Chao Li
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
Research Subjects
Research Interests
Chao Li has a total of 76 co-authors. Here are the top co-authors by number of shared publications:
- Jiming Chen
Zhejiang University, Hangzhou, China
14 shared publications - Shibo He
Zhejiang University
12 shared publications - Qinmin Yang
Zhejiang University
7 shared publications - Kehan Li
Department of Control Science and Engineering, Zhejiang University, Hangzhou, China
5 shared publications - Yingqian Zhang
Department of Control Science and Engineering, Zhejiang University, Hangzhou, Zhejiang, China
4 shared publications - Cunqi Shao
Department of Control Science and Engineering, Zhejiang University, Hangzhou, China
3 shared publications
Latest Publications
- Open Access
- 8 August 2026
- Published by Association for Computing Machinery (ACM)
- p. 8501-8509
CoPack: Collaborate Simulation and Reality for Robot Packing Learning in Real-world and Physical Engine
The 3D bin packing problem, with its diverse industrial applications, has garnered significant research attention in recent years. Existing approaches typically model it as a discrete and static process, while real-world applications involve continuous gravity-driven interactions. This idealized simplification leads to infeasible deployments (e.g., unstable packing) in practice. Simulations with physical engine offer an opportunity to emulate continuous gravity effects, enabling the training of reinforcement learning (RL) agents to address such limitations and improve packing stability. However, a simulation-to-reality gap persists due to dynamic variations in physical properties of real-world objects, such as various friction coefficients, elasticity, and non-uniform weight distributions. To bridge this gap, we propose a hybrid RL framework that collaborates with physical simulation with real-world data feedback. Firstly, domain randomization is applied during simulation to expose agents to a spectrum of physical parameters, enhancing their generalization capability. Secondly, the RL agent is fine-tuned with real-world deployment feedback, further reducing collapse rates. Extensive experiments demonstrate that our method achieves lower collapse rates in both simulated and real-world scenarios. Large-scale deployments in logistics systems validate the practical effectiveness, with a 35% reduction in packing collapse compared to baseline methods.
- 8 August 2026
- Published by Association for Computing Machinery (ACM)
- p. 8501-8509
Open AccessCoPack: Collaborate Simulation and Reality for Robot Packing Learning in Real-world and Physical Engine
The 3D bin packing problem, with its diverse industrial applications, has garnered significant research attention in recent years. Existing approaches typically model it as a discrete and static process, while real-world applications involve continuous gravity-driven interactions. This idealized simplification leads to infeasible deployments (e.g., unstable packing) in practice. Simulations with physical engine offer an opportunity to emulate continuous gravity effects, enabling the training of reinforcement learning (RL) agents to address such limitations and improve packing stability. However, a simulation-to-reality gap persists due to dynamic variations in physical properties of real-world objects, such as various friction coefficients, elasticity, and non-uniform weight distributions. To bridge this gap, we propose a hybrid RL framework that collaborates with physical simulation with real-world data feedback. Firstly, domain randomization is applied during simulation to expose agents to a spectrum of physical parameters, enhancing their generalization capability. Secondly, the RL agent is fine-tuned with real-world deployment feedback, further reducing collapse rates. Extensive experiments demonstrate that our method achieves lower collapse rates in both simulated and real-world scenarios. Large-scale deployments in logistics systems validate the practical effectiveness, with a 35% reduction in packing collapse compared to baseline methods.
- Open Access
- 8 August 2026
- Published by Association for Computing Machinery (ACM)
- p. 4636-4646
LTSV: Layered Type-Constrained Shapley Value for Heterogeneous Graph Data Valuation
- 8 August 2026
- Published by Association for Computing Machinery (ACM)
- p. 4636-4646
Open AccessLTSV: Layered Type-Constrained Shapley Value for Heterogeneous Graph Data Valuation
- 21 May 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Knowledge and Data Engineering
- Vol. 38 (8) , 5047-5061
Enhancing Active Learning for Class Imbalance With an Incrementally Weighted Approach
Active learning can significantly reduce the cost of labeling instances while improving model performance. However, similar to other traditional algorithms, active learning encounters the problem of class imbalance and delivers sub-optimal performance. Additionally, existing approaches suffer from poor performance and are time-consuming. To address these issues, we propose an Actively Incrementally Weighted Broad Learning System (AI-WBLS). Firstly, we introduce an active learning framework based on the weighted broad learning system, which employs a double uncertainty sample selection strategy to enhance the value and reasonableness of sample selection in each iteration of active learning. To further improve the model's adaptability during the iterative learning process, an adaptive weighting strategy is designed to adaptively modify the penalty weights according to the changes in the sample labels. Finally, an efficient incremental paradigm is developed to update the model with newly labelled samples instead of re-training, resulting in improved performance and efficiency. Extensive comparative experiments confirm that our approach outperforms other imbalanced active learning methods.
