Jingwei Ge
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Jingwei Ge has a total of 62 co-authors. Here are the top co-authors by number of shared publications:
- Li Li
Department of Automation, Tsinghua University, Beijing, China
10 shared publications - Cheng Chang
Department of Automation, Tsinghua University, Beijing, China
7 shared publications - Jiawei Zhang
Department of Automation, Tsinghua University, Beijing, China
6 shared publications - Yi Zhang
Institute of Future Human Habitats, Tsinghua Shenzhen International Graduate School, Tsinghua University, Shenzhen 518055, China
4 shared publications - Danya Yao
Tsinghua University
3 shared publications - Fei-Yue Wang
Institute of Automation, Chinese Academy of Sciences
3 shared publications
Latest Publications
- 6 July 2026
- Published by Elsevier in Transportation Research Part C: Emerging Technologies
- Vol. 191
Providing massive scenario data for intelligent vehicles using road-side cameras
- 6 July 2026
- Published by Elsevier in Transportation Research Part C: Emerging Technologies
- Vol. 191
Providing massive scenario data for intelligent vehicles using road-side cameras
- 25 February 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Automation Science and Engineering
- Vol. 23 (15455955) , 10128-10143
Automation 5.0: The Step to Systems Intelligence for a Sustainable Future
The increasing automation of modern systems—across industry, healthcare, mobility, and beyond—has raised the demand for human reasoning and expertise, while alleviating the burden of repetitive tasks. This transformation is driving us toward Automation 5.0, a new paradigm aimed at unleashing human potential. Recently, the development of foundation models (FMs) has reinvigorated its realization, making it both urgent and critical to explore the concept of Automation 5.0 in this new era. In this article, we define Automation 5.0, discuss its significance, and emphasize its new world, thinking, and technology with the goal of achieving knowledge automation. A framework, based on business FMs, human-oriented operating systems, and scenarios engineering, is proposed, where biological, robotic, and digital humans work together in three modes: autonomous, parallel, and expert/emergency modes. Additionally, a diverse range of its scenarios and applications are summarized and discussed, such as Manufacturing 5.0, Healthcare 5.0, and Transportation 5.0. We believe that Automation 5.0 can drive the co-evolution of productivity and production relations across all domains, propelling society toward a “Safety, Security, Sustainability, Sensitivity, Service, Smartness (6S)” future.
- 25 February 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Automation Science and Engineering
- Vol. 23 (15455955) , 10128-10143
Automation 5.0: The Step to Systems Intelligence for a Sustainable Future
The increasing automation of modern systems—across industry, healthcare, mobility, and beyond—has raised the demand for human reasoning and expertise, while alleviating the burden of repetitive tasks. This transformation is driving us toward Automation 5.0, a new paradigm aimed at unleashing human potential. Recently, the development of foundation models (FMs) has reinvigorated its realization, making it both urgent and critical to explore the concept of Automation 5.0 in this new era. In this article, we define Automation 5.0, discuss its significance, and emphasize its new world, thinking, and technology with the goal of achieving knowledge automation. A framework, based on business FMs, human-oriented operating systems, and scenarios engineering, is proposed, where biological, robotic, and digital humans work together in three modes: autonomous, parallel, and expert/emergency modes. Additionally, a diverse range of its scenarios and applications are summarized and discussed, such as Manufacturing 5.0, Healthcare 5.0, and Transportation 5.0. We believe that Automation 5.0 can drive the co-evolution of productivity and production relations across all domains, propelling society toward a “Safety, Security, Sustainability, Sensitivity, Service, Smartness (6S)” future.
- 28 January 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Cognitive Communications and Networking
- Vol. 12, 5913-5936
Cognitive Underwater Acoustic Networking and Target Tracking: A Comprehensive Survey
Underwater acoustic networks are evolving from static, manually-configured systems into cognitive, learning-enabled platforms that can perceive, reason, and adapt to harsh ocean dynamics in real-time. Accurate target tracking is a core service of these networks and underpins marine resource exploration, environmental monitoring, and maritime security. Existing reviews or surveys, however, rarely examine underwater acoustic target tracking through the lens of cognitive communications and networking, and often offer a narrow perspective on addressing the paradigm shifts driven by emerging technologies like deep learning. To fill this gap, this work presents a systematic survey of this field and introduces an innovative three-dimensional taxonomy framework based on the three levels of the cognitive underwater acoustic target tracking network: the target layer, the perception layer, and the processing layer.Within this framework, we comprehensively survey the literature over the period 2016-2025, spanning from the theoretical foundations to diverse algorithmic approaches in underwater acoustic target tracking. Particularly, we emphasize the transformative potential and recent advancements of machine learning techniques, including deep learning and reinforcement learning, in enhancing the performance and adaptability of cognitive underwater tracking systems. Finally, this survey concludes by identifying key challenges in the field and proposing future avenues based on emerging technologies such as data desensitization, embodied intelligence, and large models.
