Jirong Zha
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Jirong Zha has a total of 44 co-authors. Here are the top co-authors by number of shared publications:
- Xinlei Chen
Tsinghua University
6 shared publications - Yanggang Xu
Shenzhen International Graduate School, Tsinghua University, Shenzhen, China
3 shared publications - Chenyu Zhao
Shenzhen International Graduate School, Tsinghua University, Shenzhen, China
2 shared publications - Jiyuan Ren
Tsinghua University, Beijing, China
2 shared publications - Yuhan Cheng
Shenzhen International Graduate School, Tsinghua University, Shenzhen, China
2 shared publications Bin Zhang
Shenzhen Smart City Technology Development Group, Shenzhen, China
1 shared publication
Latest Publications
- Top Cited Papers
- 1 July 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Mobile Computing
- Vol. 25 (7) , 11173-11190
Scalable UAV Multi-Hop Networking via Multi-Agent Reinforcement Learning With Large Language Models
- 1 July 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Mobile Computing
- Vol. 25 (7) , 11173-11190
Top Cited PapersScalable UAV Multi-Hop Networking via Multi-Agent Reinforcement Learning With Large Language Models
- Open Access
- 22 June 2026
- Published by Association for Computing Machinery (ACM) in ACM Computing Surveys
- Vol. 58 (13) , 1-38
Large-Scale UAV Swarm Coordination for Sensing and Communication: A Spatiotemporal Perspective
The rapid advancement of unmanned aerial vehicle (UAV) swarm systems has enabled their deployment in large-scale applications such as disaster response, environmental monitoring, logistics, and communication networks. In these scenarios, effective scheduling and coordination of UAV swarms are critical for mission success, particularly under complex spatiotemporal constraints. This article provides a comprehensive survey of scheduling and planning algorithms for large-scale UAV swarm coordination under spatiotemporal constraints. The unique challenges posed by these constraints are analyzed, and state-of-the-art algorithms, including sampling-based, graph-based, mathematical optimization-based, and learning-based methods, are systematically evaluated. In addition, two representative application domains, sensing and communication, are investigated to demonstrate how spatiotemporal constraints shape algorithm design and performance. Furthermore, this article also explores the key challenges faced by UAV swarms and proposes corresponding future research directions, which are crucial for advancing the development of this field. This survey aims to serve as a foundational reference for researchers and practitioners developing scalable coordination and planning solutions for UAV swarms.
- 22 June 2026
- Published by Association for Computing Machinery (ACM) in ACM Computing Surveys
- Vol. 58 (13) , 1-38
Open AccessLarge-Scale UAV Swarm Coordination for Sensing and Communication: A Spatiotemporal Perspective
The rapid advancement of unmanned aerial vehicle (UAV) swarm systems has enabled their deployment in large-scale applications such as disaster response, environmental monitoring, logistics, and communication networks. In these scenarios, effective scheduling and coordination of UAV swarms are critical for mission success, particularly under complex spatiotemporal constraints. This article provides a comprehensive survey of scheduling and planning algorithms for large-scale UAV swarm coordination under spatiotemporal constraints. The unique challenges posed by these constraints are analyzed, and state-of-the-art algorithms, including sampling-based, graph-based, mathematical optimization-based, and learning-based methods, are systematically evaluated. In addition, two representative application domains, sensing and communication, are investigated to demonstrate how spatiotemporal constraints shape algorithm design and performance. Furthermore, this article also explores the key challenges faced by UAV swarms and proposes corresponding future research directions, which are crucial for advancing the development of this field. This survey aims to serve as a foundational reference for researchers and practitioners developing scalable coordination and planning solutions for UAV swarms.
