SYShenglun Yi

Shenglun Yi

*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


Shenglun Yi has a total of 17 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Open Access

    A robust approach to sigma point Kalman filtering

    by Shenglun Yi, Mattia Zorzi

    In this paper, we address a robust nonlinear state estimation problem under model uncertainty by formulating a dynamic minimax game: one player designs the robust estimator, while the other selects the least favorable model from an ambiguity set of possible models centered around the nominal one. To characterize a closed-form expression for the conditional expectation characterizing the estimator, we approximate the center of this ambiguity set by means of a sigma point approximation. Furthermore, since the least favorable model is generally nonlinear and non-Gaussian, we derive a simulator based on a Markov chain Monte Carlo method to generate data from such model. Finally, some numerical examples show that the proposed filter outperforms the existing filters.

  • Open Access

    An update-resilient Kalman filtering approach

    by Shenglun Yi, Mattia Zorzi

    We propose a new robust filtering paradigm considering the situation in which model uncertainty, described through an ambiguity set, is present only in the observations. We derive the corresponding robust estimator, referred to as update-resilient Kalman filter, which appears to be novel compared to existing minimax game-based filtering approaches. Moreover, we characterize the corresponding least favorable state space model and analyze the filter stability. Finally, some numerical examples show the effectiveness of the proposed estimator.

  • Open Access

    Data-driven robust UAV position estimation in GPS signal-challenged environment

    by Shenglun Yi, Xuebo Jin, Zhengjie Wang, Zhijun Liu, Mattia Zorzi

    In this paper, we consider a position estimation problem for an unmanned aerial vehicle (UAV) equipped with both proprioceptive sensors, i.e. IMU, and exteroceptive sensors, i.e. GPS and a barometer. We propose a data-driven position estimation approach based on a robust estimator which takes into account that the UAV model is affected by uncertainties and thus it belongs to an ambiguity set. We propose an approach to learn this ambiguity set from the data.

  • Open Access

    Adaptive Tunable Predefined-Time Backstepping Control for Uncertain Robotic Manipulators

    by Huihui Shi, Shuzong Xie, Qiang Chen, Shuangyi Hu, Shenglun Yi

    In engineering applications, high-precision tracking control is crucial for robotic manipulators to successfully complete complex operational tasks. To achieve this goal, this study proposes an adaptive tunable predefined-time backstepping control strategy for uncertain robotic manipulators with external disturbances and model uncertainties. By establishing a novel practical predefined-time stability criterion, a tunable predefined-time backstepping controller is systematically presented, allowing the upper bound of tracking error settling time to be precisely determined by adjusting only one control parameter. To accurately address lumped uncertainty, two updating laws are designed: a fuzzy weight updating law and a boundary adaptive updating law, which together reduce dependence on system model knowledge. In addition, the singularity problem in the predefined-time design process is effectively avoided by constructing the hyperbolic tangent function. The efficacy of the proposed control strategy is verified through numerical simulations.


  • Open Access

    Enhanced Recognition for Finger Gesture-Based Control in Humanoid Robots Using Inertial Sensors

    by Jingyi Xie, Na Xiang, Shenglun Yi

    Humanoid robots play a significant role in numerous fields, where efficient and intuitive control inputs are essential, particularly in applications requiring remote operation. In this paper, we investigate the potential advantages of inertial sensors as a key component for generating command signals in humanoid robot control systems. The objective is to accurately detect user motion through inertial sensing, thereby enabling precise control commands. Finger gestures are first captured as signals from the inertial sensor, and movement commands are extracted through filtering and recognition processes. These commands are then translated into corresponding robot actions based on the sensor’s attitude angles. Experimental results demonstrate the accuracy and effectiveness of this method in recognizing finger movements and converting them into reliable robot operations. The use of inertial sensors for gesture recognition simplifies the transmission of control inputs, promoting more user-friendly and efficient interfaces for humanoid robot operation. This approach not only improves control precision but also enhances the practicality of deploying humanoid robots in real-world environments.


