We present URSim, a complete Software-in-the-Loop simulation of robotic systems, specially designed to meet the needs of testing platforms for planetary exploration. By simulating the sensors of a robotic system and p...
详细信息
ISBN:
(数字)9781665437608
ISBN:
(纸本)9781665437615
We present URSim, a complete Software-in-the-Loop simulation of robotic systems, specially designed to meet the needs of testing platforms for planetary exploration. By simulating the sensors of a robotic system and providing similar interfaces to the real system, URSim enables developing and continuous testing of high-level software components in various scenarios. URSim is based on the Unreal Engine 4, which offers photo-realistic visual and physics support in real-time. A generic robot interface allows the integration of different robotic systems with various sensors that are simulated in real-time. Its modern and adaptable system architectures make it possible to customize URSim for different setups, frameworks, and modules. To demonstrate URSim and its advances, we simulate different robotic systems, including the Lightweight Rover Unit (LRU), the hexacopter ARDEA and the humanoid robot Rollin’ Justin. We integrate the complete navigation and mapping pipeline of the LRU in URSim and conduct an exploration mission in a simulated Martian and Lunar environment.
Nowadays, the problem of forecasting complex signals is significant and has many applications in real life. One of such applications is the prediction of neurophysiological signals, like EEG. Such signals are macrosco...
详细信息
This paper presents a novel application of Path Following and Nonlinear Model Predictive Control techniques to a tendon-actuated snake robot with rolling joints. The study investigates the efficacy of NMPC in guiding ...
详细信息
ISBN:
(数字)9798350370942
ISBN:
(纸本)9798350370959
This paper presents a novel application of Path Following and Nonlinear Model Predictive Control techniques to a tendon-actuated snake robot with rolling joints. The study investigates the efficacy of NMPC in guiding the robot’s end-effector along predefined trajectories in the robot output space, emphasizing its relevance for inspection and maintenance tasks in cluttered environments where traditional manipulators may be impractical or ineffective. The particular mechanical design of the snake robot presents unique challenges, necessitating nonlinear control strategies that take into account constraints in both state and input spaces. The simulation results will demonstrate the effectiveness of NMPC in achieving an accurate convergence to the reference path, and will evaluate its potential, in terms of computational burden, for future development into real-world scenarios.
This article aims to show the results of a Final Degree Project where electronics combines with other fields for the development of precision positioning systems. Thus, electronics, mechanics, computation and control ...
详细信息
ISBN:
(数字)9798350348675
ISBN:
(纸本)9798350348682
This article aims to show the results of a Final Degree Project where electronics combines with other fields for the development of precision positioning systems. Thus, electronics, mechanics, computation and control come together in real time for innovation in these cutting-edge devices, whose development is a revolution for today's industry. This transversal methodology as the axis of electronics engineering is in line with the philosophy of the development of practices for students within the Department of Electronics of University of Málaga.
Rescue robotics sets high requirements to perception algorithms due to the unstructured and potentially vision-denied environments. Pivoting Frequency-Modulated Continuous Wave radars are an emerging sensing modality ...
详细信息
ISBN:
(数字)9798350377705
ISBN:
(纸本)9798350377712
Rescue robotics sets high requirements to perception algorithms due to the unstructured and potentially vision-denied environments. Pivoting Frequency-Modulated Continuous Wave radars are an emerging sensing modality for SLAM in this kind of environment. However, the complex noise characteristics of radar SLAM makes, particularly indoor, applications computationally demanding and slow. In this work, we introduce a novel radar SLAM framework, RaNDT SLAM, that operates fast and generates accurate robot trajectories. The method is based on the Normal Distributions Transform augmented by radar intensity measures. Motion estimation is based on fusion of motion model, IMU data, and registration of the intensity-augmented Normal Distributions Transform. We evaluate RaNDT SLAM in a new benchmark dataset and the Oxford Radar RobotCar dataset. The new dataset contains indoor and outdoor environments besides multiple sensing modalities (LiDAR, radar, and IMU).
This paper aims to highlight the outcomes of a demonstrator where a Stewart platform and its Digital Twin are developed within the scope of a Final Degree Project. First, an exhaustive charaterization of the sensors a...
详细信息
ISBN:
(数字)9798350348675
ISBN:
(纸本)9798350348682
This paper aims to highlight the outcomes of a demonstrator where a Stewart platform and its Digital Twin are developed within the scope of a Final Degree Project. First, an exhaustive charaterization of the sensors and actuators was performed, followed by the assembly of both the mechanical and electronic elements of the Stewart Platform. Afterwards, the Hexapod was programmed, set up and calibrated and, finally, a user interface that combines the digital twin animation with other dynamic inputs and outputs is developed to interact with the real prototype. This cross-disciplinary methodology, as the core of electronic engineering, aligns with the philosophy of laboratory practices for students in the Electronics Department at University of Málaga.
Accurate victim localization in Remote, Outdoor, Unstructured, and Disaster (ROUD) scenarios remains a significant challenge due to limited infrastructure, complex terrains, and time constraints inherent in Search and...
详细信息
Automatic Robotic Assembly Sequence Planning (RASP) can significantly improve productivity and resilience in modern manufacturing along with the growing need for greater product customization. One of the main challeng...
Automatic Robotic Assembly Sequence Planning (RASP) can significantly improve productivity and resilience in modern manufacturing along with the growing need for greater product customization. One of the main challenges in realizing such automation resides in efficiently finding solutions from a growing number of potential sequences for increasingly complex assemblies. Besides, costly feasibility checks are always required for the robotic system. To address this, we propose a holistic graphical approach including a graph representation called Assembly Graph for product assemblies and a policy architecture, Graph Assembly Processing Network, dubbed GRACE for assembly sequence generation. With GRACE, we are able to extract meaningful information from the graph input and predict assembly sequences in a step-by-step manner. In experiments, we show that our approach can predict feasible assembly sequences across product variants of aluminum profiles based on data collected in simulation of a dual-armed robotic system. We further demonstrate that our method is capable of detecting infeasible assemblies, substantially alleviating the undesirable impacts from false predictions, and hence facilitating real-world deployment soon. Code and training data are available at https://***/DLR-RM/GRACE.
Designing for rapid maintenance requires an approach whereby the replacement of rapidly wearing sub-assemblies can be easily replaced while ensuring that the degree of wear can be tracked in real-time if possible. The...
详细信息
In recent years, competition within Radio Frequency (RF) communication bands has led to an overlap between the U-NII-4 band used by low-cost consumer devices, and the Dedicated Short Communication Band (DSRC) used by ...
详细信息
暂无评论