- 21 May 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Knowledge and Data Engineering
- Vol. 38 (8) , 5047-5061
Enhancing Active Learning for Class Imbalance With an Incrementally Weighted Approach
Active learning can significantly reduce the cost of labeling instances while improving model performance. However, similar to other traditional algorithms, active learning encounters the problem of class imbalance and delivers sub-optimal performance. Additionally, existing approaches suffer from poor performance and are time-consuming. To address these issues, we propose an Actively Incrementally Weighted Broad Learning System (AI-WBLS). Firstly, we introduce an active learning framework based on the weighted broad learning system, which employs a double uncertainty sample selection strategy to enhance the value and reasonableness of sample selection in each iteration of active learning. To further improve the model's adaptability during the iterative learning process, an adaptive weighting strategy is designed to adaptively modify the penalty weights according to the changes in the sample labels. Finally, an efficient incremental paradigm is developed to update the model with newly labelled samples instead of re-training, resulting in improved performance and efficiency. Extensive comparative experiments confirm that our approach outperforms other imbalanced active learning methods.
- 8 May 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Vehicular Technology
- Vol. PP (00189545) , 1-14
Cross-City Traffic Prediction via Self-Supervised Graph Learning
Traffic prediction plays a critical role in intelligent transportation systems. Recently, data-driven methods for traffic prediction have become increasingly popular and have outperformed traditional approaches in terms of effectiveness. However, the data scarcity problem that arises from inadequate sensing and data storage infrastructure in underdeveloped urban areas and dilapidated districts impedes the deployment of existing deep learning-based models, which typically require substantial training data. To address these issues, we propose a novel self-supervised graph learning-based cross-city learning framework (SSGL-CTP) for traffic prediction across cities. The framework first pretrains a transferable spatial feature extractor on a data-abundant source city and then adapts it to the target city through parameter transfer, without requiring direct cross-city data sharing. Specifically, the framework combines a dynamic trajectory-transfer graph and an origin-destination graph to model short-range and long-range spatial-temporal dependencies, and learns transferable representations through masked node recovery before target-city fine-tuning. The effectiveness of SSGL-CTP is validated through extensive experiments utilizing real-world taxi data from Chengdu and Wenzhou, China. These experiments demonstrate its superiority over contemporary baseline methods, with improvements of up to 9.2%.
- 8 May 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Vehicular Technology
- Vol. PP (00189545) , 1-14
Cross-City Traffic Prediction via Self-Supervised Graph Learning
Traffic prediction plays a critical role in intelligent transportation systems. Recently, data-driven methods for traffic prediction have become increasingly popular and have outperformed traditional approaches in terms of effectiveness. However, the data scarcity problem that arises from inadequate sensing and data storage infrastructure in underdeveloped urban areas and dilapidated districts impedes the deployment of existing deep learning-based models, which typically require substantial training data. To address these issues, we propose a novel self-supervised graph learning-based cross-city learning framework (SSGL-CTP) for traffic prediction across cities. The framework first pretrains a transferable spatial feature extractor on a data-abundant source city and then adapts it to the target city through parameter transfer, without requiring direct cross-city data sharing. Specifically, the framework combines a dynamic trajectory-transfer graph and an origin-destination graph to model short-range and long-range spatial-temporal dependencies, and learns transferable representations through masked node recovery before target-city fine-tuning. The effectiveness of SSGL-CTP is validated through extensive experiments utilizing real-world taxi data from Chengdu and Wenzhou, China. These experiments demonstrate its superiority over contemporary baseline methods, with improvements of up to 9.2%.
