“…Existing works [8], [9] focus on mechanical spinning radars that take spatial constraints to infer the Doppler shift so as to compensate for the map distortion coarsely. They have inferior accuracy due to the lack of radial velocity measurements, making the impact of Doppler distortion still exist in data association, as shown in our study in [10].…”
mentioning
confidence: 74%
“…2) Overall Performance on nuScenes: We compare our approach with 4 SOTA radar metric localization methods, including direct methods (convention ICP [21] and submap NDT [38]), and feature-based method (MC-RANSAC [8] and DC-Loc [10]). Note that the SOTA joint-Doppler-based NDT approach [39] is designed for odometry rather than metric localization.…”
Metric localization is vital to autonomous driving where it corrects cumulative errors in a long-term run. Such errors are inevitable in real scenarios where GPS signals or some other drift-free exteroceptive measurements are not available, e.g., when an automobile goes through a tunnel. Using FMCW-based mmWave radars is an attractive metric localization technique with improved robustness as RF signals can traverse small particles in harsh weather conditions like snowing, foggy, and storming, but it faces a fundamental challenge of Doppler distortion. Existing works take spatial constraints to mitigate the Doppler distortion of point clouds from mechanical radars with limited accuracy. Modern single-chip mmWave radars that provide dynamic estimates, i.e., radial velocities, bring new opportunities to develop more accurate approaches. This paper presents DC-Loc++, a robust metric localization framework by compensating Doppler distortions using a single-chip mmWave radar. It consists of an explicit velocity-assisted Doppler compensation module for each radar sub-map, an uncertainty-aware metric registration algorithm, and a failure recovery method that validates measurement constraints to generate a more confident pose graph for optimizing vehicle poses. Extensive experiments on both nuScenes dataset and a synthetic CARLA dataset show the effectiveness of DC-Loc++, achieving 99.2% success rate and more than 20.0%, 30.2% error reductions in terms of translation and rotation estimates, respectively, compared with existing approaches.
“…Existing works [8], [9] focus on mechanical spinning radars that take spatial constraints to infer the Doppler shift so as to compensate for the map distortion coarsely. They have inferior accuracy due to the lack of radial velocity measurements, making the impact of Doppler distortion still exist in data association, as shown in our study in [10].…”
mentioning
confidence: 74%
“…2) Overall Performance on nuScenes: We compare our approach with 4 SOTA radar metric localization methods, including direct methods (convention ICP [21] and submap NDT [38]), and feature-based method (MC-RANSAC [8] and DC-Loc [10]). Note that the SOTA joint-Doppler-based NDT approach [39] is designed for odometry rather than metric localization.…”
Metric localization is vital to autonomous driving where it corrects cumulative errors in a long-term run. Such errors are inevitable in real scenarios where GPS signals or some other drift-free exteroceptive measurements are not available, e.g., when an automobile goes through a tunnel. Using FMCW-based mmWave radars is an attractive metric localization technique with improved robustness as RF signals can traverse small particles in harsh weather conditions like snowing, foggy, and storming, but it faces a fundamental challenge of Doppler distortion. Existing works take spatial constraints to mitigate the Doppler distortion of point clouds from mechanical radars with limited accuracy. Modern single-chip mmWave radars that provide dynamic estimates, i.e., radial velocities, bring new opportunities to develop more accurate approaches. This paper presents DC-Loc++, a robust metric localization framework by compensating Doppler distortions using a single-chip mmWave radar. It consists of an explicit velocity-assisted Doppler compensation module for each radar sub-map, an uncertainty-aware metric registration algorithm, and a failure recovery method that validates measurement constraints to generate a more confident pose graph for optimizing vehicle poses. Extensive experiments on both nuScenes dataset and a synthetic CARLA dataset show the effectiveness of DC-Loc++, achieving 99.2% success rate and more than 20.0%, 30.2% error reductions in terms of translation and rotation estimates, respectively, compared with existing approaches.
“…Applying artificial sensing systems to provide synthetic data is an efficient method for addressing these issues. A massive amount of virtual data, critical for data-driven downstream tasks such object detection [28], [29], semantic segmentation [30], and self-localization [31], can be collected through descriptive sensing. Taking the widely used LiDAR sensor as an example, it has already been demonstrated that synthetic point cloud data can significantly improve model performance.…”
In the construction of Metaverses, sensors that are referred to as the "bridge of information transmission", play a key role. The functionality and efficiency of today's sensors, which operate in a manner similar to physical sensing, are frequently constrained by their hardware and software. In this research, we proposed the Parallel Sensing framework, which includes background, concept, basic methods and typical application of parallel sensing. In our formulation, sensors are redefined as the integration of real physical sensors and virtual software-defined sensors based on parallel intelligence, in order to boost the performance of the sensors. Each sensor will have a parallel counterpart in the virtual world within the framework of parallel sensing. Digital sensors serve as the brain of sensors and maintain the same properties as physical sensors. Parallel sensing allows physical sensors to operate in discrete time periods to conserve energy, while cloud-based descriptive, predictive, and prescriptive sensors operate continuously to offer compensation data and serve as guardians. To better illustrate parallel sensing concept, we show some example applications of parallel sensing such as parallel vision, parallel point cloud and parallel light fields, both of which are designed by construct virtual sensors to extend small real data to virtual big data and then boost the performance of perception models. Experimental results demonstrate the effective of parallel sensing framework. The interaction between the real and virtual worlds enables sensors to operate actively, allowing them to intelligently adapt to various scenarios and ultimately attain the goal of "Cognitive, Parallel, Crypto, Federated, Social and Ecologic" 6S sensing.
“…We use a large amount of virtual data for models pre-training and conduct fine tuning with small real data. The generated virtual data have alredy been proven effective for object detection [26,27], segmentation [28][29][30][31], and mapping [32][33][34]. Additionally, Descriptive Radars can also be used to extract the hidden features of different traffic scenes to make the model achieve better generalization.…”
Section: Descriptive Radarsmentioning
confidence: 99%
“…With the rapid development of artificial intelligence and computer science, digital twins in cyber-physical systems (CPS) [13][14][15], which are regarded as the key to the next industrial revolution, are being used to construct digital radars in cyberspace to achieve intelligence. Radar models in CPS [16][17][18][19][20][21][22][23][24][25] have already been extensively researched and demonstrated to be effective in solving many problems, including generating virtual data for various downstream tasks [26][27][28][29][30][31][32][33][34] and closed-loop testing.…”
Radar is widely employed in many applications, especially in autonomous driving. At present, radars are only designed as simple data collectors, and they are unable to meet new requirements for real-time and intelligent information processing as environmental complexity increases. It is inevitable that smart radar systems will need to be developed to deal with these challenges and digital twins in cyber-physical systems (CPS) have proven to be effective tools in many aspects. However, human involvement is closely related to radar technology and plays an important role in the operation and management of radars; thus, digital twins’ radars in CPS are insufficient to realize smart radar systems due to the inadequate consideration of human factors. ACP-based parallel intelligence in cyber-physical-social systems (CPSS) is used to construct a novel framework for smart radars, called Parallel Radars. A Parallel Radar consists of three main parts: a Descriptive Radar for constructing artificial radar systems in cyberspace, a Predictive Radar for conducting computational experiments with artificial systems, and a Prescriptive Radar for providing prescriptive control to both physical and artificial radars to complete parallel execution. To connect silos of data and protect data privacy, federated radars are proposed. Additionally, taking mines as an example, the application of Parallel Radars in autonomous driving is discussed in detail, and various experiments have been conducted to demonstrate the effectiveness of Parallel Radars.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.