- 4 May 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Mobile Computing
- Vol. PP (15361233) , 1-14
Breaking the Communication-Accuracy Trade-off: A Sparsified Information Diffusion Framework for Multi-Agent Collaborative Perception
The growing relevance of multi-agent systems has drawn increasing focus on communication-efficient filters for collaborative perception to alleviate the system's communication burden. While the event-triggered (ET) mechanism can improve communication efficiency in collaborative state estimation, an inevitable trade-off exists between estimation accuracy and communication cost in ET filters. This paper proposes a fast and accurate ET diffusion-based filter for real-time multi-agent collaborative target tracking, aiming to reduce the system's data transmission without compromise in tracking performance. The proposed filter achieves improved tracking accuracy, reduced data transmission, and accelerated convergence using an error-minimized ET cubature information filter (CIF) for local estimation, and a correlation-aware diffusion strategy for global fusion. The experimental results confirm the scalability of the proposed EDC-CIF algorithm and demonstrate its efficacy in simultaneously reducing estimation error and computation time while significantly enhancing communication efficiency.
- 4 May 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Mobile Computing
- Vol. PP (15361233) , 1-14
Breaking the Communication-Accuracy Trade-off: A Sparsified Information Diffusion Framework for Multi-Agent Collaborative Perception
The growing relevance of multi-agent systems has drawn increasing focus on communication-efficient filters for collaborative perception to alleviate the system's communication burden. While the event-triggered (ET) mechanism can improve communication efficiency in collaborative state estimation, an inevitable trade-off exists between estimation accuracy and communication cost in ET filters. This paper proposes a fast and accurate ET diffusion-based filter for real-time multi-agent collaborative target tracking, aiming to reduce the system's data transmission without compromise in tracking performance. The proposed filter achieves improved tracking accuracy, reduced data transmission, and accelerated convergence using an error-minimized ET cubature information filter (CIF) for local estimation, and a correlation-aware diffusion strategy for global fusion. The experimental results confirm the scalability of the proposed EDC-CIF algorithm and demonstrate its efficacy in simultaneously reducing estimation error and computation time while significantly enhancing communication efficiency.
- Open Access
- 4 December 2024
- Published by Association for Computing Machinery (ACM)
- p. 1992-1997
Multi-Agent Target Pursuit Using Perception Uncertainty-Aware Reinforcement Learning
Existing target pursuit systems are able to coordinate a team of mobile agents to capture or intercept unauthorized targets. Multi-agent reinforcement learning (MARL) further empowers pursuit strategies with the potential to emerge complex behaviors. However, existing solutions lack the ability to handle the perception uncertainty caused by relative position measurement noises, which blurs the understanding of the target's state and complicates the pursuit strategy learning process. This study proposes PUARL, which enhances the learning under the perception uncertainty process by guiding exploration with probabilistic estimation and adapting the policy based on awareness of perception uncertainty. We validate its performance in terms of both accuracy and efficiency. PUARL achieves a success rate increase of 12.3%+ and a reduction in total steps by 58.3%+, outperforming both state-of-the-art heuristic and learning-based solutions.
- 4 December 2024
- Published by Association for Computing Machinery (ACM)
- p. 1992-1997
Open AccessMulti-Agent Target Pursuit Using Perception Uncertainty-Aware Reinforcement Learning
Existing target pursuit systems are able to coordinate a team of mobile agents to capture or intercept unauthorized targets. Multi-agent reinforcement learning (MARL) further empowers pursuit strategies with the potential to emerge complex behaviors. However, existing solutions lack the ability to handle the perception uncertainty caused by relative position measurement noises, which blurs the understanding of the target's state and complicates the pursuit strategy learning process. This study proposes PUARL, which enhances the learning under the perception uncertainty process by guiding exploration with probabilistic estimation and adapting the policy based on awareness of perception uncertainty. We validate its performance in terms of both accuracy and efficiency. PUARL achieves a success rate increase of 12.3%+ and a reduction in total steps by 58.3%+, outperforming both state-of-the-art heuristic and learning-based solutions.