- Open Access
- 15 December 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Mobile Computing
- Vol. 25 (6) , 7685-7697
HeroCS: Cooperative Courier Scheduling for Heterogeneous Tasks in Last-Mile Delivery
In last-mile delivery, efficient courier scheduling for heterogeneous tasks (i.e., delivery, pick-up, and customer expansion tasks) simultaneously benefits customers, couriers, and the platform. Existing scheduling methods for heterogeneous tasks neglect long-term optimization or are based on simple agent mobility settings. In this work, we focus on a scenario with varying task characteristics compared to existing studies and explore reinforcement learning for courier scheduling in last-mile delivery, considering fine-grained courier mobility. It is challenging due to: i) the large state and action space; ii) the courier cooperation under asynchronous decision-making caused by various task service times and courier travel times between location pairs; and iii) the multi-objective optimization under the dynamic environment. Therefore, we propose a heterogeneous task-aware cooperative courier scheduling system, HeroCS, to improve courier working efficiency and fairness in last-mile delivery. Specifically, we first design a distance-constrained courier modeling module to generate the single courier scheduling decisions, where a distance-aware top-$k$ action pruning scheme is proposed to reduce state representation and action space. Then, a cooperative scheduling learning module is explored for optimizing courier cooperation. A status-aware action masking scheme is designed to solve asynchronous decision-making in model training. We also design a hybrid reward function to optimize various objectives adaptively. Extensive evaluation with real-world data from one of the largest logistics companies in China demonstrates that compared to state-of-the-art methods, HeroCS improves the task completion rate by up to 40.7% and reduces courier unfairness by up to 83.3%.- 15 December 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Mobile Computing
- Vol. 25 (6) , 7685-7697
Open AccessHeroCS: Cooperative Courier Scheduling for Heterogeneous Tasks in Last-Mile Delivery
In last-mile delivery, efficient courier scheduling for heterogeneous tasks (i.e., delivery, pick-up, and customer expansion tasks) simultaneously benefits customers, couriers, and the platform. Existing scheduling methods for heterogeneous tasks neglect long-term optimization or are based on simple agent mobility settings. In this work, we focus on a scenario with varying task characteristics compared to existing studies and explore reinforcement learning for courier scheduling in last-mile delivery, considering fine-grained courier mobility. It is challenging due to: i) the large state and action space; ii) the courier cooperation under asynchronous decision-making caused by various task service times and courier travel times between location pairs; and iii) the multi-objective optimization under the dynamic environment. Therefore, we propose a heterogeneous task-aware cooperative courier scheduling system, HeroCS, to improve courier working efficiency and fairness in last-mile delivery. Specifically, we first design a distance-constrained courier modeling module to generate the single courier scheduling decisions, where a distance-aware top-$k$ action pruning scheme is proposed to reduce state representation and action space. Then, a cooperative scheduling learning module is explored for optimizing courier cooperation. A status-aware action masking scheme is designed to solve asynchronous decision-making in model training. We also design a hybrid reward function to optimize various objectives adaptively. Extensive evaluation with real-world data from one of the largest logistics companies in China demonstrates that compared to state-of-the-art methods, HeroCS improves the task completion rate by up to 40.7% and reduces courier unfairness by up to 83.3%. - 3 December 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Network Science and Engineering
- Vol. 13, 4226-4241
Uncertainty-Aware Decisioning for Robust Delivery Zone Partition in Last-Mile Logistics
In last-mile logistics, robust delivery zone partitioning is critical for ensuring timely service and maintaining a positive courier experience. However, existing network-structured spatial partitioning strategies often fail to address heterogeneous uncertainties in both delivery demand and courier supply. In particular, two challenges remain: (i) irregular demand patterns with weak periodicity, and (ii) stochastic courier availability. To this end, we propose the Prediction and Sampling Then Optimization (PSTO) paradigm, which integrates hybrid uncertainty modeling with Monte Carlo optimization. Specifically, we implement a model named RobustDZP, which combines time-series prediction with residual learning for demand estimation, a multi-agent RL sampler for supply estimation, and an iterative perturb-and-vote algorithm for partition optimization. Extensive experiments on a large real-world dataset from JD Logistics demonstrate that our approach improves delivery timeliness by over 16.3% and significantly outperforms baselines under stress tests. Furthermore, we present a real-world case study to validate the practical effectiveness of our framework and highlight key lessons for designing robust and well-received partition schemes.
