Yixiang Ren

Mr. Yixiang Ren

Zhejiang University, Hangzhou, Zhejiang, China
orcid

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
1 May 2022 in Entropy
Verified
Journal Article
Open access
PDF file
Yixiang RenYixiang Ren
Yixiang Ren
ZYZhenhui YE
Zhenhui YE
GSGuanghua Song
Guanghua Song
XJXiaohong Jiang
Xiaohong Jiang
Mobile crowdsensing (MCS) is attracting considerable attention in the past few years as a new paradigm for large-scale information sensing. Unmanned aerial vehicles (UAVs) have played a significant role in MCS tasks and served as crucial nodes in the newly-proposed space-air-ground integrated network (SAGIN). In this paper, we incorporate SAGIN into MCS task and present a Space-Air-Ground integrated Mobile CrowdSensing (SAG-MCS) problem. Based on multi-source observations from embedded sensors and satellites, an aerial UAV swarm is required to carry out energy-efficient data collection and recharging tasks. Up to date, few studies have explored such multi-task MCS problem with the cooperation of UAV swarm and satellites. To address this multi-agent problem, we propose a novel deep reinforcement learning (DRL) based method called Multi-Scale Soft Deep Recurrent Graph Network (ms-SDRGN). Our ms-SDRGN approach incorporates a multi-scale convolutional encoder to process multi-source raw observations for better feature exploitation. We also use a graph attention mechanism to model inter-UAV communications and aggregate extra neighboring information, and utilize a gated recurrent unit for long-term performance. In addition, a stochastic policy can be learned through a maximum-entropy method with an adjustable temperature parameter. Specifically, we design a heuristic reward function to encourage the agents to achieve global cooperation under partial observability. We train the model to convergence and conduct a series of case studies. Evaluation results show statistical significance and that ms-SDRGN outperforms three state-of-the-art DRL baselines in SAG-MCS. Compared with the best-performing baseline, ms-SDRGN improves 29.0% reward and 3.8% CFE score. We also investigate the scalability and robustness of ms-SDRGN towards DRL environments with diverse observation scales or demanding communication conditions.

26 May 2023
Verified
Conference Paper
Open access
YJYuxuan Jin
Yuxuan Jin
Yixiang RenYixiang Ren
Yixiang Ren
TSTiantian Song
Tiantian Song
ZJZhiling Jiang
Zhiling Jiang
GSGuanghua Song
Guanghua Song
Flapping-wing aerial vehicle (FAV) is a novel type of aircraft that mimics the flight mode of birds and insects. Visual perception plays a crucial role in enabling FAVs to acquire ground information and achieve intelligent capabilities. However, most current FAV vision systems rely on ground processing systems for assistance, which limits their operational range due to communication constraints between the aircraft and the ground. Moreover, the use of vision systems for ground target localization on FAVs is still under-researched. In this work, we present a monocular vision-based on-board ground target recognition and localization system for a self-designed FAV, which can run in quasi-real time, and truly endows the FAV with ground autonomous visual perception capabilities. The system utilizes both the images from camera and attitude-position data of the aircraft, and resolves the issue of temporal mismatch between them. To validate feasibility and accuracy of the system, a series of real-world flight experiments are conducted, followed by a discussion of the errors observed.

14 June 2024 in Mathematics
Verified
Journal Article
Open access
PDF file
CDCHENGJIE DAI
CHENGJIE DAI
TSTiantian Song
Tiantian Song
YJYuxuan Jin
Yuxuan Jin
Yixiang RenYixiang Ren
Yixiang Ren
BYBowei Yang
Bowei Yang
GSGuanghua Song
Guanghua Song
Deploying high-accuracy detection models on lightweight edge devices (e.g., drones) is challenging due to hardware constraints. To achieve satisfactory detection results, a common solution is to compress and transmit the images to a cloud server where powerful models can be used. However, the image compression process for transmission may lead to a reduction in detection accuracy. In this paper, we propose a feature compression method tailored for object detection tasks, and it can be easily integrated with existing learned image compression models. In the method, the encoding process consists of two steps. Firstly, we use a feature extractor to obtain the low-level feature, and then use a mask generator to obtain an object mask to select regions containing objects. Secondly, we use a neural network encoder to compress the masked feature. As for decoding, a neural network decoder is used to restore the compressed representation into the feature that can be directly inputted into the object detection model. The experimental results demonstrate that our method surpasses existing compression techniques. Specifically, when compared to one of the leading methods—TCM2023—our approach achieves a 25.3% reduction in compressed file size and a 6.9% increase in mAP0.5.

27 March 2023 in Frontiers of Information Technology & Electronic Engineering
Verified
Journal Article
Open access
PDF file
Yixiang RenYixiang Ren
Yixiang Ren
ZYZhenhui YE
Zhenhui YE
YCYining Chen
Yining Chen
XJXiaohong Jiang
Xiaohong Jiang
GSGuanghua Song
Guanghua Song
Unfortunately the funding information was incorrect. It should be the National Key R&D Program of China (No. 2018AAA0102302).

23 January 2023 in Frontiers of Information Technology & Electronic Engineering
Verified
Journal Article
Closed access
PDF file
Yixiang RenYixiang Ren
Yixiang Ren
ZYZhenhui YE
Zhenhui YE
YCYining Chen
Yining Chen
XJXiaohong Jiang
Xiaohong Jiang
GSGuanghua Song
Guanghua Song
The recent progress in multi-agent deep reinforcement learning (MADRL) makes it more practical in real-world tasks, but its relatively poor scalability and