- Open Access
- 4 December 2024
- Published by Association for Computing Machinery (ACM)
- p. 2028-2033
Scalable Multi-Agent Reinforcement Learning for Effective UAV Scheduling in Multi-Hop Emergency Networks
Utilizing unmanned aerial vehicles (UAVs) as mobile access points can assist urban communication systems in establishing emergency networks in disaster scenarios. However, in large-scale dynamic environments, the extensive exploration space makes effective collaboration among a large number of UAVs challenging. In this paper, to schedule the deployment of UAVs for networking purposes, we propose a novel approach, MAEN, using multi-agent reinforcement learning. The grouping and information sharing mechanisms in MAEN enable the algorithm to easily scale up the number of UAVs to dozens and address the issue of strategy equilibrium. Additionally, a reward decomposition module is designed to handle coordination and task allocation among UAVs. Experimental results demonstrate that the algorithm outperforms existing algorithms in terms of ground device coverage and communication quality.
- 4 December 2024
- Published by Association for Computing Machinery (ACM)
- p. 2028-2033
Open AccessScalable Multi-Agent Reinforcement Learning for Effective UAV Scheduling in Multi-Hop Emergency Networks
Utilizing unmanned aerial vehicles (UAVs) as mobile access points can assist urban communication systems in establishing emergency networks in disaster scenarios. However, in large-scale dynamic environments, the extensive exploration space makes effective collaboration among a large number of UAVs challenging. In this paper, to schedule the deployment of UAVs for networking purposes, we propose a novel approach, MAEN, using multi-agent reinforcement learning. The grouping and information sharing mechanisms in MAEN enable the algorithm to easily scale up the number of UAVs to dozens and address the issue of strategy equilibrium. Additionally, a reward decomposition module is designed to handle coordination and task allocation among UAVs. Experimental results demonstrate that the algorithm outperforms existing algorithms in terms of ground device coverage and communication quality.
- Open Access
- 4 December 2024
- Published by Association for Computing Machinery (ACM)
- p. 1377-1392
Foes or Friends: Embracing Ground Effect for Edge Detection on Lightweight Drones
Drone-based rapid and accurate environmental edge detection is highly advantageous for tasks such as disaster relief and autonomous navigation. Current methods, using radar or cameras, raise deployment costs and burden lightweight drones with high computational demands. In this paper, we propose AirTouch, a system that transforms the ground effect from a stability "foe" in traditional flight control views, into a "friend" for accurate and efficient edge detection. Our key insight is that analyzing drone sensor readings and flight commands allows us to detect ground effect changes. Such changes typically indicate the drone flying over an edge, making this information valuable for edge detection. We approach this insight through theoretical analysis, algorithm design, and implementation, fully leveraging the ground effect as a new sensing modality without compromising drone flight stability, thereby achieving accurate and efficient scene edge detection. Extensive evaluations demonstrate that our system achieves a high detection accuracy with mean detection distance errors of 0.051m, outperforming the baseline performance by 86%.
- 4 December 2024
- Published by Association for Computing Machinery (ACM)
- p. 1377-1392
Open AccessFoes or Friends: Embracing Ground Effect for Edge Detection on Lightweight Drones
Drone-based rapid and accurate environmental edge detection is highly advantageous for tasks such as disaster relief and autonomous navigation. Current methods, using radar or cameras, raise deployment costs and burden lightweight drones with high computational demands. In this paper, we propose AirTouch, a system that transforms the ground effect from a stability "foe" in traditional flight control views, into a "friend" for accurate and efficient edge detection. Our key insight is that analyzing drone sensor readings and flight commands allows us to detect ground effect changes. Such changes typically indicate the drone flying over an edge, making this information valuable for edge detection. We approach this insight through theoretical analysis, algorithm design, and implementation, fully leveraging the ground effect as a new sensing modality without compromising drone flight stability, thereby achieving accurate and efficient scene edge detection. Extensive evaluations demonstrate that our system achieves a high detection accuracy with mean detection distance errors of 0.051m, outperforming the baseline performance by 86%.
