The use of Unmanned Ground Vehicles (UGVs) and Unmanned Aerial Vehicles (UAVs) has seen significant growth in the research community, industry, and society. Many of these agents are equipped with communication systems...
详细信息
ISBN:
(纸本)9798350310375
The use of Unmanned Ground Vehicles (UGVs) and Unmanned Aerial Vehicles (UAVs) has seen significant growth in the research community, industry, and society. Many of these agents are equipped with communication systems that are essential for completing certain tasks successfully. This has led to the emergence of a new interdisciplinary field at the intersection of robotics and communications, which has been further driven by the integration of UAVs into 5G and 6G communication networks. However, one of the main challenges in this research area is how many researchers tend to oversimplify either the robotics or the communications aspects, hindering the full potential of this new interdisciplinary field. In this paper, we present some of the necessary modeling tools for addressing these problems from both a robotics and communications perspective, using the UAV communications relay as an example.
Cognitive search strategies are highly suitable for Odour Source Localisation (OSL) under turbulent flow conditions where continuous cues are not always available. While reliable, these methods have a known tendency t...
详细信息
ISBN:
(纸本)9783031586750;9783031586767
Cognitive search strategies are highly suitable for Odour Source Localisation (OSL) under turbulent flow conditions where continuous cues are not always available. While reliable, these methods have a known tendency to shift the weight of the search towards exploration, which increases the time and distance required to locate the source. Balancing the trade-off between exploration and exploitation (EE) is crucial since it can directly influence the efficiency and reliability of the mission. However, its understanding from a motion decision perspective still remains unclear with most conclusions being drawn from visual interpretation of the search trajectories or from results of performance metrics. This work aims to study the EE trade-off of cognitive OSL actions by identifying movement patterns and quantifying their values for multiple metrics associated with the decision. A large number of experiments were performed under realistic simulated environments, with the results showing the emergence of multiple well-defined movement patterns and EE tendencies that remain identical across different scenarios.
We present the Grasp Proposal Network (GP-net), a Convolutional Neural Network model which can generate 6-DoF grasps from flexible viewpoints, e.g. as experienced by mobile manipulators. To train GP-net, we synthetica...
详细信息
ISBN:
(纸本)9798350342291
We present the Grasp Proposal Network (GP-net), a Convolutional Neural Network model which can generate 6-DoF grasps from flexible viewpoints, e.g. as experienced by mobile manipulators. To train GP-net, we synthetically generate a dataset containing depth-images and ground-truth grasp information. In real-world experiments, we use the EGAD evaluation benchmark to evaluate GP-net against two commonly used algorithms, the Volumetric Grasping Network (VGN) and the Grasp Pose Detection package (GPD), on a PAL TIAGo mobile manipulator. In contrast to the state-of-the-art methods in robotic grasping, GP-net can be used for grasping objects from flexible, unknown viewpoints without the need to define the workspace and achieves a grasp success of 54.4% compared to 51.6% for VGN and 44.2% for GPD. We provide a ROS package along with our code and pre-trained models at https://***/GP- net/.
This paper deals with synchronization for a class of coupled stochastic reaction-diffusion systems driven by G-Brownian motion (G-CSRDSs, in short). The mean square exponential synchronization criteria for G-CSRDSs ar...
详细信息
The article explores how to resolve challenges in putting together electrical cabinets, particularly in managing wires and cables, with a focus on deformable linear objects (DLO). The study combines complex systems de...
详细信息
Microrobotic systems have shown remarkable capabilities to handle various tasks within the human body, such as transporting drug and performing biopsies. However, the intricate and hostile environment of the gastroint...
详细信息
ISBN:
(纸本)9798350385731;9798350385724
Microrobotic systems have shown remarkable capabilities to handle various tasks within the human body, such as transporting drug and performing biopsies. However, the intricate and hostile environment of the gastrointestinal (GI) tract imposes great challenge for these small-scale robots, due to the narrow pathways and unpredictable obstacles like mucus and convoluted surfaces. In this study, we introduce the new design of a magnetically driven miniaturized robot, named multifunctional magnetic miniature van robot (MVR). This device is uniquely engineered to navigate and adapt to the dynamic GI environment. It is achieved through an innovative design that enables it to overcome physical barriers, accurately disperse medications, and efficiently manage cargo operations. The MVR's operation is enhanced by an external magnetic field, empowering it to carry and maneuver even smaller robotic units through complex, branching paths within the GI tract. It is further complemented by a new mechanism for unloading and retrieving auxiliary robotic units, paving the way for more precise and targeted robotic-assisted medical procedures. This work may provide a significant stride in advancing miniature robotic applications in healthcare.
