State estimation is a crucial component for the successful implementation of robotic systems, relying on sensors such as cameras, LiDAR, and IMUs. However, in real-world scenarios, the performance of these sensors is ...
详细信息
ISBN:
(纸本)9798350384581;9798350384574
State estimation is a crucial component for the successful implementation of robotic systems, relying on sensors such as cameras, LiDAR, and IMUs. However, in real-world scenarios, the performance of these sensors is degraded by challenging environments, e.g. adverse weather conditions and low-light scenarios. The emerging 4D imaging radartechnology is capable of providing robust perception in adverse conditions. Despite its potential, challenges remain for indoor settings where noisy radardata does not present clear geometric features. Moreover, disparities in radardata resolution and field of view (FOV) can lead to inaccurate measurements. While prior research has explored radar-inertial odometry based on Doppler velocity information, challenges remain for the estimation of 3D motion because of the discrepancy in the FOV and resolution of the radarsensor. In this paper, we address Doppler velocity measurement uncertainties. We present a method to optimize body frame velocity while managing Doppler velocity uncertainty. Based on our observations, we propose a dual imaging radar configuration to mitigate the challenge of discrepancy in radardata. To attain high-precision 3D state estimation, we introduce a strategy that seamlessly integrates radardata with a consumer-grade IMU sensor using fixed-lag smoothing optimization. Finally, we evaluate our approach using real-world 3D motion data.
With the continuous development of data storage, analysis, processing and other technologies, people are eager to visualize the mining process of complex data, and data mining visualizationtechnology is gradually app...
详细信息
The Earth's geological diversity exposes regions to various natural hazards, including earthquakes, landslides, and volcanic eruptions, with soil displacement posing significant risks to infrastructure stability a...
详细信息
ISBN:
(纸本)9798350389937;9798350389920
The Earth's geological diversity exposes regions to various natural hazards, including earthquakes, landslides, and volcanic eruptions, with soil displacement posing significant risks to infrastructure stability and agricultural productivity. Previous landslide monitoring systems encountered challenges such as data transmission stability and the vulnerability of power supply systems. In response, a soil displacement monitoring system is proposed, integrating extensometer sensors with advanced fiber optic communication technology and a laser-based power system. Extensometer sensors, known for their precise soil displacement measurements, face difficulties in long-distance data transmission, addressed by fiber optic communication offering higher bandwidth and extended transmission distances. The laser-based power system enhances system reliability and efficiency through fiber optics, ensuring uninterrupted operation even in remote locations. System accessibility is further facilitated with a Python-based graphical user interface (GUI) for real-time datavisualization. The system's performance is validated through comprehensive soil displacement simulations, supported by continuous monitoring using a rain simulator to observe potential displacements. This integrated approach, leveraging a robust laser-based power system and advanced communication technology, aims to enhance disaster management strategies in geologically active regions.
With the rapid development of artificial intelligence technology, simultaneous localization and mapping (SLAM), as a key technology, has attracted widespread attention. However, laser-based SLAM technology suffers fro...
详细信息
ISBN:
(纸本)9798350387780;9798350387797
With the rapid development of artificial intelligence technology, simultaneous localization and mapping (SLAM), as a key technology, has attracted widespread attention. However, laser-based SLAM technology suffers from significant drift issues. A heterogeneous sensordata fusion algorithm aimed at improving the performance of SLAM is proposed in this paper. First, data from laser radar and the Inertial Measurement Unit (IMU) is collected. Then, the Cartographer algorithm itself employs the Extended Kalman Filter (EKF) method to fuse the data from both sources, ultimately constructing a 2D SLAM framework for environmental mapping. Laser radardata and FAN data from three different experimental scenarios are collected, and the mentioned algorithm is utilized to fuse the data for map construction. The error between the constructed map and the real map is compared, demonstrating that the heterogeneous sensordata fusion-based SLAM algorithm in this paper outperforms single lidar Cartographer. It overcame the issue of rotational drift and exhibited promising application potential.
We connected pH sensor and solar cell into Arduino Board to control data transmission via red laser communication or popular known as visible light communication (VLC). The sensor was calibrated through pH water solut...
详细信息
ISBN:
(纸本)9798350389937;9798350389920
We connected pH sensor and solar cell into Arduino Board to control data transmission via red laser communication or popular known as visible light communication (VLC). The sensor was calibrated through pH water solution measurement compared with conventional pH Meter. This sensor collected and then modulated pH data in Arduino to be sent via laser beam. The beam is captured by solar cell which acts as a photodetector in receiver. The received data will be demodulated in Arduino to be displayed in serial monitor to observe the communication performance. As the result, the link distance of laser communication can reach 35 m using 1-PWM and 15 m using 2-PWM, in free-space environment. When the transmission channel was changed into water environment, the link distance will decrease severely. The prototype output of this work will be a future self-powered modem for water surface and underwater monitoring system.
radartechnology has been a cornerstone of numerous applications, from aviation to meteorology, offering invaluable capabilities for object detection and tracking. Traditional radar systems, while powerful, often come...
