Xiaoqing Zhu

Dr. Xiaoqing Zhu

Beijing University of Technology, Beijing, China
orcid

Research Focus & Metrics

Academic Career Length

9Years (2018-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
4 April 2019 in Sensors
Verified
Journal Article
Open access
PDF file
YXYao Xiao
Yao Xiao
XRXiaogang Ruan
Xiaogang Ruan
JCJie Chai
Jie Chai
XZXiaoping Zhang
Xiaoping Zhang
Xiaoqing ZhuXiaoqing Zhu
Xiaoqing Zhu
Low-cost microelectro mechanical systems (MEMS)-based inertial measurement unit (IMU) measurements are usually affected by inaccurate scale factors, axis misalignments, and g-sensitivity errors. These errors may significantly influence the performance of visual-inertial methods. In this paper, we propose an online IMU self-calibration method for visual-inertial systems equipped with a low-cost inertial sensor. The goal of our method is to concurrently perform 3D pose estimation and online IMU calibration based on optimization methods in unknown environments without any external equipment. To achieve this goal, we firstly develop a novel preintegration method that can handle the IMU intrinsic parameters error propagation. Then, we frame IMU calibration problem into general factors so that we can easily integrate the factors into the current graph-based visual-inertial frameworks and jointly optimize the IMU intrinsic parameters as well as the system states in a big bundle. We evaluate the proposed method with a publicly available dataset. Experimental results verify that the proposed approach is able to accurately calibrate all the considered parameters in real time, leading to significant improvement of estimation precision of visual-inertial system (VINS) compared with the estimation results with offline precalibrated IMU measurements.

2 March 2022 in Scientific Reports
Verified
Journal Article
Open access
PDF file
XRXiaogang Ruan
Xiaogang Ruan
PLPeng Li
Peng Li
Xiaoqing ZhuXiaoqing Zhu
Xiaoqing Zhu
PLPengfei Liu
Pengfei Liu
Target-driven visual navigation is essential for many applications in robotics, and it has gained increasing interest in recent years. In this work, inspired by animal cognitive mechanisms, we propose a novel navigation architecture that simultaneously learns exploration policy and encodes environmental structure. First, to learn exploration policy directly from raw visual input, we use deep reinforcement learning as the basic framework and allow agents to create rewards for themselves as learning signals. In our approach, the reward for the current observation is driven by curiosity and calculated by a count-based approach and temporal distance. While agents learn exploration policy, we use temporal distance to find waypoints in observation sequences and incrementally describe the structure of the environment in a way that integrates episodic memory. Finally, space topological cognition is integrated into the model as a path planning module and combined with a locomotion network to obtain a more generalized approach to navigation. We test our approach in the DMlab, a visually rich 3D environment, and validate its exploration efficiency and navigation performance through extensive experiments. The experimental results show that our approach can explore and encode the environment more efficiently and has better capability in dealing with stochastic objects. In navigation tasks, agents can use space topological cognition to effectively reach the target and guide detour behaviour when a path is unavailable, exhibiting good environmental adaptability.

8 March 2022 in Electronics
Verified
Journal Article
Open access
PDF file
Xiaoqing ZhuXiaoqing Zhu
Xiaoqing Zhu
MWMingchao Wang
Mingchao Wang
XRXiaogang Ruan
Xiaogang Ruan
LCLu Chen
Lu Chen
TJTingdong Ji
Tingdong Ji
XLXinyuan Liu
Xinyuan Liu
To deal with the problem of stable walking of quadruped robots on slopes, a gait planning algorithm framework for quadruped robots facing unknown slopes is proposed. We estimated the terrain slope by the attitude information measured by the inertial measurement unit (IMU) without relying on the robot vision. The crawl gait was adopted, and the center of gravity trajectory planning was carried out based on the stability criterion zero-moment point (ZMP). Then, the augmented random search (ARS) algorithm was used to modulate the parameters of the Bezier curve to realize the planning of the robot foot trajectory. Additionally, the robot can adjust the posture in real time to follow the desired joint angle, which realizes the adaptive adjustment of the robot’s posture during the slope movement. Simulation experiment results show that the proposed algorithm for slope gait planning can adaptively adjust the robot’s attitude and stably pass through the slope environment when the slope is unknown.

9 November 2023 in Journal of Shanghai Jiaotong University (Science)
Verified
Journal Article
Closed access
PDF file
CLChunyang Li
Chunyang Li
Xiaoqing ZhuXiaoqing Zhu
Xiaoqing Zhu
XRXiaogang Ruan
Xiaogang Ruan
XLXinyuan Liu
Xinyuan Liu
SZSiyuan Zhang
Siyuan Zhang

1 January 2021 in Computational Intelligence and Neuroscience
Verified
Journal Article
Open access
PDF file
XRXiaogang Ruan
Xiaogang Ruan
PLPeng Li
Peng Li
Xiaoqing ZhuXiaoqing Zhu
Xiaoqing Zhu
HYHejie Yu
Hejie Yu
NYNaigong Yu
Naigong Yu
Developing artificial intelligence (AI) agents is challenging for efficient exploration in visually rich and complex environments. In this study, we formulate the exploration question as a reinforcement learning problem and rely on intrinsic motivation to guide exploration behavior. Such intrinsic motivation is driven by curiosity and is calculated based on episode memory. To distribute the intrinsic motivation, we use a count‐based method and temporal distance to generate it synchronously. We tested our approach in 3D maze‐like environments and validated its performance in exploration tasks through extensive experiments. The experimental results show that our agent can learn exploration ability from raw sensory input and accomplish autonomous exploration across different mazes. In addition, the learned policy is not biased by stochastic objects. We also analyze the effects of different training methods and driving forces on exploration policy.

1 September 2025 in Applied Sciences
Verified
Journal Article
Open access
PDF file
Xiaoqing ZhuXiaoqing Zhu
Xiaoqing Zhu
LBLanyue Bi
Lanyue Bi
TWTong Wu
Tong Wu
CZChuan Zhang
Chuan Zhang
JWJiahao Wu
Jiahao Wu
Deep Reinforcement Learning (DRL) has achieved remarkable success in robotic control, autonomous driving, and game-playing agents. However, its decision-making process often remains a black box, lacking both interpretability and verifiability. In robotic control tasks, developers cannot pinpoint decision errors or precisely adjust control strategies based solely on observed robot behaviors. To address this challenge, this work proposes an interpretable DRL framework based on a Causal Correction and Compensation Network (C2-Net), which systematically captures the causal relationships underlying decision-making and enhances policy robustness. C2-Net integrates a Graph Neural Network-based Neural Causal Model (GNN-NCM) to compute causal influence weights for each action. These weights are then dynamically applied to correct and compensate the raw policy outputs, thereby balancing performance optimization and transparency. This work validates the approach on OpenAI Gym’s Hopper, Walker2d, and Humanoid environments, as well as the multi-agent AzureLoong platform built on Isaac Gym. In terms of convergence speed, final return, and policy robustness, experimental results show that C2-Net achieves higher performance over both non-causal baselines and conventional attention-based models. Moreover, it provides rich causal explanations for its decisions. The framework represents a principled shift from correlation to causation and offers a practical solution for the safe and reliable deployment of multi-robot systems.