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.

To address the limitations of the centralized hydraulic steering system used in the first-generation heavy-duty wheeled platform developed by our team, this study proposes a fully electrified steering system based on a compact direct-drive electro-mechanical actuator (DEMA) architecture. Compared with the original hydraulic system, the proposed solution reduces the steering-system weight from approximately 150 kg to 32 kg in the single-channel configuration and 40 kg in the dual-channel configuration, while significantly improving system integration and maintainability. For the single-channel DEMA steering system, a composite control strategy combining three-loop PID control with feedforward compensation is developed to improve dynamic response and position-tracking accuracy. AMESim simulation results under a steering resistance torque of 6000 ± 500 Nm show that the system achieves an overshoot below 2%, a steady-state error below 0.1°, and a tracking error below 0.4°. To reduce motor power and thermal-management requirements, a dual-channel DEMA steering architecture is further proposed. Considering inter-channel parameter differences, a primary–secondary synchronization control strategy is developed to suppress force-fighting behavior and improve motion consistency. Simulation results demonstrate that the proposed strategy effectively reduces synchronization errors and maintains highly consistent force output between channels while preserving excellent steering accuracy and tracking performance. The proposed fully electrified steering system and synchronization control strategy provide an effective solution for improving the dynamic performance, lightweight design, and reliability of heavy-duty wheeled platforms.

Carrier-based aircraft exhibit highly complex coupling characteristics across control channels. To address the control coupling issues encountered during carrier-based aircraft landing, as well as the undershoot phenomenon observed in trajectory adjustment, this paper proposes a direct longitudinal force control method based on the vertical translation mode. The proposed method enables decoupled control of altitude, velocity, and pitch channels while maintaining the aircraft's attitude stability. This approach simplifies the control logic and eliminates the undershoot phenomenon in trajectory adjustment. Furthermore, given the difficulty in acquiring the relative position between the aircraft and the carrier, a Kalman filter-based multi-source signal fusion method is introduced, which effectively suppresses the noise interference in radar signal acquisition by the carrier-based aircraft. Simulation results demonstrate that the proposed composite control method enables rapid trajectory tracking and enhances landing accuracy.

One of the most promising uncrewed aerial vehicles (UAVs), tail-sitter UAVs combine the long endurance of fixed-wing aircraft with the vertical takeoff and landing capabilities of rotary-wing aircraft. This versatility has driven significant research interest over the past decade. However, a comprehensive overview of their development remains lacking. This article presents a comprehensive review of tail-sitter UAVs from a mechatronics perspective, emphasizing their integrated design and flight control technologies. Based on actuator integration methods, tail-sitter UAVs are classified into five types: single rotor (with or without thrust-vectoring), dual rotor (coaxial and parallel), quadrotor (monoplane and biplane), ducted fan, and others. The advantages and limitations of each type are analyzed. Flight control remains a primary challenge for tail-sitter UAVs due to highly variable flight speeds and strongly coupled dynamics during transition maneuvers. Therefore, flight control techniques are systematically reviewed from four aspects: dynamic characteristics analysis, flight corridor development, transition trajectory design, and controller design. Finally, current research gaps and future directions are discussed, particularly in distributed propulsion, hybrid electric systems, autonomous flight, and other areas. The insights provided herein aim to systematically guide future research on tail-sitter UAVs, facilitating their integration into diverse industrial applications.

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.