详细信息
Micro-Doppler radar is a cutting-edge technology that has revolutionized the field of radar sensing to enable the detection and characterization of complex targets by leveraging their micro-motion dynamics. This paper...
详细信息
ISBN:
(纸本)9781510674158;9781510674141
Micro-Doppler radar is a cutting-edge technology that has revolutionized the field of radar sensing to enable the detection and characterization of complex targets by leveraging their micro-motion dynamics. This paper discusses the design and construction of a 10-GHz continuous wave (CW) micro-Doppler radar, an explanation of how the system operates and extracts data, as well as a discussion of the device's possible applications for characterizing external vibrations of vehicles under different scenarios. The objective is to highlight the potential of micro-Doppler radar for remotely recognizing vehicle transmission shifts and occupancy.
For autonomous driving applications, knowledge of the ego position, orientation, and velocity is a necessary prerequisite for recognizing landmarks and moving targets. We use radarsensors for the determination of the...
详细信息
ISBN:
(纸本)9798350371420;9781737749769
For autonomous driving applications, knowledge of the ego position, orientation, and velocity is a necessary prerequisite for recognizing landmarks and moving targets. We use radarsensors for the determination of these quantities in a radar odometry system. radar odometry uses the advantage of a direct measurement of the radial speed using radarsensors. radarsensors are less susceptible to bad weather and lighting conditions than camera and lidar sensors. In addition, radardata is not susceptible to wheel slippage or blocked wheels compared with wheel speed measurements. However, radardata is still susceptible to clutter. In order to achieve a combination of good precision under optimal conditions and good precision under adverse weather conditions, we fuse measurements from radarsensors, wheel speed sensors and the gyrometer. We do not simply combine these measurements according to assumed covariances. Instead, we check the plausibility of the measurements based on their likelihood. Subsequently, we weight the results of the sensor combinations accordingly. The decision about sensor weighting is carried out in a principled, probabilistic manner and adaptively with regard to environmental influences. We validate our approach using real data. Our approach is more precise under adverse conditions than using wheel speed sensors and gyrometers alone. On the other hand, it is more precise under good conditions than using only radar measurements.
In the realm of autonomous driving, millimeter-wave radar is widely acknowledged as a potent and cost-effective solution for object recognition. In this paper, we propose an improved RAMP-CNN network for radar object ...
详细信息
ISBN:
(纸本)9798350389968
In the realm of autonomous driving, millimeter-wave radar is widely acknowledged as a potent and cost-effective solution for object recognition. In this paper, we propose an improved RAMP-CNN network for radar object recognition by optimizing high-dimensional data projection branches, eliminating the feature fusion and introducing a coherence loss function. Our experiments, conducted on a self-collected multi-person radardataset, illustrate that the enhanced network achieved approximately 3% improvement, attaining an average precision (AP) of 84.7% and an average recall (AR) of 88.6% in object detection performances.
In today's world, a sensor-based autonomous industry needs a range of sensors to understand its environment and decide how to function safely and productively. The precise and trustworthy assessment of the surroun...
详细信息
ISBN:
(纸本)9798350370058;9798350370164
In today's world, a sensor-based autonomous industry needs a range of sensors to understand its environment and decide how to function safely and productively. The precise and trustworthy assessment of the surroundings around a vehicle has made a variety of autonomous or assisted driving approaches possible. Hence, we provide a novel radar camera fusion technique based on deep learning that greatly enhances object identification performance. The combination of radar and camera data in particular has emerged as a promising strategy for improving the precision and dependability of object identification systems. However, the performance of current fusion algorithms is frequently constrained by issues with occlusion, variable illumination, and sensor noise. With enhancing capabilities of autonomous vehicles through different algorithms and perception methodologies, it has become important to look into the importance of computationally lighter algorithms which work efficiently as well. Based on the knowledge gleaned from analyzing several deep learning models, we came up with a modified fusion algorithm by adding a number of new operations. The processes of this algorithm consist of improved object identification techniques, feature extraction, and feature fusion. Our approach successfully addresses the issues posed by occlusion, varying illumination, and sensor noise by utilizing the complementary nature of radar and camera technologies, resulting in enhanced object detection performance. In conclusion, this study offers a cutting-edge deep learning-based radar camera fusion technique that surpasses current methods for object detection. Our approach provides improved accuracy, robustness, and real-time performance by using insights from several deep-learning models and including extra processes. The suggested approach provides a sizable improvement in sensor fusion methods, opening the door for more improvements to perception system enhancement.
暂无评论