- 3 December 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Network Science and Engineering
- Vol. 13, 4226-4241
Uncertainty-Aware Decisioning for Robust Delivery Zone Partition in Last-Mile Logistics
In last-mile logistics, robust delivery zone partitioning is critical for ensuring timely service and maintaining a positive courier experience. However, existing network-structured spatial partitioning strategies often fail to address heterogeneous uncertainties in both delivery demand and courier supply. In particular, two challenges remain: (i) irregular demand patterns with weak periodicity, and (ii) stochastic courier availability. To this end, we propose the Prediction and Sampling Then Optimization (PSTO) paradigm, which integrates hybrid uncertainty modeling with Monte Carlo optimization. Specifically, we implement a model named RobustDZP, which combines time-series prediction with residual learning for demand estimation, a multi-agent RL sampler for supply estimation, and an iterative perturb-and-vote algorithm for partition optimization. Extensive experiments on a large real-world dataset from JD Logistics demonstrate that our approach improves delivery timeliness by over 16.3% and significantly outperforms baselines under stress tests. Furthermore, we present a real-world case study to validate the practical effectiveness of our framework and highlight key lessons for designing robust and well-received partition schemes.
- 23 September 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Industrial Informatics
- Vol. 21 (12) , 9745-9756
A Semi-decentralized Data-Model-Driven Optimization Scheme for Coordinated Control of Large-Scale Wind Farm Power Maximization
The wake effect, which significantly degrades the power output of a wind farm, has prompted widespread consideration of the farm-level power generation optimization problem. However, the optimization problem is highly challenging when a large-scale wind farm encounters highly dynamic wind conditions. To address this issue, we proposed a semi-decentralized data-model-driven optimization scheme that utilizes real-time data by interacting with the wind farm and has a fast solving speed. First, the optimization problem is divided into several static subproblems according to the power efficiency in different wind directions. For every static subproblem, the large-scale farm is decomposed into clusters based on the wake model and the spectral clustering algorithm. When controlled online, data-driven methods are performed in parallel for power maximization according to the cluster division result. In addition, a multivariable coupling wake model is employed to validate the effectiveness of the optimization scheme. Simulation results indicate an apparent enhancement in energy output for large-scale wind farms operating under dynamic wind conditions.
- 23 September 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Industrial Informatics
- Vol. 21 (12) , 9745-9756
A Semi-decentralized Data-Model-Driven Optimization Scheme for Coordinated Control of Large-Scale Wind Farm Power Maximization
The wake effect, which significantly degrades the power output of a wind farm, has prompted widespread consideration of the farm-level power generation optimization problem. However, the optimization problem is highly challenging when a large-scale wind farm encounters highly dynamic wind conditions. To address this issue, we proposed a semi-decentralized data-model-driven optimization scheme that utilizes real-time data by interacting with the wind farm and has a fast solving speed. First, the optimization problem is divided into several static subproblems according to the power efficiency in different wind directions. For every static subproblem, the large-scale farm is decomposed into clusters based on the wake model and the spectral clustering algorithm. When controlled online, data-driven methods are performed in parallel for power maximization according to the cluster division result. In addition, a multivariable coupling wake model is employed to validate the effectiveness of the optimization scheme. Simulation results indicate an apparent enhancement in energy output for large-scale wind farms operating under dynamic wind conditions.
