Jingyi He

Dr. Jingyi He


Research Focus & Metrics

Academic Career Length

5Years (2022-Present)

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

Representative Publications

View All Publications
5 January 2024 in IEEE Internet of Things Journal
Verified
Journal Article
Closed access
MXMeng Xi
Meng Xi
HDHuiao Dai
Huiao Dai
JHJingyi He
Jingyi He
WLWenjie Li
Wenjie Li
JWJiabao Wen
Jiabao Wen
Jiachen YangJiachen Yang
Jiachen Yang
The unmanned aerial vehicles (UAVs) are competent to perform a variety of applications, possessing great potential and promise. The deep neural networks (DNN) technology has enabled the UAV-assisted paradigm, accelerated the construction of smart cities, and propelled the development of the Internet of Things (IoT). UAVs play an increasingly important role in various applications, such as surveillance, environmental monitoring, emergency rescue, and supplies delivery, for which a robust path-planning technique is the foundation and prerequisite. However, existing methods lack comprehensive consideration of the complicated urban environment and do not provide an overall assessment of the robustness and generalization. Meanwhile, due to the resource constraints and hardware limitations of UAVs, the complexity of deploying the network needs to be reduced. This article proposes a lightweight, reinforcement-learning-based (RL-based) real-time path-planning method for UAVs, adaptive SAC (ASAC) algorithm, which optimizing the training process, network architecture, and algorithmic models. First of all, we establish a framework of global training and local adaptation, where the structured environment model is constructed for interaction, and local dynamically varying information aids in improving generalization. Second, ASAC introduces a cross-layer connection approach that passes the original state information into the higher layers to avoid feature loss and improve learning efficiency. Finally, we propose an adaptive temperature coefficient, which flexibly adjusts the exploration probability of UAVs with the training phase and experience data accumulation. In addition, a series of comparison experiments have been conducted in conjunction with practical application requirements, and the results have fully proved the favorable superiority of ASAC.

19 August 2022 in IEEE Transactions on Network Science and Engineering
Verified
Journal Article
Closed access
JWJiabao Wen
Jiabao Wen
Jiachen YangJiachen Yang
Jiachen Yang
YLYang Li
Yang Li
JHJingyi He
Jingyi He
ZLZhengjian Li
Zhengjian Li
Houbing Herbert SongHoubing Herbert Song
Houbing Herbert Song
The new generation of artificial intelligence technology has improved the autonomous monitoring capabilities of marine equipment. The ocean monitoring platform based on edge computing realizes the autonomous collaboration of multi-agent equipment groups. Autonomous Underwater Glider (AUG) is a new type of energy-saving marine equipment that can realize long-range ocean exploration. However, the non-negligible power constraints, time delays, communication failures and other unfavorable factors in the special underwater working environment have brought great challenges to the underwater monitoring operations of multi-AUG systems. This research establishes an improved artificial potential field method scheme based on the Maritime Internet of Things, which is based on the AUG leader's edge device to control multi-AUGs. In this process, an improved artificial potential field method is designed to solve the local optimal problem through behavior-based path optimization. Then, multi-AUGs are controlled to adapt to the task team plan based on the edge computing of the AUG leader. From the experimental results, it effectively realizes the AUG group cooperative control in the leader mode. Meanwhile, we established a marine communication model and AUG physics engine control model to complete a digital twin of multi-AUG monitoring tasks.

12 September 2022 in IEEE Internet of Things Journal
Verified
Journal Article
Closed access
Jiachen YangJiachen Yang
Jiachen Yang
JHJiaming Huo
Jiaming Huo
MXMeng Xi
Meng Xi
JHJingyi He
Jingyi He
ZLZhengjian Li
Zhengjian Li
Houbing Herbert SongHoubing Herbert Song
Houbing Herbert Song
Autonomous underwater vehicle (AUV) shows great potential in the Internet of Underwater Things (IoUT) system, in which the path planning algorithm plays a fundamental role. However, the complex underwater environment brings greater challenges to AUV path planning, especially the ocean current, which has a profound impact on time and energy consumption. This article focuses on the complex ocean current condition and proposes an underwater path planning method based on proximal policy optimization (UP4O). In this novel method, a deep reinforcement network is constructed to serve as a decision control to plan the moving direction of AUV. An information encoding module is developed to extract the features of the local obstacles. Furthermore, UP4O integrates the obstacle features with the current state information, including relative position, ocean current, and velocity, enabling the AUV to focus on the global direction and local obstacles at the same time. Additionally, to further adapt to the ocean current and shorten the time cost, UP4O expands the action space of AUV, realizing a fine and flexible action adjustment. The wide applicability of UP4O has been proved by numerous experiments. The proposed algorithm can always plan the time-saving and collision-free paths in complex underwater environments with various terrains and ocean current.

