Zhenyang Yu
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Zhenyang Yu has a total of 10 co-authors. Here are the top co-authors by number of shared publications:
- Amina Ningru1 shared publication
Bo Cao
1 shared publication- Bo Cao
School of Mechanical Engineering, Anhui Science and Technology University, Chuzhou, China
1 shared publication Chao Zhang
School of Intelligent Manufacturing, Anhui Science and Technology University, Chuzhou, China
1 shared publication- Chao Zhang1 shared publication
Linghua Cui
School of Intelligent Manufacturing, Anhui Science and Technology University, Chuzhou, China
1 shared publication
Latest Publications
- Open Access
- 7 October 2026
- Published by Elsevier in SSRN Electronic Journal
A Visual-IMU Tightly Coupled Method Using Adaptive Sliding Window for Facility Environments
Autonomous navigation of mobile robotic navigation serves as the fundamental prerequisite for task execution in agricultural environments. Conventional vision-based simultaneous localization and mapping (SLAM) methods often struggle to achieve accurate positioning in agricultural environments because of their complex, variable, and poorly structured characteristics. To overcome these challenges, we propose a novel visual–inertial SLAM (VI-SLAM) framework to improve the localization accuracy and robustness of mobile robots operating in facility environments. Firstly, a robust initialization strategy is developed by jointly utilizing tracked visual features and (inertial measurement unit) IMU pre-integrated measurements, so that the complementary information provided by the camera and inertial sensor can be effectively exploited to improve the stability and reliability of the initial state estimation. Afterwards, the sliding window optimization algorithm is employed to reduce the computational efficiency, and an adaptive factor is strategically introduced to dynamically assign corresponding optimization weights to balance the contributions of visual and IMU measurements. Additionally, the loop detection and loop closure constraints are implemented to correct drift errors, thereby refining the overall positioning precision of the system. The effectiveness and robustness of the presented approach is experimentally validated through comprehensive evaluations on both the EuRoC benchmark dataset and real-world facility greenhouse scenarios. Experimental results confirm that the proposed VI-SLAM algorithm achieves improved localization accuracy and enhanced robustness in facility environments.
- 7 October 2026
- Published by Elsevier in SSRN Electronic Journal
Open AccessA Visual-IMU Tightly Coupled Method Using Adaptive Sliding Window for Facility Environments
Autonomous navigation of mobile robotic navigation serves as the fundamental prerequisite for task execution in agricultural environments. Conventional vision-based simultaneous localization and mapping (SLAM) methods often struggle to achieve accurate positioning in agricultural environments because of their complex, variable, and poorly structured characteristics. To overcome these challenges, we propose a novel visual–inertial SLAM (VI-SLAM) framework to improve the localization accuracy and robustness of mobile robots operating in facility environments. Firstly, a robust initialization strategy is developed by jointly utilizing tracked visual features and (inertial measurement unit) IMU pre-integrated measurements, so that the complementary information provided by the camera and inertial sensor can be effectively exploited to improve the stability and reliability of the initial state estimation. Afterwards, the sliding window optimization algorithm is employed to reduce the computational efficiency, and an adaptive factor is strategically introduced to dynamically assign corresponding optimization weights to balance the contributions of visual and IMU measurements. Additionally, the loop detection and loop closure constraints are implemented to correct drift errors, thereby refining the overall positioning precision of the system. The effectiveness and robustness of the presented approach is experimentally validated through comprehensive evaluations on both the EuRoC benchmark dataset and real-world facility greenhouse scenarios. Experimental results confirm that the proposed VI-SLAM algorithm achieves improved localization accuracy and enhanced robustness in facility environments.
- Open Access
- 10 April 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 14, 56584-56596
A Novel Multi-IMU Fusion Positioning Method Using an Adaptive Federated Kalman Filter
Reliable navigation for underground mining vehicles remains a critical challenge due to the rapid error accumulation of low-cost micro-electro-mechanical systems sensors in global navigation satellite systems-denied environments. To reconcile hardware limitations with high-precision requirements, this article proposes the adaptive federated Kalman filter (A_FKF), a fusion framework wherein a pyramid-shaped volumetric topology combined with singular value decomposition kinematics is constructed. By rigorously modeling the lever-arm effect, this approach explicitly decouples rotational dynamics from translational acceleration to resolve the observability deficiencies of single-point sensing. Integrated within this framework, a decentralized federated Kalman filter architecture featuring dynamic information sharing is developed, which reallocates fusion weights based on real-time subsystem confidence to mitigate the impact of local sensor inaccuracies. Validation under a 300 s dynamic trajectory confirms the algorithm effectively suppresses cumulative drift, achieving a 1.480 m position root mean square error (RMSE) and 3.214 m 95% spherical error probable. Furthermore, a regular pyramid sensor topology mitigates coplanar geometric dilution of precision; compared to planar baselines, this volumetric configuration restricts attitude errors below 0.5° and further reduces position RMSE to 1.131 m. These results substantiate the method’s efficacy for robust, low-cost autonomous navigation in complex mining environments.
- 10 April 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 14, 56584-56596
Open AccessA Novel Multi-IMU Fusion Positioning Method Using an Adaptive Federated Kalman Filter
Reliable navigation for underground mining vehicles remains a critical challenge due to the rapid error accumulation of low-cost micro-electro-mechanical systems sensors in global navigation satellite systems-denied environments. To reconcile hardware limitations with high-precision requirements, this article proposes the adaptive federated Kalman filter (A_FKF), a fusion framework wherein a pyramid-shaped volumetric topology combined with singular value decomposition kinematics is constructed. By rigorously modeling the lever-arm effect, this approach explicitly decouples rotational dynamics from translational acceleration to resolve the observability deficiencies of single-point sensing. Integrated within this framework, a decentralized federated Kalman filter architecture featuring dynamic information sharing is developed, which reallocates fusion weights based on real-time subsystem confidence to mitigate the impact of local sensor inaccuracies. Validation under a 300 s dynamic trajectory confirms the algorithm effectively suppresses cumulative drift, achieving a 1.480 m position root mean square error (RMSE) and 3.214 m 95% spherical error probable. Furthermore, a regular pyramid sensor topology mitigates coplanar geometric dilution of precision; compared to planar baselines, this volumetric configuration restricts attitude errors below 0.5° and further reduces position RMSE to 1.131 m. These results substantiate the method’s efficacy for robust, low-cost autonomous navigation in complex mining environments.