limit cycle and its stable linearized approximation. Full article

The efficient computation of viewpoints while considering various system and process constraints is a common challenge that any robot vision system is confronted with when trying to execute a vision task. Although fundamental research has provided solid and sound solutions for tackling this problem, a holistic framework that poses its formal description, considers the heterogeneity of robot vision systems, and offers an integrated solution remains unaddressed. Hence, this publication outlines the generation of viewpoints as a geometrical problem and introduces a generalized theoretical framework based on Feature-Based Constrained Spaces ($\mathcal{C}$-spaces) as the backbone for solving it. A $\mathcal{C}$-space can be understood as the topological space that a viewpoint constraint spans, where the sensor can be positioned for acquiring a feature while fulfilling the constraint. The present study demonstrates that many viewpoint constraints can be efficiently formulated as $\mathcal{C}$-spaces, providing geometric, deterministic, and closed solutions. The introduced $\mathcal{C}$-spaces are characterized based on generic domain and viewpoint constraints models to ease the transferability of the present framework to different applications and robot vision systems. The effectiveness and efficiency of the concepts introduced are verified on a simulation-based scenario and validated on a real robot vision system comprising two different sensors. Full article

Soft pneumatic grippers (SPGs) have garnered significant attention and recognition in various industries owing to their remarkable flexibility, safety, and adaptability. They excel in manipulating delicate, irregularly shaped, and soft objects, surpassing the limitations of conventional grippers. However, effective control techniques for managing the grasping profile of SPGs are still under development. Simple on–off pressure control using a regulator valve is inadequate for delicate gripping with pneumatic robot grippers. To address this, a synergy pressure control system was implemented. In addition, a proportional–integral–derivative control technique, complemented by an unknown input observer, was devised to control the volume of the soft pneumatic robotic gripper, ensuring its alignment with the desired volume level. The simulation and experimental results provide substantial evidence of the effectiveness of the developed control technique and the unknown input observer in managing the volume and pressure of the gripper. Consequently, this breakthrough empowers precise and delicate gripping actions, enabling the handling of delicate objects such as tofu. Full article

Exoskeleton devices are designed for applications such as rehabilitation, assistance, and haptics. Due to the nature of physical human–machine interaction, designing and operating these devices is quite challenging. Optimization methods lessen the severity of these challenges and help designers develop the device they need. In this paper, we present an extensive and systematic literature search on the optimization methods used for the mechanical design of exoskeletons. We completed the search in the IEEE, ACM, and MDPI databases between 2017 and 2023 using the keywords “exoskeleton”, “design”, and “optimization”. We categorized our findings in terms of which limb (i.e., hand, wrist, arm, or leg) and application (assistive, rehabilitation, or haptic) the exoskeleton was designed for, the optimization metrics (force transmission, workspace, size, and adjustability/calibration), and the optimization method (categorized as evolutionary computation or non-evolutionary computation methods). We discuss our observations with respect to how the optimization methods have been implemented based on our findings. We conclude our paper with suggestions for future research. Full article

This research proposes a robust nonlinear hybrid control approach to the speed control of a multi-input-and-multi-output separately excited DC motor (SEDCM). The motor that was under consideration experienced parametric uncertainties and load disturbances in the weak field region. The proposed technique aims to merge the benefits of adaptive backstepping (AB) and integral sliding mode control (ISMC) to enhance the overall system’s robustness. The unknown parameters with load disturbances are estimated using an adaptation law. These estimated parameters are incorporated into the controller design, to achieve a highly robust controller. The theoretical stability of the system is proved using the Lyapunov stability criteria. The effectiveness of the proposed AB–ISMC was demonstrated by simulation, to track the reference speed under parametric uncertainties and load disturbances. The control performance of the proposed technique was compared to that of feedback linearization (FBL), conventional sliding mode control (SMC), and AB control laws without and with the adaptation law. Regression parameters, such as integral square error, integral absolute error, and integral time absolute error, were calculated to quantitatively analyze the tracking performance and robustness of the implemented nonlinear control techniques. The simulation results demonstrated that the proposed controller could accurately track the reference speed and exhibited robustness, with steady-state error accuracy. Moreover, AB–ISMC overperformed, compared to the FBL, SMC, AB controller without adaptation law and AB controller with adaptation law, in reducing the settling time by factors of $27\%$, $67\%$, $23\%$, and $21\%$, respectively, thus highlighting the superior performance of the proposed controller. Full article

