检索结果-内蒙古大学图书馆

Memory-Efficient Graph Convolutional Networks for Object Classification and Detection with Event Cameras

学校读者我要写书评

暂无评论

TechRxiv

TechRxiv 2023年

作者： Jeziorek, Kamil Pinna, Andrea Kryjak, Tomasz Embedded Vision Systems Group Department of Automatic Control and Robotics AGH University Krakow Poland Sorbonne Universite CNRS LIP6 ParisF-75005 France

Recent advances in event camera research emphasize processing data in its original sparse form, which allows the use of its unique features such as high temporal resolution, high dynamic range, low latency, and resistance to image blur. One promising approach for analyzing event data is through graph convolutional networks (GCNs). However, current research in this domain primarily focuses on optimizing computational costs, neglecting the associated memory costs. In this paper, we consider both factors together in order to achieve satisfying results and relatively low model complexity. For this purpose, we performed a comparative analysis of different graph convolution operations, considering factors such as execution time, the number of trainable model parameters, data format requirements, and training outcomes. Our results show a 450-fold reduction in the number of parameters for the feature extraction module and a 4.5-fold reduction in the size of the data representation while maintaining a classification accuracy of 52.3%, which is 6.3% higher compared to the operation used in state-of-the-art approaches. To further evaluate performance, we implemented the object detection architecture and evaluated its performance on the N-Caltech101 dataset. The results showed an accuracy of 53.7% mAP@0.5 and reached an execution rate of 82 graphs per second. © 2023, CC BY.

关键词： Convolution

Memory-Efficient Graph Convolutional Networks for Object Classification and Detection with Event Cameras

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Jeziorek, Kamil Pinna, Andrea Kryjak, Tomasz Embedded Vision Systems Group Department of Automatic Control and Robotics AGH University of Krakow Poland Sorbonne Universite CNRS LIP6 ParisF-75005 France

关键词： Cameras

Implementation of a perception system for autonomous vehicles using a detection-segmentation network in SoC FPGA

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Baczmanski, MacIej Wasala, Mateusz Kryjak, Tomasz Embedded Vision Systems Group Computer Vision Laboratory Department of Automatic Control and Robotics Agh University of Krakow Al. Mickiewicza 30 Krakow30-059 Poland

Perception and control systems for autonomous vehicles are an active area of scientific and industrial research. These solutions should be characterised by both high efficiency in recognising obstacles and other environmental elements in different road conditions, real-time capability, and energy efficiency. Achieving such functionality requires an appropriate algorithm and a suitable computing platform. In this paper, we have used the MultiTaskV3 detection-segmentation network as the basis for a perception system that can perform both functionalities within a single architecture. It was appropriately trained, quantised, and implemented on the AMD Xilinx Kria KV260 Vision AI embedded platform. By using this device, it was possible to parallelise and accelerate the computations. Furthermore, the whole system consumes relatively little power compared to a CPU-based implementation (an average of 5 watts, compared to the minimum of 55 watts for weaker CPUs, and the small size (119mm x 140mm x 36mm) of the platform allows it to be used in devices where the amount of space available is limited. It also achieves an accuracy higher than 97% of mAP (mean average precision) for object detection and above 90% of mIoU (mean intersection over union) score for image segmentation. The article also details the design of the Mecanum wheel vehicle, which was used to test the proposed solution in a mock-up city. © 2023, CC BY.

关键词： Field programmable gate arrays (FPGA)

LiDAR-based drone navigation with reinforcement learning

学校读者我要写书评

暂无评论

TechRxiv

TechRxiv 2023年

作者： Miera, Pawel Szolc, Hubert Kryjak, Tomasz Embedded Vision Systems Group Computer Vision Laboratory Department of Automatic Control and Robotics AGH University of Science and Technology Al. Mickiewicza 30 Krakow30-059 Poland

Reinforcement learning is of increasing importance in the field of robot control and simulation plays a key role in this process. In the unmanned aerial vehicles (UAVs, drones), there is also an increase in the number of published scientific papers involving this approach. In this work, an autonomous drone control system was prepared to fly forward (according to its coordinates system) and pass the trees encountered in the forest based on the data from a rotating LiDAR sensor. The Proximal Policy Optimization (PPO) algorithm, an example of reinforcement learning (RL), was used to prepare it. A custom simulator in the Python language was developed for this purpose. The Gazebo environment, integrated with the Robot Operating System (ROS), was also used to test the resulting control algorithm. Finally, the prepared solution was implemented in the Nvidia Jetson Nano eGPU and verified in the real tests scenarios. During them, the drone successfully completed the set task and was able to repeatably avoid trees and fly through the forest. © 2023, CC BY.

关键词： Drones

LiDAR-based drone navigation with reinforcement learning

学校读者我要写书评

暂无评论

arXiv 2023年

关键词： Robot Operating System

Hybrid Unmanned Aerial Underwater Vehicles: A Survey on Concepts and Technologies

学校读者我要写书评

暂无评论

SSRN

SSRN 2023年

作者： Pinheiro, Pedro Miranda Dias de Oliveira Evald, Paulo Jefferson Grando, Ricardo Bedin Neto, Armando Alves Jorge Drews, Paulo Lilles Intelligent Robotics and Automation Group Federal University of Rio Grande Rio Grande Brazil Intelligent Systems and Control Group Federal University of Pelotas Pelotas Brazil Department of Robotics Technological University of Uruguay Rivera Uruguay Department of Electronic Engineering Federal University of Minas Gerais Belo Horizonte Brazil

