Yang Lyu

Yang Lyu

*This is an algorithmically generated author record based on publicly available information.

Current Organizations / Institutes

The organizations/institutes from the scholar's latest article

Previous Organizations / Institutes

The organizations / institutes from the scholar's other articles in the past ten years


Yang Lyu has a total of 75 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Radar and Event Camera Fusion for Agile Robot Ego-Motion Estimation

    by Yang Lyu, Zhenghao Zou, Yanfeng Li, Xiaohu Guo, Chunhui Zhao, Quan Pan

    Achieving reliable ego motion estimation for agile robots, e.g., aerobatic aircraft, remains challenging because most robot sensors fail to respond promptly and clearly to highly dynamic robot motions, often resulting in measurement blurring, distortion, and delays. In this article, we propose an inertial measurement unit (IMU)-free and feature-association-free framework to achieve aggressive ego-motion velocity estimation of a robot platform in highly dynamic scenarios by combining two types of exteroceptive sensors, an event camera and a millimeter-wave radar. First, we propose instantaneous raw events and Doppler measurements to derive rotational and translational velocities directly. Without a sophisticated association process between measurement frames, the proposed method is more robust in textureless and structureless environments and is more computationally efficient for edge computing devices. Then, in the back-end, we propose a continuous-time state-space model to fuse the hybrid time-based and event-based measurements to estimate the ego-motion velocity in a fixed-lag smoother fashion. In the end, we validate our velometer framework extensively in self-collected experimental datasets featured by aggressive motion and high dynamic range (HDR) lighting conditions. The results indicate that our IMU-free and association-free ego motion estimation framework can achieve reliable and efficient velocity output in challenging environments.


  • Learning structural consistency and monocular priors for progressive depth completion

    by Haochen Chai, Yang Lyu, Shenghai Yuan, Meimei Su, Chunhui Zhao, Zhunga Liu

  • Robust Skew-t Kalman Filter for USBL Tightly Integrated Positioning System Under Measurement Uncertainties

    by Ruoyu Xu, Chunhui Zhao, Yang Lyu, Honghao Xu, Yanyan Song

    Underwater Ultra-Short Baseline (USBL) positioning systems suffer from significant estimation errors due to complex noise characteristics. Our analysis indicates that these errors manifest distinct skewed and heavy-tailed statistical characteristics, primarily attributed to system biases, time delays, and multipath effects. To effectively mitigate these issues, we propose a novel Kalman filter approach utilizing a skew-t distribution (SKF). The SKF employs a hierarchical variational Bayesian approach to resolve linearization challenges caused by distribution asymmetry, using a structured likelihood representation of measurement errors. Simulations and field tests demonstrated that the SKF method improved accuracy by more than 56% in the USBL positioning system.


  • A Bi-Directional Adaptive Framework for Agile UAV Landing

    by Chunhui Zhao, Xirui Kao, Yilin Lu, Yang Lyu

    Autonomous landing on mobile platforms is crucial for extending quadcopter operational flexibility, yet conventional methods are often too inefficient for highly dynamic scenarios. The core limitation lies in the prevalent “track-then-descend” paradigm, which treats the platform as a passive target and forces the quadcopter to perform complex, sequential maneuvers. This article challenges that paradigm by introducing a bi-directional cooperative landing framework that redefines the roles of the vehicle and the platform. The essential innovation is transforming the problem from a single-agent tracking challenge into a coupled system optimization. Our key insight is that the mobile platform is not merely a target, but an active agent in the landing process. It proactively tilts its surface to create an optimal, stable terminal attitude for the approaching quadcopter. This active cooperation fundamentally breaks the sequential model by parallelizing the alignment and descent phases. Concurrently, the quadcopter’s planning pipeline focuses on generating a time-optimal and dynamically feasible trajectory that minimizes energy consumption. This bi-directional coordination allows the system to execute the recovery in an agile manner, characterized by aggressive trajectory tracking and rapid state synchronization within transient windows. The framework’s effectiveness, validated in dynamic scenarios, significantly improves the efficiency, precision, and robustness of autonomous quadrotor recovery in complex and time-constrained missions.

  • Open Access

    A Bi-directional Adaptive Framework for Agile UAV Landing

    by Chunhui Zhao, Xirui Kao, Yilin Lu, Yang Lyu

    Autonomous landing on mobile platforms is crucial for extending quadcopter operational flexibility, yet conventional methods are often too inefficient for highly dynamic scenarios. The core limitation lies in the prevalent ``track-then-descend'' paradigm, which treats the platform as a passive target and forces the quadcopter to perform complex, sequential maneuvers. This paper challenges that paradigm by introducing a bi-directional cooperative landing framework that redefines the roles of the vehicle and the platform. The essential innovation is transforming the problem from a single-agent tracking challenge into a coupled system optimization. Our key insight is that the mobile platform is not merely a target, but an active agent in the landing process. It proactively tilts its surface to create an optimal, stable terminal attitude for the approaching quadcopter. This active cooperation fundamentally breaks the sequential model by parallelizing the alignment and descent phases. Concurrently, the quadcopter's planning pipeline focuses on generating a time-optimal and dynamically feasible trajectory that minimizes energy consumption. This bi-directional coordination allows the system to execute the recovery in an agile manner, characterized by aggressive trajectory tracking and rapid state synchronization within transient windows. The framework's effectiveness, validated in dynamic scenarios, significantly improves the efficiency, precision, and robustness of autonomous quadrotor recovery in complex and time-constrained missions.

