In outdoor environments, ground segmentation is an important pre-processing task for the local environment perception of autonomous vehicle platforms and is the basis for obstacle detection, classification, and path planning. However, existing ground segmentation algorithms primarily focus on dense point cloud data and often struggle to achieve satisfactory accuracy when applied to sparse point cloud data. In light of this challenge, we propose a novel ground segmentation method, LR-Seg, specifically tailored for sparse point cloud data. Our method aims to address the limitations observed in previous approaches and provide improved performance, particularly on sparse point cloud data. To achieve faster processing speed, the method first divides the original point cloud into sub-regions of different sizes based on the distribution characteristics of the sparse point cloud data in the XOY plane. Then, the point clouds are appropriately assigned, and most of the non-ground points in each sub-region are removed using the PCA plane fitting method. Finally, the point cloud geometric feature information within each sub-region is used to reduce over-segmentation. The experimental results show that our method can perform ground segmentation quickly on flat and slope road sections, and the average F1 score can be maintained above 90% with an average time of 3 ms, which is suitable for various road environments.

The continuous configuration changes and velocity variations of tilt-rotor UAVs during the transition phase pose significant challenges to flight safety. Hence, the transition phase trajectory must be specially designed. The transition corridor is an effective means of characterizing the controllable flight state and safe flight boundary of the tilt-rotor UAV transition phase. However, the conventional transition corridor is established based on the trim criterion, which cannot fully characterize the dynamic characteristics of the transition phase, resulting in deviations in the delineation of the flight boundary. This paper proposes a method that characterizes the dynamic transition corridor of a tilt-rotor UAV during the transition phase. A three-dimensional transition corridor considering the nacelle angle, velocity, and angle of attack is established by relaxing the force constraints and introducing angle of attack variables, allowing the dynamic characteristics of acceleration and deceleration in the transition phase to be characterized. On this basis, a transition trajectory optimization method based on the three-dimensional dynamic transition corridor is established using pigeon-inspired optimization with an objective that considers the smooth transition of tilt-rotor UAVs. Numerical simulations show that, compared with the transition trajectory obtained using a two-dimensional transition corridor, the proposed method ensures smoother changes in the velocity, nacelle angle, and expected angle of attack during the transition phase, resulting in stronger engineering practicality.

In off-road scenes, the fusion of dual-LiDAR data is crucial for ensuring the accuracy of environmental perception in autonomous vehicles. The terrain in off-road scenes is complex and filled with unstructured information. This leads to significant noise and a lack of distinct structural features in the point cloud data, making traditional point cloud registration methods difficult to apply. To address these issues posed by complex off-road scenes, we propose a novel point cloud fusion framework named Off-Fusion. We first filter and segment the ground in the input point cloud data, focusing on preserving the core features of the ground while effectively removing noise caused by the terrain. Next, we propose a robust and efficient feature point extraction method based on voxel division and curvature weighting, ensuring extracting meaningful and representative feature points from complex off-road scenes. Based on this, we use feature matching to calculate rough relative transformation pairs, providing a high-quality starting position for the Iterative Closest Point (ICP) algorithm, effectively avoiding local optima. Finally, by combining the kd-tree accelerated ICP algorithm, we achieve precise point cloud registration, successfully calculating the optimal rotation and translation matrix between the two LiDARs. The experimental results show that our method significantly improves the quality and speed of data fusion. Compared to some of the most advanced methods, it performs better in off-road scenes, achieving the best results.

Tilt-rotor uncrewed aerial vehicles (UAVs) combine vertical takeoff and landing capability with efficient, long-endurance forward flight. However, transition maneuvers between hover and cruise are particularly challenging due to complex aerodynamic coupling. This article proposes a control method that enables stable flight across the full range of nacelle tilt angles, treating transition not merely as a transient phase but as a robust and controllable flight regime. A velocity-based attitude compensation system combined with a control augmentation strategy is developed to suppress pitching moments caused by longitudinal asymmetry. Additionally, a linear fade-in and fade-out actuator weight optimization strategy is introduced to maximize transition control capability while considering control efficiency and coupling constraints. On this basis, a weighted pseudoinverse control allocation strategy is employed to achieve smooth and accurate actuator coordination in transition flights. Extensive flight experiments are conducted on a newly developed tilt-rotor UAV equipped with tiltable outer wings and inward-inclined tail propellers. The results demonstrate that the proposed method enables stable flight across all nacelle tilt angles and flight speeds, representing a significant advancement in improving the maneuverability of tilt-rotor UAVs.

Random communication delay, delay jitter, and packet loss cause remote bearing measurements in dual-UAV bearing-only cooperative passive localization to arrive after their generation times. Direct fusion of these historical measurements with current local measurements misaligns the observation rays, platform geometry, and target state. Within the Cubature Kalman filter (CKF) framework, this article constructs a timestamped cache that preserves historical states, measurements, and platform geometry, and investigates two processing strategies. The Predictive Compensation Strategy (PCS) migrates a historical angular innovation to the current geometry and inflates its covariance. Timestamp-Aligned Replay (TSA) activates the historical record at the measurement generation time, restores the corresponding dual-platform observation geometry, and propagates the corrected state to the current time. The evaluation jointly considers the baseline terminal-window error B, average-delay sensitivity S, delay-jitter sensitivity J, and packet-loss response intensity L. Monte Carlo communication scans show that, under the tested conditions, TSA achieves lower terminal-window localization error and a more favorable overall communication-disturbance response than CDS and PCS, while incurring higher average computational cost.

The complexities and dynamics of modern driving environments have amplified the uncertainties faced by autonomous driving systems, posing significant challenges to their decision-making processes. This paper introduces a novel reinforcement learning framework inspired by posterior return estimation, designed to enhance safety and foresight in robotic decision-making. To overcome the challenges of long-term dependency in reinforcement learning, a tree structure is utilized to record the interaction history between the agent and the environment. The posterior distribution of returns for each state is estimated from this historical data, with a neural network employed to model this distribution for enhanced decision-making. The framework's efficacy is validated through two decision-making and planning scenarios, where it surpasses several commonly used frameworks and demonstrates notably more anticipatory decision-making patterns.