3 April 2024 in IEEE Internet of Things Journal
Verified
Journal Article
Closed access
JWJiabao Wen
Jiabao Wen
HDHuiao Dai
Huiao Dai
JHJingyi He
Jingyi He
LSLijiao Sun
Lijiao Sun
LGLiqing Gao
Liqing Gao
With the development of society and the economy, low-carbon and low-energy means of exploiting marine resources are receiving increasing attention. Autonomous path planning is a fundamental capability for IoT autonomous underwater vehicle (AUV) to carry out ocean exploration tasks. Currently, the main issue lies in the numerous disturbances and uncertainties present in the marine environment during practical applications, which can significantly impact path planning, leading to high-energy consumption and carbon emissions. To address this challenge, this article presents a sustainable reinforcement learning algorithm for handling time-varying current disturbances to achieve low-carbon AUV path planning, which is delineated into three steps. First, a 3-D time-varying current environment is established as the environmental framework for reinforcement learning, and the dynamic model of the AUV is formulated. Second, to enhance training efficiency and reduce AUV’s energy consumption, this article puts forth the ocean current disturbance rejection PPO (OCDRP) algorithm, which incorporates tidal current information to enhance the AUV’s resilience to time-varying currents. Lastly, expectile regression methods are introduced to facilitate the algorithm’s convergence. Experimental results confirm the efficacy of the proposed algorithm and its adaptability to time-varying currents, making it an efficient, adaptable, and low-carbon sustainable path planning approach.

8 November 2023 in IEEE Transactions on Consumer Electronics
Verified
Journal Article
Closed access
JWJiabao Wen
Jiabao Wen
HDHuiao Dai
Huiao Dai
JHJingyi He
Jingyi He
MXMeng Xi
Meng Xi
Shuai XiaoShuai Xiao
Shuai Xiao
Jiachen YangJiachen Yang
Jiachen Yang
The Tactile Internet (TI) allows operators to have an immersive experience in a remote environment. During this process, users generate a large amount of demonstration data containing tactile information. It is important to reasonably use user-generated data to improve the intelligence of Tactile Internet applications without infringing on user privacy. In order to use only user-generated datasets for learning without expensive environment interaction, conservative policy estimation in offline reinforcement learning is introduced in this paper to ensure the convergence of reinforcement learning algorithms. In addition, the dataset composed of different user behavior data has the characteristics of multimodal distribution, where the same state corresponds to different actions. The offline reinforcement learning algorithm is used to reconstruct and learn the user’s behavior under the framework of federated learning, and the diffusion model is introduced to model the multimodal distribution caused by different user preference. Based on this, we propose a federated diffusion Q-learning (FDQL) algorithm and verify the effectiveness of the algorithm in the d4rl dataset. Experimental results demonstrate that the FDQL algorithm performs efficiently within the federated learning framework, effectively capturing users’ multimodal behaviors and achieving state-of-the-art results.

13 February 2025 in IEEE Internet of Things Journal
Verified
Journal Article
Closed access
JWJiabao Wen
Jiabao Wen
ZLZhen Li
Zhen Li
MXMeng Xi
Meng Xi
JHJingyi He
Jingyi He
With the rapid development of Industrial Internet of Things (IIoT), the emergence of credible federated learning provides a more effective solution for it. In this article, we use the credible collaboration between large language models (LLMs) and reinforcement learning (RL) model to improve the autonomous decision-making efficiency of autonomous underwater vehicle (AUV), reduce resource and power consumption, and solve robust decision-making problem in open environments. First, considering the complex terrain and hydrodynamic environment in the ocean, we construct a 3-D ocean simulation environment with high accuracy and high reliability to simulate the behavioral constraints of AUV in the real ocean. Second, we integrate LLaMA model into the decision-making process of AUV, utilizing its powerful information processing capability for environmental analysis and action selection, so as to improve the decision-making generalization ability of AUV in dynamic ocean environments. Finally, we propose proximal policy advantage estimation (PPAE) method and achieve safe and efficient path planning for AUV based on LLMs decision output and dynamic field environment information. The experimental results show that our method achieves a good effect in improving the decision accuracy and robustness of the AUV, which proves the effectiveness of the LLMs in the application of underwater intelligent agent control decision.