- Open Access
- 2 December 2024
- Published by Association for Computing Machinery (ACM)
- p. 1241-1255
A Unified Membership Inference Method for Visual Self-supervised Encoder via Part-aware Capability
Self-supervised learning shows promise in harnessing extensive unlabeled data, but it also confronts significant privacy concerns, especially in vision. In this paper, we aim to perform membership inference on visual self-supervised models in a more realistic setting: self-supervised training method and details are unknown for an adversary when attacking as he usually faces a black-box system in practice. In this setting, considering that self-supervised model could be trained by completely different self-supervised paradigms, e.g., masked image modeling and contrastive learning, with complex training details, we propose a unified membership inference method called PartCrop. It is motivated by the shared part-aware capability among models and stronger part response on the training data. Specifically, PartCrop crops parts of objects in an image to query responses with the image in representation space. We conduct extensive attacks on self-supervised models with different training protocols and structures using three widely used image datasets. The results verify the effectiveness and generalization of PartCrop. Moreover, to defend against PartCrop, we evaluate two common approaches, i.e., early stop and differential privacy, and propose a tailored method called shrinking crop scale range. The defense experiments indicate that all of them are effective. Our code is available at https://github.com/JiePKU/PartCrop.
- 2 December 2024
- Published by Association for Computing Machinery (ACM)
- p. 1241-1255
Open AccessA Unified Membership Inference Method for Visual Self-supervised Encoder via Part-aware Capability
Self-supervised learning shows promise in harnessing extensive unlabeled data, but it also confronts significant privacy concerns, especially in vision. In this paper, we aim to perform membership inference on visual self-supervised models in a more realistic setting: self-supervised training method and details are unknown for an adversary when attacking as he usually faces a black-box system in practice. In this setting, considering that self-supervised model could be trained by completely different self-supervised paradigms, e.g., masked image modeling and contrastive learning, with complex training details, we propose a unified membership inference method called PartCrop. It is motivated by the shared part-aware capability among models and stronger part response on the training data. Specifically, PartCrop crops parts of objects in an image to query responses with the image in representation space. We conduct extensive attacks on self-supervised models with different training protocols and structures using three widely used image datasets. The results verify the effectiveness and generalization of PartCrop. Moreover, to defend against PartCrop, we evaluate two common approaches, i.e., early stop and differential privacy, and propose a tailored method called shrinking crop scale range. The defense experiments indicate that all of them are effective. Our code is available at https://github.com/JiePKU/PartCrop.
- Open Access
- 8 April 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in TechRxiv
Diffusion-based Filter for Fast and Accurate Collaborative Tracking with Low Data Transmission
The growing relevance of multi-agent systems has drawn increasing focus on communication-efficient filters for collaborative target tracking to alleviate the system's communication burden. While the event-triggered (ET) mechanism can improve communication efficiency in collaborative tracking, an inevitable trade-off exists between estimation accuracy and communication cost in ET filters. This paper proposes a fast and accurate ET diffusion-based filter for real-time multi-agent collaborative tracking, aiming to reduce the system's data transmission without notable compromise in tracking performance. The proposed filter achieves improved tracking accuracy, reduced data transmission, and accelerated convergence using an error-minimized ET cubature information filter (CIF) for local estimation, and a correlation-aware diffusion strategy for global fusion. Our algorithm's stability has been proved. Results show that our algorithm can reduce estimation error by 21.6-72.18%, decrease computation time by 47.2-62.55%, and improve communication efficiency by 34.42-49.65% compared to mainstream collaborative tracking approaches.
- 8 April 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in TechRxiv
Open AccessDiffusion-based Filter for Fast and Accurate Collaborative Tracking with Low Data Transmission
The growing relevance of multi-agent systems has drawn increasing focus on communication-efficient filters for collaborative target tracking to alleviate the system's communication burden. While the event-triggered (ET) mechanism can improve communication efficiency in collaborative tracking, an inevitable trade-off exists between estimation accuracy and communication cost in ET filters. This paper proposes a fast and accurate ET diffusion-based filter for real-time multi-agent collaborative tracking, aiming to reduce the system's data transmission without notable compromise in tracking performance. The proposed filter achieves improved tracking accuracy, reduced data transmission, and accelerated convergence using an error-minimized ET cubature information filter (CIF) for local estimation, and a correlation-aware diffusion strategy for global fusion. Our algorithm's stability has been proved. Results show that our algorithm can reduce estimation error by 21.6-72.18%, decrease computation time by 47.2-62.55%, and improve communication efficiency by 34.42-49.65% compared to mainstream collaborative tracking approaches.