While the demand for interdisciplinary knowledge is undeniable, there are formidable challenges when offering graduate education to Engineering students. To address that, we designed an educational research project th...
详细信息
Advancements in Automated Driving systems (ADSs) have enabled the achievement of a certain level of autonomy while commuting in a car. However, emergency and high-speed maneuvers still arise as significant challenges ...
详细信息
ISBN:
(纸本)9798350384581;9798350384574
Advancements in Automated Driving systems (ADSs) have enabled the achievement of a certain level of autonomy while commuting in a car. However, emergency and high-speed maneuvers still arise as significant challenges for ADSs due to the intrinsic nonlinearity and fast-paced behavior of such events. These maneuvers are a distinctive feature within the recently established motorsport discipline of Autonomous Racing (AR). In this work, we explore the use of Learning-based Model Predictive Control (LMPC) to address possible model mismatches of the first principles model in high-speed racing. To this end, a Model Predictive Contouring Control (MPCC) (a specific formulation of the standard Model Predictive Control, MPC) is formulated, and a Neural Network (NN) that leverages the use of Feedforward and Recurrent layers is employed to learn the errors of the first principles model. By combining the NN with the first principles model, the LMPC is born, capable of accurately predicting the future with a computational effort compatible with real-time feasibility, effectively handling the vehicle at its limits. Furthermore, the controller can adapt to changing environments by training the NN during the race. The MPCC (formulation without the NN) is deployed on a real autonomous formula student racing car showing an improvement of 16% in mean lap times across the same track between a common geometric controller. The LMPC is analyzed in a high-fidelity simulator, achieving an improvement of 8.9% in mean lap times when compared to the MPCC. Video Playlist - ***/playlist?list=PLxbUnBTSF_WBt9GTMm6vppqskhR-RlOCe
The dynamic and unpredictable nature of environmental elements, such as weather and ground conditions, profoundly influences the efficiency of agricultural robots. Real-time environmental perception is an enabling tec...
详细信息
ISBN:
(纸本)9798350358513;9798350358520
The dynamic and unpredictable nature of environmental elements, such as weather and ground conditions, profoundly influences the efficiency of agricultural robots. Real-time environmental perception is an enabling technology for several agricultural automatic systems, facilitating precise scheduling of tasks like planting, harvesting, and irrigation. Drawing inspiration from successful applications of computer vision in crop health monitoring and AI-driven weather impact prediction, in this paper we propose a system for simultaneous recognition of weather and ground conditions based on computer vision techniques. The system can run in realtime onboard smart cameras, making it affordable at low cost. After providing a detailed description of its architecture and methodology, we conduct extensive experiments to demonstrate the effectiveness of the system in real-world conditions and its significance in advancing agricultural robotics, fostering sustainable farming practices by optimizing resource utilization, and mitigating environmental impact.
In 2012, I published a book chapter called "Educational robotics Theories and Practice: tips for how to do it right," focusing on the theoretical foundation of educational robotics and pedagogical approaches...
详细信息
ISBN:
(纸本)9783031384530;9783031384547
In 2012, I published a book chapter called "Educational robotics Theories and Practice: tips for how to do it right," focusing on the theoretical foundation of educational robotics and pedagogical approaches to enhance student learning through educational robotics as a learning tool. The pedagogical approaches include the "learner-centered approach," "project-/inquiry-based approach," "supporting student learning with good scaffolding," and "promoting documentation." The chapter was written even before Computing/Computer science (CS) Education was officially introduced to schools (i.e., The U.K. made computing teaching compulsory from the age of 5 in 2014). The paper revisits the chapter and reexamines the pedagogical approaches, including those in CS education and engineering education, to update the knowledge base to deepen the understanding of the power of educational robotics (ER) in constructionist learning environments. It aims to support educators who are new to ER learning but interested in integrating constructionist ER learning practices in their teacher education or/and teacher professional development programs as well as in their classrooms.
暂无评论