Location awareness and navigation promote varieties of emerging applications of mobile collaborative multiple uncrewed aerial vehicles (UAVs). Cooperative UAVs fuse the global position system (GPS), inertial navigation systems (INS), peer to peer ranging radios derived from relative navigation of ultra-wideband (UWB) under complicated environments. Those information sources can be incorporated into spatiotemporal cooperation posited by the intra-user measurement of INS and GPS, and the inter-user measurement of the relative navigation of swarm UAVs. This paper considers the localization and navigation of multiple collaborative UAVs in networks with GPS/INS/UWB jammers in the case that the measurements are missed or randomly delayed by a sampling period. In a navigation situation with a partially denied navigation signals (e.g.GPS Jammers for some UAVs, UWB jammers for others, etc.), we propose an improved method of cooperation location for the swarm, allowing measurement jammers concerning the normal sigma point belief propagation (SPBP). This algorithm integrates message passing based on the Bayesian framework, a sigma point belief propagation of random packet loss (SPBP-RPL) to exploit spatiotemporal cooperation and measurement knowledge. Compared with existing general sigma point belief propagation, the advantages of the novel method are validated through a simulation of swarm UAVs with GPS/INS/UWB. Results show that the algorithm of combining spatiotemporal cooperation with measurement knowledge reduces the location uncertainty of swarm UAVs agents and improves location accuracy remarkably.

Rotor unbalance (RUB) and Sensor Runout (SR) are two main vibration sources for active magnetic bearing (AMB) system, and they not only produce considerable harmonic vibration but also endanger the stability of AMB system. Therefore, a nonlinear adaptive algorithm, whose asymptotic stability is guaranteed by Lyapunov's theory, is proposed in this paper to suppress the harmonic vibration. Nevertheless, RUB and the synchronous component of SR have the same frequency with the rotational frequency, and it is highly necessary to distinguish them from each other for the compensation of displacement stiffness force. Hence, the scheme of changing rotor speed is adopted for the permanent magnet biased magnetic bearing system. As a consequence, the harmonic current caused by RUB and SR is effectively attenuated and the displacement stiffness force is correctly compensated. The results of the numerical simulations and experiments demonstrate that the harmonic vibration is dramatically suppressed through the proposed method.

Cooperative perception in the field of connected autonomous vehicles (CAVs) aims to overcome the inherent limitations of single-vehicle perception systems, including long-range occlusion, low resolution, and susceptibility to weather interference. In this regard, we propose a high-precision 3D object detection V2V cooperative perception algorithm. The algorithm utilizes a voxel grid-based statistical filter to effectively denoise point cloud data to obtain clean and reliable data. In addition, we design a feature extraction network based on the fusion of voxels and PointPillars and encode it to generate BEV features, which solves the spatial feature interaction problem lacking in the PointPillars approach and enhances the semantic information of the extracted features. A maximum pooling technique is used to reduce the dimensionality and generate pseudoimages, thereby skipping complex 3D convolutional computation. To facilitate effective feature fusion, we design a feature level-based crossvehicle feature fusion module. Experimental validation is conducted using the OPV2V dataset to assess vehicle coperception performance and compare it with existing mainstream coperception algorithms. Ablation experiments are also carried out to confirm the contributions of this approach. Experimental results show that our architecture achieves lightweighting with a higher average precision (AP) than other existing models.

Existing studies on autonomous driving methods focus on the fusion of onboard sensor data. However, the driving behavior might be unsteady because of the uncertainties of environments. In this article, an expectation line is proposed to quantify the driving behavior motivated by the driving continuity of human drivers. Furthermore, the smooth driving could be achieved by predicting the future trajectory of the expectation line. First, a convolutional neural network-based method is applied to detect lanes in images sampled from driving video. Second, the expectation line is defined to model driving behavior of an autonomous vehicle. Finally, the long short-term memory-based method is applied to the expectation line so that the future trajectory of the vehicle could be predicted. By incorporating convolutional neural network- and long short-term memory-based methods, the autonomous vehicles could smoothly drive because of the prior information. The proposed method is evaluated using driving video data, and the experimental results demonstrate that the proposed method outperforms methods without trajectory predictions.

Cooperative localization is critical for multi-robot systems to accurately ascertain their positions in the environment. This paper presents a robust and convergent distributed cooperative localization algorithm to effectively address localization inaccuracies and inconsistency caused by intermittent or limited absolute observation capabilities. The algorithm integrates three key modules: propagation, observation, and communication, enabling each robot to estimate its states and measure noise covariance simultaneously. To enhance the estimation consistency, inter-vehicle relative observations and landmark absolute observations are modeled as multi-Bernoulli random finite sets (RFSs), with robot states updated using a coupled correlation scheme. By combining extended particle filtering, and covariance intersection techniques, the algorithm efficiently handles intermittent observations, leading to substantial improvements in localization accuracy and estimation consistency. Further, the proofs of convergent consistency are provided in the paper, validating the algorithm’s robustness and convergence.

Position and orientation system (POS) is a high-precision inertial navigation systems/Global navigation satellite system (INS/GNSS) integrated system that can continuously provide time-spatial reference for airborne remote sensing, mobile mapping and vehicle localization using Kalman Filter (KF) during the availability of GPS measurements. However, the POS suffers from the GPS outages in some especial environment, whose accuracy of motion parameters degrades with the time accumulation. In order to suppress the performance degradation caused by GPS outages, this work proposes a hybrid predictor based on data-driven Deep Gaussian Process Regression (DGPR), which uses multi-layer Gaussian Process Regression to deal with highly complex data relationships and predictive uncertainty. Once GPS outages happen, the proposed approach starts to predict the observation measurement, and then feeds it to KF as a virtual update to estimate all the INS errors. The proposed approach is validated by the real flight test, and the experimental results show that significant performance improvement has been achieved during various GPS outages.