Juan Li

Surround-view depth estimation is critical for robotic perception and autonomous driving. Existing methods rely on implicit cross-view feature learning, which incurs a high computational cost. In this paper, we propose E${^{2}}$Depth, an efficient self-supervised surround-view depth estimation framework that explicitly leverages geometric and signal priors at each pipeline stage. First, hierarchical volumetric fusion is performed to align multi-level features across cameras with controlled memory consumption. Second, wavelet-domain edge enhancement is introduced to recover sharper depth boundaries without external supervision. Finally, an explicit pose estimation network guided by noisy motion priors is designed to stabilize training and improve depth scale reliability. Extensive experiments on the DDAD and nuScenes benchmarks demonstrate that E${^{2}}$Depth achieves a favorable trade-off between accuracy and efficiency, supporting practical deployment on real-world platforms.

Achieving adaptive swarm navigation for quadrotors in cluttered environments presents significant challenges, stemming from limited individual sensing capabilities and delayed collective responses. To address these issues, this article proposes a swarm control approach that integrates a motion salience-based coordination rule (MS-CR) with obstacle avoidance guided by a boundary point-based rotational potential field (BP-RPF), thereby enabling safe and adaptive swarm navigation in cluttered environments. For coordination, an MS metric is introduced, enabling each quadrotor to dynamically weight its neighbors based on local perception. This allows local stimuli to propagate efficiently throughout the swarm, enhancing collective responsiveness. For obstacle avoidance, the BP-RPF-based approach relies solely on detected obstacle boundary points, eliminating the need for full obstacle reconstruction. An RPF is introduced to guide quadrotors in executing stable avoidance and surface-following maneuvers. These components are unified within a multirule swarm navigation framework that combines coordination, obstacle avoidance, and task-oriented behaviors. Extensive six-degree-of-freedom (6-DoF) simulations in cluttered environments demonstrate that the proposed method outperforms existing baselines in maintaining interagent spacing, enhancing obstacle avoidance success rates, and improving task completion efficiency. Real-world experiments with a quadrotor swarm further confirm the method’s robustness and practical feasibility. These results validate the effectiveness of the proposed approach and highlight its potential for real-world deployment in complex and constrained environments.

Depth estimation is one of the key technologies for realizing 3D perception in unmanned systems. Monocular depth estimation has been widely researched because of its low-cost advantage, but the existing methods face the challenges of poor depth estimation performance and blurred object boundaries on embedded systems. In this paper, we propose a novel monocular depth estimation model, BoRe-Depth, which contains only 8.7M parameters. It can accurately estimate depth maps on embedded systems and significantly improves boundary quality. Firstly, we design an Enhanced Feature Adaptive Fusion Module (EFAF) which adaptively fuses depth features to enhance boundary detail representation. Secondly, we integrate semantic knowledge into the encoder to improve the object recognition and boundary perception capabilities. Finally, BoRe-Depth is deployed on NVIDIA Jetson Orin, and runs efficiently at 50.7 FPS. We demonstrate that the proposed model significantly outperforms previous lightweight models on multiple challenging datasets, and we provide detailed ablation studies for the proposed methods. The code is available at https://github.com/liangxiansheng093/BoRe-Depth.

Swarm intelligence for uncrewed aerial vehicles (UAVs) significantly improves the success rate of executing intricate tasks using “distributed platforms and aggregated effects”. However, the high experimental costs and safety risks constrain its development. This paper introduces SIGMA (Swarm Intelligence Generic simulator for Multi-UAVs), a high-fidelity distributed UAV swarm simulator for swarm intelligence algorithms. As an agent-based modeling simulator (ABMS), SIGMA has three key innovations: First, an automatic model tuning method improves aircraft dynamics fidelity. Second, a bidirectional discrete-event simulation (BiDES) architecture resolves the time alignment challenges in distributed systems. Third, a multi-agent learning toolbox ensures algorithm compatibility via an episodic training structure and a memory replay mechanism. In the verification part, the fidelity and scalability of the simulator are verified by quantitative simulations and experiments, and several successful applications demonstrate the practicality of the proposed simulator. Notice to Practitioners—The motivation for this paper stems from the need to develop a scalable and high-fidelity simulator for practical applications of swarm intelligence algorithms. Simulators developed based on game engines are widely used in swarm robotics due to their realistic 3D environments. However, as the number of nodes increases, the real-time performance and scalability of the simulators will decrease significantly. To achieve real-time simulation of large-scale swarms and improve swarm fidelity, SIGMA is proposed. It uses ABMS technology to achieve better performance and can effectively fit the learning tasks of UAV swarms.