  • SSD: A State-Based Stealthy Backdoor Attack for IMU/GNSS Navigation System in UAV Route Planning

    by Zhaoxuan Wang, Yang Li, Jie Zhang, Xingshuo Han, Kangbo Liu, Yang Lyu, Yuan Zhou, Tianwei Zhang, Quan Pan

    Unmanned aerial vehicles (UAVs) are increasingly employed to perform high-risk tasks that require minimal human intervention. However, they face escalating cybersecurity threats, particularly from GNSS spoofing attacks. While previous studies have extensively investigated the impacts of GNSS spoofing on UAVs, few have focused on its effects on specific tasks. Moreover, the influence of UAV motion states on the assessment of cybersecurity risks is often overlooked. To address these gaps, we first provide a detailed evaluation of how motion states affect the effectiveness of network attacks. We demonstrate that nonlinear motion states not only enhance the effectiveness of position spoofing in GNSS spoofing attacks but also reduce the probability of detecting speed-related attacks. Building upon this, we propose a state-triggered backdoor attack method (SSD) to deceive GNSS systems and assess its risk to trajectory planning tasks. Extensive validation of SSD’s effectiveness and stealthiness is conducted. Experimental results show that, with appropriately tuned hyperparameters, SSD significantly increases positioning errors and the risk of task failure, while maintaining high stealthy rates across three state-of-the-art detectors.


  • Open Access

    Lightweight Obstacle Avoidance for Fixed-Wing UAVs Using Entropy-Aware PPO

    by Meimei Su, Haochen Chai, Chunhui Zhao, Yang Lyu, Jinwen Hu

    Obstacle avoidance during high-speed, low-altitude flight remains a significant challenge for unmanned aerial vehicles (UAVs), particularly in unfamiliar environments where prior maps and heavy onboard sensors are unavailable. To address this, we present an entropy-aware deep reinforcement learning framework that enables fixed-wing UAVs to navigate safely using only monocular onboard cameras. Our system features a lightweight, single-frame depth estimation module optimized for real-time execution on edge computing platforms, followed by a reinforcement learning controller equipped with a novel reward function that balances goal-reaching performance with path smoothness under fixed-wing dynamic constraints. To enhance policy optimization, we incorporate high-quality experiences from the replay buffer into the gradient computation, introducing a soft imitation mechanism that encourages the agent to align its behavior with previously successful actions. To further balance exploration and exploitation, we integrate an adaptive entropy regularization mechanism into the Proximal Policy Optimization (PPO) algorithm. This module dynamically adjusts policy entropy during training, leading to improved stability, faster convergence, and better generalization to unseen scenarios. Extensive software-in-the-loop (SITL) and hardware-in-the-loop (HITL) experiments demonstrate that our approach outperforms baseline methods in obstacle avoidance success rate and path quality, while remaining lightweight and deployable on resource-constrained aerial platforms.


  • DMCN Nash Seeking Based on Distributed Approximate Gradient Descent Optimization Algorithms for MASs

    by Meimei Su, Chunhui Zhao, Yang Lyu, Zheng Tan, Jinwen Hu, Xiaolei Hou, Quan Pan

    A key problem in multiagent multitask systems is optimizing conflict-free strategies, especially when task-assignment is coupled with path-planning. Incomplete information exacerbates this complexity, leading to frequent conflicts, such as redundant agents performing the same task. Different from the existing single-type game model, this article introduces a distributed mixed cooperative-noncooperative (DMCN) model that considers nondifferentiable constraints. In order to deal with nondifferentiable task layer constraints, we use approximation operators and splitting schemes to transform the original optimization function into the primal-dual differentiable function. In order to obtain more stable solutions, a distributed approximate gradient descent optimization algorithm and conflict resolution mechanism are proposed, which enhances the convergence of our method. We use Lyapunov theory to verify the exponential convergence of the algorithm in the time range. Simulation and experiments demonstrate the superiority of this method and its applicability in engineering applications.


  • Robust Fault Detection for Unmanned Aerial Vehicles Subject to Denial-of-Service Attacks

    by Kunpeng Pan, Feisheng Yang, Yang Lyu, Quan Pan

    During the flight of unmanned aerial vehicles (UAVs), potential system faults can lead to mission failure or even crashes. Therefore, it is important to equip the ground control station (GCS) with a fault detection module. However, malicious attackers may launch denial-of-service (DoS) attacks to interfere with the network communication between UAVs and GCS, which can result in the failure of the fault detection mechanism. This study presents a robust fault detection scheme for UAVs in the presence of DoS attacks. Specifically, a fault detection filter (FDF) is devised to produce residual signals, while a resilient event-triggered mechanism (ETM) is implemented to enhance network bandwidth utilization efficiency and alleviate the adverse effects of DoS attacks. By considering the H∞ performance index and analyzing the exponential stability of the switching residual system, the event triggering parameters and the filter gain matrix are obtained.Furthermore, a detection logic utilizing residuals and thresholds is introduced to facilitate fault detection. Simulation results confirm the viability of this fault detection approach, which is grounded in a resilient event trigger mechanism.