Hybrid Unmanned Aerial Underwater Vehicle (HUAUV) is a class of multi-modal mobile robots characterized by the ability to fly and navigate underwater, as well as being able to perform the transition between both environments. The development of modern vehicles of this class is driven by the enhancement of mobile robotic systems, sensors, and control techniques. However, the class definition and hierarchy for these vehicles are still vague and undefined. Therefore, this work presents a survey of concepts and prototypes of HUAUVs, developed from 2010 until 2022. The search for works was performed in relevant international conference proceedings and journals. We present a classification of state-of-the-art concepts and prototypes of HUAUVs based on specific main features of vehicles, allowing the identification of trends in HUAUV development, and an actuator-based taxonomy for HUAUVs. Hence, our categorization provides a more cohesive background for future works, as well as a better understanding of the main features of hybrid vehicles. Finally, a pragmatic approach to future applications is provided, given the current trends in Mobile robotics, focusing on unmanned aerial/underwater vehicles. © 2023, The Authors. All rights reserved.

关键词： Antennas

Epistemic uncertainty estimation with evidential learning on semantic segmentation of underwater images

学校读者我要写书评

暂无评论

Epistemic uncertainty estimation with evidential learning on...

IEEE Latin American robotics Symposium, LARS

作者： Gustavo Henrique Do Nascimento Paulo Jefferson Dias De Oliveira Evald Paulo Lilles Jorge Drews Intelligent Robotics and Automation Group Federal University of Rio Grande Rio Grande Brazil Intelligent Systems and Control Group Federal University of Pelotas Pelotas Brazil

ISBN: (数字)9781665462808

ISBN: (纸本)9781665462815

As the evolution of robotics occurs, it has become increasingly common for robotic systems to be integrated with intelligent systems. Despite the relevant advance in the area of neural networks, what happens inside a network is still not completely comprehended. The uncertainties in the neural network prediction can be epistemic, which is related to the model, or aleatory, which is related to the data. The reliability of network predictions can be increased with uncertainty estimation. Making the fusion of sensor data with trustful predictions, robotic systems could operate in more critical environments, where high accuracy is required, as well as maintaining navigation in the case of sensor fault. Underwater environments suffer from some disturbances that affect the acquisition of images due to light interference or wave movement, and these perturbations make difficult the use of neural networks for underwater robots, due to doubtful predictions. Taking this into account, this paper proposes a methodology to estimate the epistemic uncertainty with the case study in semantic segmentation for underwater images, where the behavior of uncertainty during training is observed, resulting in a qualitative analysis of epistemic uncertainty for Semantic Segmentation. The results suggest estimated epistemic uncertainty is directly connected with the parameters, amounts of epochs, size, and quality of the dataset.

关键词： Training Uncertainty Semantic segmentation Perturbation methods Neural networks Estimation Predictive models

Techno-Economic Assessment of a Large-Scale Electrolysis Plant in Hydrogen and Ancillary Service Markets

学校读者我要写书评

暂无评论

IFAC-PapersOnLine 2024年第13期58卷 140-145页

作者： Yassine Ennassiri Giulio Ferro Michela Robba Gilney Damm Edemar O. Prado DIBRIS—Department of Informatics Bioengineering Robotics and Systems Engineering University of Genova 16145 Italy IMSE Laboratory Gustave Eiffel University Marne-la-Vallée France Power Electronics and Control Research Group GEPOC Federal University of Santa Maria SantaMaria 97105-900 RS Brazil

Hydrogen electrolysis systems have seen considerable interest from energy communities as a potential solution for shifting from fossil-based energy resources to clean energy alternatives. The system consists of transforming electricity into hydrogen via water electrolysis. As it is expected to have a large-scale connection with the grid to compensate the fluctuation of renewables, it is important to understand the system’s technical and economic feasibility. Therefore, this work aims to provide a high-level techno-economic assessment for the participation of a large-scale electrolysis plant in hydrogen and grid ancillary service markets. The plant generates revenue from two sources: hydrogen and frequency regulation. Based on market prices of electricity and hydrogen, a linear programming (LP) optimization has shown that a 50MW electrolysis plant can generate a 33% increase in profit if the plant includes the grid support market in the business model. Additionally, simulations under unstable grid frequency have shown high reactivity of the system to maintain grid stability.

关键词： optimization hydrogen production frequency regulation linear programming

Hardware-in-the-loop simulation of a UAV autonomous landing algorithm implemented in SoC FPGA

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Szolc, Hubert Kryjak, Tomasz Embedded Vision Systems Group Computer Vision Laboratory Department of Automatic Control and Robotics AGH University of Science and Technology Krakow Poland

This paper presents a system for hardware-in-the-loop (HiL) simulation of unmanned aerial vehicle (UAV) control algorithms implemented on a heterogeneous SoC FPGA computing platforms. The AirSim simulator running on a PC and an Arty Z7 development board with a Zynq SoC chip from AMD Xilinx were used. Communication was carried out via a serial USB link. An application for autonomous landing on a specially marked landing strip was selected as a case study. A landing site detection algorithm was implemented on the Zynq SoC platform. This allowed processing a 1280 × 720 @ 60 fps video stream in real time. Performed tests showed that the system works correctly and there are no delays that could negatively affect the stability of the control. The proposed concept is characterised by relative simplicity and low implementation cost. At the same time, it can be applied to test various types of high-level perception and control algorithms for UAV implemented on embedded platforms. We provide the code developed on GitHub, which includes both Python scripts running on the PC and C code running on Arty Z7. © 2022, CC BY.

关键词： System-on-chip