Performing long-duration navigation without the global navigation satellite system (GNSS) network is a challenging task, particularly for small unmanned aerial vehicles (UAVs) equipped with low-cost micro-electro-mechanical sensors. This study proposes a hybrid neural network that integrates self-attention mechanisms with long short-term memory (SALSTM) to enhance GNSS-denied navigation performance. The estimation task of GNSS-denied navigation is first modeled based on UAV aerodynamics and kinematics, enabling a precise definition of the inputs and outputs that SALSTM needs to map. A self-attention layer is inserted in multiple LSTM layers to capture long-range dependencies in subtle dynamic changes. The output layer is designed to generate state sequences, leveraging the recursive nature of LSTM to enforce state continuity constraints. The outputs of SALSTM are fused to enhance integrated navigation within an extended Kalman filter framework. The performance of the proposed method is evaluated using flight data obtained from field tests. The results demonstrate that SALSTM-enhanced integrated navigation achieves superior long-term stability and improves velocity and position estimation accuracy by more than 50% compared to the best existing methods.

Dynamic derivatives are critical for evaluating an aircraft’s aerodynamic characteristics, dynamic modeling, and control system design during the design phase. However, due to the multiple iterations of the design phase, a method for calculating dynamic derivatives that balances computational efficiency and accuracy is required. This work presents a CFD-enhanced engineering calculation method (CEHM) for calculating tandem-wing UAVs’ dynamic derivatives. A coupling-effect-driven estimation strategy is proposed to incorporate the contribution of the rear wing to the longitudinal dynamic derivatives, and it accounts for the aerodynamic coupling effects between the front and rear wings. To enhance the accuracy of the dynamic derivative calculations, we put forward a dynamic derivative-correction mechanism based on the CFD method. It achieves three types of parameters from the static derivative CFD simulations to enhance accuracy, including parameters for aerodynamic force coefficient fitting, the dynamic pressure ratio, and the upwash and downwash gradients. The CEHM method is applied to compute the dynamic derivatives of the SULA90 tandem-wing UAV, with results compared to those obtained from the traditional engineering estimation tools (XFLR5 and OpenVSP). The simulation experiment results show that the proposed method not only calculates the acceleration derivatives but also provides higher calculation accuracy. To further validate the method’s effectiveness, open-loop model verifications were conducted using field flight test data of the SULA90. The field flight test results show that the CEHM method’s predicted results align closely with the measured flight data. The proposed method calculates dynamic derivatives in seconds, balancing accuracy and computational cost, making it highly suitable for tandem-wing aircraft during the design phase. Furthermore, this approach is generalizable and can be applied to other aircraft configurations.

The accurate estimation of flow angles is crucial for enhancing flight performance and aircraft safety. Flow angles of fixed-wing small unmanned aerial vehicles (SUAVs) are more vulnerable due to their low airspeed. Current flow angle measurement devices have not been widely implemented in SUAVs due to their substantial cost and size constraints. Moreover, there are no general estimation methods suitable for SUAVs based on their rudimentary sensor suite. This study presents a generalized optimization-assisted filter estimation (OAFE) method for estimating the relative velocity and flow angles of fixed-wing SUAVs based on a standard sensor suite. This OAFE method mainly consists of a cubature Kalman filter and an optimizer. The filter serves as the main loop with which to generate flow angles in real time by fusing the acceleration, angular rate, attitude, and airspeed. Without flow angle measurements, the optimizer generates approximate aerodynamic derivatives, which serve as pseudo-measurements with which to refine the performance of the filter. The results demonstrate that the estimated angle of attack and side slip angle displayed root mean square errors of around 0.11° and 0.24° in the simulation. The feasibility was also verified in field tests. The OAFE method does not require flow angle measurements, the prior acquisition of aerodynamic parameters, or model training, making it suitable for quick deployment on different SUAVs.