The passive suspension system based on centralized hydraulic sources suffers from prominent issues such as large space occupancy, low energy efficiency, maintenance difficulties, and insufficient overall performance. To address these issues, this paper innovatively proposes design solutions and control strategies for multiple suspension systems based on distributed hydraulic sources, specifically tailored for heavy-duty special wheeled vehicles. A semi-active suspension system is developed based on both PID control strategy and sky-hook control strategy, which enhances suspension performance under the constraints of limited cost and minimal structural changes. A detailed comprehensive performance simulation model is established, and simulation analysis is conducted under different driving states and road surface conditions. The results indicate that the PID control strategy performs better under dynamic operating conditions such as curves, acceleration, and braking, while the sky-hook control strategy performs better when the vehicle traverses on Class C-F road surfaces. To further enhance the suspension system's performance, active and slow-active suspension systems are designed. By actively applying control forces, the limitations of the semi-active suspension, which can only respond passively, are overcome. Through the integration of road surface recognition technology, the systems can sense the road surface conditions ahead in real time and convert them into control commands in a feedforward form. This significantly improves the dynamic performance of the suspension system and reduces the performance requirements on posture stabilization devices for onboard weapons and other equipment. In terms of vehicle body deflection, vehicle body acceleration, and dynamic tire load, the relevant indicators for the active suspension are reduced to 2.5%, 7.2%, and 7.3% of those for the semi-active suspension, respectively, while the relevant indicators for the slow-active suspension are reduced to 46.3%, 31.4%, and 31.5% of those for the semi-active suspension, respectively.

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.

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.

The flying-wing aircraft is an innovative design that seamlessly integrates the wing and fuselage, offering improved aerodynamics and fuel efficiency. However, due to changes in layout and control surfaces, its attitude control has undergone significant changes. In this paper, the attitude control methods with different control allocation strategies are investigated. Based on a newly developed flying-wing UAV, systematic wind tunnel free flight tests are conducted. Compared with the split-drag-rudder alone, the results show that the addition of differential thrust of electric ducts can effectively enhance heading control capability. The degradation of the stealth performance due to preopening of the split-drag-rudders can thus be avoided. Meanwhile, the elevons exhibit a close tracking in different roll and pitch attitude commands, presenting a good performance in both dynamic and steady-state responses.

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.

Direct-drive PMSM require high dynamic and high precision servo actuator systems. In view of the difficulty of traditional control methods in balancing system dynamics and precision, this paper designs a time-optimized multimode position control strategy with frictional perturbation compensation for velocity observation. Firstly, a characteristic model of the second-order integral system is established. Then, the switching region of the near time-optimal control is given by using the phase plane as an analytical tool; the Bang-Bang optimal control is adopted outside the switching region with the objective of fastness, and the bang-bang suboptimal control is adopted inside the switching region with the objective of avoiding oscillation and overshooting; in order to improve the steady-state performance, the linear control is adopted in the time of small error. The experiments show that this method is fast in response, avoids oscillation and overshoot, and meets the requirement of high dynamic and high accuracy of servo system well.

Flight mechanics/dynamics models are essential for analyzing aircraft flight performance, where aerodynamic data play a critical role. This paper establishes a missile flight dynamics model and investigates the influence of aerodynamic modeling errors based on wind tunnel test data. Common aerodynamic modeling methods are compared, the effects of longitudinal coefficient deviations on the linearized missile model are analyzed using a deviation test approach, and the results are validated through simulations. The results show that interpolation-based aerodynamic modeling may lead to overfitting; segmented or denser Mach number testing is recommended to improve accuracy. Although aerodynamic error models based on derivatives and coefficients are applicable only within limited flight envelopes, they offer faster simulation and convenient uncertainty introduction. The missile’s longitudinal eigenvalue distribution is affected only by CLα, CmCL, and Cmq¯. The frequency domain differences between lift and pitch control surface effects determine the system’s non-minimum phase behavior. Furthermore, aerodynamic uncertainties may increase overshoot risk in a closed-loop control system, highlighting the need for robust control design.

This study investigates the challenges associated with achieving synchronized arrivals in unmanned aerial vehicle (UAV) formations through an integrated approach to trajectory optimization and waypoint allocation. By implementing advanced optimization algorithms, including the Hungarian method, and utilizing Dubins paths for controlled trajectory adjustments, this methodology ensures that all UAVs reach their designated waypoints concurrently, complying with predefined speed and heading constraints. Simulations conducted within a digital twin environment validate the effectiveness of the approach, demonstrating significant reductions in total path length and formation time, thereby enhancing operational efficiency. We introduce innovative modifications to traditional trajectory planning by focusing on minimal adjustments to the initial turning radius, which maintains compliance with trajectory requirements while optimizing the formation's dynamic responses. The proposed strategies enhance operational adaptability to various initial conditions and offer marked improvements over traditional methods in convergence speed and efficiency.