- Open Access
- 20 July 2025
- Published by Association for Computing Machinery (ACM)
- p. 2703-2712
Effective AOI-level Parcel Volume Prediction: When Lookahead Parcels Matter
- 20 July 2025
- Published by Association for Computing Machinery (ACM)
- p. 2703-2712
Open AccessEffective AOI-level Parcel Volume Prediction: When Lookahead Parcels Matter
- 4 July 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Communications Surveys & Tutorials
- Vol. 28, 149-180
Missing Data Recovery Methods on Multivariate Time Series in IoT: A Comprehensive Survey
This survey comprehensively examines the challenges and methodologies for missing data recovery in Multivariate Time Series (MTS) within the context of Internet of Things (IoT) environments. It delves into the distinct mechanisms and patterns of missing data that are prevalent in IoT MTS, providing a detailed categorization of existing methods into three primary frameworks: non-data mining, traditional data mining, and deep learning approaches. Each category is critically analyzed to highlight strategic improvements tailored to MTS data and their applicability to various missing patterns of IoT. The paper also discusses the computational demand, convergence speed, real-time capability, and adaptability to missing patterns of these methods, offering a thorough evaluation of their strengths and weaknesses. By synthesizing current methodologies and identifying gaps in the literature from 2013 to 2024, this work identifies future research directions aimed at enhancing the robustness and efficiency of missing data recovery in complex IoT systems.
- 4 July 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Communications Surveys & Tutorials
- Vol. 28, 149-180
Missing Data Recovery Methods on Multivariate Time Series in IoT: A Comprehensive Survey
This survey comprehensively examines the challenges and methodologies for missing data recovery in Multivariate Time Series (MTS) within the context of Internet of Things (IoT) environments. It delves into the distinct mechanisms and patterns of missing data that are prevalent in IoT MTS, providing a detailed categorization of existing methods into three primary frameworks: non-data mining, traditional data mining, and deep learning approaches. Each category is critically analyzed to highlight strategic improvements tailored to MTS data and their applicability to various missing patterns of IoT. The paper also discusses the computational demand, convergence speed, real-time capability, and adaptability to missing patterns of these methods, offering a thorough evaluation of their strengths and weaknesses. By synthesizing current methodologies and identifying gaps in the literature from 2013 to 2024, this work identifies future research directions aimed at enhancing the robustness and efficiency of missing data recovery in complex IoT systems.
- 23 May 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Mobile Computing
- Vol. 24 (10) , 10840-10852
Toward Generalized Urban Computing: Pretraining a Spatial-Temporal Model for Diverse Urban Tasks
Urban computing leverages data analysis to improve urban areas’ efficiency and sustainability, tackling tasks like traffic management, crime forecasting, and air quality predictions. Current models, while efficient, often struggle with tasks beyond their initial training due to limited flexibility. Typically, new tasks require developing specialized models, which may not perform optimally with limited data. To overcome these challenges, we propose the development of a universal pretrained model that understands a city’s various aspects comprehensively. This model serves as a robust foundation, ready to be quickly adjusted for different urban tasks as they arise, even if they occur in different cities. Unlike language models, urban computing models must handle unique spatial-temporal dynamics, making standard pretraining techniques inadequate. Our approach includes a spatial-temporal module with multi-graph convolution and temporal attention mechanisms, capturing the necessary spatial-temporal patterns during pretraining. We also integrate a prompt-tuning module within this framework, which can be adapted for new predictive tasks. The results of extensive experiments on four urban predictive tasks across two cities demonstrate the effectiveness of our model.
- 23 May 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Mobile Computing
- Vol. 24 (10) , 10840-10852
Toward Generalized Urban Computing: Pretraining a Spatial-Temporal Model for Diverse Urban Tasks
Urban computing leverages data analysis to improve urban areas’ efficiency and sustainability, tackling tasks like traffic management, crime forecasting, and air quality predictions. Current models, while efficient, often struggle with tasks beyond their initial training due to limited flexibility. Typically, new tasks require developing specialized models, which may not perform optimally with limited data. To overcome these challenges, we propose the development of a universal pretrained model that understands a city’s various aspects comprehensively. This model serves as a robust foundation, ready to be quickly adjusted for different urban tasks as they arise, even if they occur in different cities. Unlike language models, urban computing models must handle unique spatial-temporal dynamics, making standard pretraining techniques inadequate. Our approach includes a spatial-temporal module with multi-graph convolution and temporal attention mechanisms, capturing the necessary spatial-temporal patterns during pretraining. We also integrate a prompt-tuning module within this framework, which can be adapted for new predictive tasks. The results of extensive experiments on four urban predictive tasks across two cities demonstrate the effectiveness of our model.