In recent years, Embodied AI has become one of the main topics in robotics. For the agent to operate in human-centric environments, it needs the ability to explore previously unseen areas and to navigate to objects that humans want the agent to interact with. This task, which can be formulated as ObjectGoal Navigation (ObjectNav), is the main focus of this work. To solve this challenging problem, we suggest a hybrid framework consisting of both not-learnable and learnable modules and a switcher between them—SkillFusion. The former are more accurate, while the latter are more robust to sensors’ noise. To mitigate the sim-to-real gap, which often arises with learnable methods, we suggest training them in such a way that they are less environment-dependent. As a result, our method showed top results in both the Habitat simulator and during the evaluations on a real robot. Full article

In this paper, we propose a solution for the problem of searching for multiple targets by a group of mobile agents with sensing errors of the first and the second types. The agents’ goal is to plan the search and follow its trajectories that lead to target detection in minimal time. Relying on real sensors’ properties, we assume that the agents can detect the targets in various directions and distances; however, they are exposed to first- and second-type statistical errors. Furthermore, we assume that the agents in the group have errorless communication with each other. No central station or coordinating agent is assumed to control the search. Thus, the search follows a fully distributed decision-making process, in which each agent plans its path independently based on the information about the targets, which is collected independently or received from the other agents. The suggested solution includes two algorithms: the Distributed Expected Information Gain (DEIG) algorithm, which implements dynamic Voronoi partitioning of the search space and plans the paths by maximizing the expected one-step look-ahead information per region, and the Collective Q-max (CQM) algorithm, which finds the shortest paths of the agents in the group by maximizing the cumulative information about the targets’ locations using deep Q-learning techniques. The developed algorithms are compared against previously developed reactive and learning methods, such as the greedy centralized Expected Information Gain (EIG) method. It is demonstrated that these algorithms, specifically the Collective Q-max algorithm, considerably outperform existing solutions. In particular, the proposed algorithms improve the results by 20% to 100% under different scenarios of noisy environments and sensors’ sensitivity. Full article

This manuscript presents an efficient algorithm for solving the inverse kinematics problem of a 6R robot manipulator to be deployed on embedded control hardware. The proposed method utilizes the geometric relationship between the end-effector and the base of the manipulator, resulting in a computationally efficient solution. The approach aims to minimize computational complexity and memory consumption while maintaining the accuracy and real-time performance demonstrated by simulations and verified by experimental results on an embedded system. Furthermore, the manipulator is analyzed in terms of singularities, limits, the workspace, and general solvability. Due to the simplicity of the algorithm, a platform-independent implementation is possible. As a result, the average calculation time is reduced by a factor of five to eight and the average error is decreased by a factor of fifty compared to a powerful analytical solver. Full article

In recent years, deep learning techniques for processing 3D point cloud data have seen significant advancements, given their unique ability to extract relevant features and handle unstructured data. These techniques find wide-ranging applications in fields like robotics, autonomous vehicles, and various other computer-vision applications. This paper reviews the recent literature on key tasks, including 3D object classification, tracking, pose estimation, segmentation, and point cloud completion. The review discusses the historical development of these methods, explores different model architectures, learning algorithms, and training datasets, and provides a comprehensive summary of the state-of-the-art in this domain. The paper presents a critical evaluation of the current limitations and challenges in the field, and identifies potential areas for future research. Furthermore, the emergence of transformative methodologies like PoinTr and SnowflakeNet is examined, highlighting their contributions and potential impact on the field. The potential cross-disciplinary applications of these techniques are also discussed, underscoring the broad scope and impact of these developments. This review fills a knowledge gap by offering a focused and comprehensive synthesis of recent research on deep learning techniques for 3D point cloud data processing, thereby serving as a useful resource for both novice and experienced researchers in the field. Full article