  • Open Access

    Spatio-temporal Feature Soft Correlation Concatenation Aggregation Structure for Video Action Recognition Networks

    by Fafa Wang, Shenglun Yi

    The efficient extraction and fusion of video features to accurately identify complex and similar actions has consistently remained a significant research endeavor in the field of video action recognition. While adept at feature extraction, prevailing methodologies for video action recognition frequently exhibit suboptimal performance in the context of complex scenes and similar actions. This shortcoming arises primarily from their reliance on uni-dimensional feature extraction, thereby overlooking the interrelations among features and the significance of multi-dimensional fusion. To address this issue, this paper introduces an innovative framework predicated upon a soft correlation strategy aimed at augmenting the representational capacity of features by implementing multi-level, multi-dimensional feature aggregation and concatenating the temporal features produced by the network. Our end-to-end multi-feature encoding soft correlation concatenation aggregation layer, situated at the temporal feature output terminal of the Video Action Recognition network, proficiently aggregates and integrates the output temporal features. This approach culminates in producing a composite feature that cohesively unifies multi-dimensional information, markedly enhancing the network's competency in differentiating analogous video actions. Empirical findings demonstrate that the approach delineated in this paper bolsters the efficacy of video action recognition networks, achieving a more thorough depiction of images, and yielding superior accuracy and robustness.


  • Open Access

    A Switched Approach for Smartphone-Based Pedestrian Navigation

    by Shenglun Yi, Mattia Zorzi, Xuebo Jin, Tingli Su

    In this paper, we propose a novel switched approach to perform smartphone-based pedestrian navigation tasks even in scenarios where GNSS signals are unavailable. Specifically, when GNSS signals are available, the proposed approach estimates both the position and the average bias affecting the measurements from the accelerometers. This average bias is then utilized to denoise the accelerometer data when GNSS signals are unavailable. We test the effectiveness of denoising the acceleration measurements through the estimated average bias by a synthetic example. The effectiveness of the proposed approach is then validated through a real experiment which is conducted along a pre-planned 150 m path.

  • Open Access

    LI3D-BiLSTM: A Lightweight Inception-3D Networks with BiLSTM for Video Action Recognition

    by Fafa Wang, Xuebo Jin, Shenglun Yi

    This paper proposes an improved video action recognition method, primarily consisting of three key components. Firstly, in the data preprocessing stage, we developed multi-temporal scale video frame extraction and multi-spatial scale video cropping techniques to enhance content information and standardize input formats. Secondly, we propose a lightweight Inception-3D networks (LI3D) network structure for spatio-temporal feature extraction and design a soft-association feature aggregation module to improve the recognition accuracy of key actions in videos. Lastly, we employ a bidirectional LSTM network to contextualize the feature sequences extracted by LI3D, enhancing the representation capability for temporal data. To improve the model’s robustness and generalization ability, we introduced spatial and temporal scale data augmentation techniques in the preprocessing stage, effectively extracting video key frames and capturing key regional actions. Furthermore, we conducted an in-depth study on spatio-temporal feature extraction methods for video data, effectively extracting spatial and temporal information through the LI3D network and transfer learning. Experimental results demonstrate that the proposed method achieves significant performance improvements in video action recognition tasks, providing new insights and approaches for research in related fields.


  • Robust adaptive Kalman filter for structural performance assessment

    by Shenglun Yi, Tingli Su, ZhenYun Tang

    Summary: Structural performance assessment is a critical stage in the health monitoring for the maintenance and risk management of engineering structures, in which the interstory drift is a key indicator. In this paper, a robust adaptive Kalman filter is proposed for an interstory drift estimation problem to show the health condition of steel structures in the case that the statistics or internal dynamics describing the signals and measurements are not known precisely. More precisely, we build an adaptive current Jerk model (ACJM) where the model parameters are updated in each time step to presuppose the statistics characterization of the steel dynamic, while the unknown measurement noise covariance is adapted based on a fixed‐lag innovation with respect to measurements. Moreover, a robust adaptive Kalman filter is designed for the modelling uncertainties in each time increment by solving a minimax game: one player tries to select an “actual” model far from the proposed ACJM with an exponential decay tolerance, while its “hostile” player, namely, the optimum filter, is designed by minimizing the estimation error according to the selected “actual” model. Finally, some simulation and experimental results show the effectiveness of the proposed algorithm.