Previous work has shown that 3D point cloud classifiers can be vulnerable to adversarial examples. However, most of the existing methods are aimed at white-box attacks, where the parameters and other information of the classifiers are known in the attack, which is unrealistic for real-world applications. In order to improve the attack performance of the black-box classifiers, the research community generally uses the transfer-based black-box attack. However, the transferability of current 3D attacks is still relatively low. To this end, this paper proposes Scale and Shear (SS) Attack to generate 3D adversarial examples with strong transferability. Specifically, we randomly scale or shear the input point cloud, so that the attack will not overfit the white-box model, thereby improving the transferability of the attack. Extensive experiments show that the SS attack proposed in this paper can be seamlessly combined with the existing state-of-the-art (SOTA) 3D point cloud attack methods to form more powerful attack methods, and the SS attack improves the transferability over 3.6 times compare to the baseline. Moreover, while substantially outperforming the baseline methods, the SS attack achieves SOTA transferability under various defenses. Our code will be available online at https://github.com/cuge1995/SS-attack

The strong nonlinear dynamics of tail-sitter vertical takeoff and landing (VTOL) unmanned aerial vehicles (UAVs) have consistently constrained their applications. Particularly, the widely-varying flight speed and attitude during the transition flights pose substantial challenges for the controller design. In order to gain a clear understanding of the nonlinear transition flights, the long- and short- period dynamic characteristics of tail-sitter UAVs are investigated for the first time. The results reveal that the short-period mode exhibits either sluggish response or excessive overshoot in different transition stages, primarily due to the widely-varying damping ratio and natural angular frequency. Even worse, the long-period mode can diverge due to positive poles. To address these issues, a systematic controller is proposed. First, the transition trajectory is optimized and the optimal control inputs are employed in a feedforward manner to trim the nominal forces and moments. On this basis, a discrete-time linear quadratic regulation (LQR) controller with a predefined decay rate is developed to position the desired poles, and a novel angular acceleration estimation method is introduced to compensate for unmodeled dynamics. Simulations under different uncertainties indicate that the proposed control method performs better in both transition trajectory tracking and uncertainty suppression, compared to the PID and incremental nonlinear dynamic inversion (INDI) controllers.

The aerodynamic coupling between the rotor, wing, and ground is highly complex during the vertical takeoff and landing (VTOL) process of a tilt-rotor aircraft, which severely affects flight stability. In this paper, a novel multi-input single-output feature model considering phase lag is first proposed to characterize the aerodynamic coupling mechanism during vertical takeoff and landing of the tilt-rotor aircraft. Based on that, a complete identification scheme for the rotor/wing/ground coupling of the tilt-rotor aircraft is proposed to derive the coupling law. Model comparison and performance verification based on flight tests are conducted to verify the accuracy of the model. The results demonstrate the effectiveness and reliability of the proposed method in identifying complex aerodynamic coupling during vertical takeoff and landing of the tilt-rotor aircraft.

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.

为了保证直升机在打击地面目标时的射击精度,需要对射击偏差的误差影响进行分析.通过研究直升机在悬停飞行时旋翼下方的诱导速度分布,分析旋翼干扰造成的机体晃动对航炮命中影响,建立机体在飞行打击目标时受到旋翼干扰下的外弹道射击方程;使用蒙特卡洛法进行打靶射击仿真实验,得到旋翼干扰下的弹丸落点分布规律.实验表明,某型武装直升机在悬停过程中打击中远距离目标时旋翼诱导速度影响弹丸落点的系统误差,机体晃动影响弹丸落点的散布误差,其圆概率误差随航炮射击俯仰角的增大呈现单边下降的趋势.通过实验可为直升机航炮火控系统的改进和实现旋翼干扰补偿提供支撑.

>Flexibility and endurance are the continuous pursuits of unmanned aerial vehicle (UAV) research. A fixed-wing UAV with vertical takeof and landing ability is ideal because it combines the advantages of long flight durations and freedom from runways [1]. Therefore, tilt-wing and tilt-rotor UAVs have been developed. The former is more suitable for long-duration flight because the propeller slip-stream is less disturbed, and a longer wingspan can be designed [2].