- 28 January 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Cognitive Communications and Networking
- Vol. 12, 5913-5936
Cognitive Underwater Acoustic Networking and Target Tracking: A Comprehensive Survey
Underwater acoustic networks are evolving from static, manually-configured systems into cognitive, learning-enabled platforms that can perceive, reason, and adapt to harsh ocean dynamics in real-time. Accurate target tracking is a core service of these networks and underpins marine resource exploration, environmental monitoring, and maritime security. Existing reviews or surveys, however, rarely examine underwater acoustic target tracking through the lens of cognitive communications and networking, and often offer a narrow perspective on addressing the paradigm shifts driven by emerging technologies like deep learning. To fill this gap, this work presents a systematic survey of this field and introduces an innovative three-dimensional taxonomy framework based on the three levels of the cognitive underwater acoustic target tracking network: the target layer, the perception layer, and the processing layer.Within this framework, we comprehensively survey the literature over the period 2016-2025, spanning from the theoretical foundations to diverse algorithmic approaches in underwater acoustic target tracking. Particularly, we emphasize the transformative potential and recent advancements of machine learning techniques, including deep learning and reinforcement learning, in enhancing the performance and adaptability of cognitive underwater tracking systems. Finally, this survey concludes by identifying key challenges in the field and proposing future avenues based on emerging technologies such as data desensitization, embodied intelligence, and large models.
- 2 January 2026
- Published by Elsevier in Chaos, Solitons & Fractals
- Vol. 205
How subgroups affect the power law governing pedestrian avoidance interactions
- 2 January 2026
- Published by Elsevier in Chaos, Solitons & Fractals
- Vol. 205
How subgroups affect the power law governing pedestrian avoidance interactions
- 3 November 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE/CAA Journal of Automatica Sinica
- Vol. 12 (10) , 1959-1962
Rethinking Off-Road ADAS: A Perspective on the Generative Co-Pilot Paradigm
Driven by advancements in artificial intelligence technologies such as deep learning, core intelligent driving technologies like advanced driver assistance systems (ADAS) have made significant advances. Some advanced ADAS systems, particularly in highway scenarios, have reached or even surpassed human drivers in terms of precision and reliability [1]. This mainstream development path is based on a replacement paradigm, whose central goal is to relieve human drivers of monotonous, repetitive tasks such as highway commuting, maximizing traffic efficiency and safety [2]. This paradigm aims to replace error-prone human operators with a tireless, consistent machine intelligence.
- 3 November 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE/CAA Journal of Automatica Sinica
- Vol. 12 (10) , 1959-1962
Rethinking Off-Road ADAS: A Perspective on the Generative Co-Pilot Paradigm
Driven by advancements in artificial intelligence technologies such as deep learning, core intelligent driving technologies like advanced driver assistance systems (ADAS) have made significant advances. Some advanced ADAS systems, particularly in highway scenarios, have reached or even surpassed human drivers in terms of precision and reliability [1]. This mainstream development path is based on a replacement paradigm, whose central goal is to relieve human drivers of monotonous, repetitive tasks such as highway commuting, maximizing traffic efficiency and safety [2]. This paradigm aims to replace error-prone human operators with a tireless, consistent machine intelligence.
- 24 June 2025
- Published by Springer Nature
- p. 241-256
An Enhanced MILP-Based Verifier for Adversary Robustness of Neural Networks
- 24 June 2025
- Published by Springer Nature
- p. 241-256
An Enhanced MILP-Based Verifier for Adversary Robustness of Neural Networks
- 15 October 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Intelligent Vehicles
- Vol. 9 (8) , 5247-5249
Large Models Defining a New Era in Intelligence Testing: A Short Discussion and Exploration
This perspective presents a short yet comprehensive discussion on the rapid advancements in the field of unmanned system testing enhancing by large models. We delve into the pivotal aspects of testing, elucidating the roles of the Testing Operating System (TOS), Testing Foundational Intelligence (TFI), and Testing Scenario Engineering (TSE), and also the challenges they face from a testing perspective.
- 15 October 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Intelligent Vehicles
- Vol. 9 (8) , 5247-5249
Large Models Defining a New Era in Intelligence Testing: A Short Discussion and Exploration
This perspective presents a short yet comprehensive discussion on the rapid advancements in the field of unmanned system testing enhancing by large models. We delve into the pivotal aspects of testing, elucidating the roles of the Testing Operating System (TOS), Testing Foundational Intelligence (TFI), and Testing Scenario Engineering (TSE), and also the challenges they face from a testing perspective.
- 4 October 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Intelligent Transportation Systems
- Vol. 25 (12) , 21559-21571
Predictive Vehicle Stability Assessment Using Lyapunov Exponent Under Extreme Conditions
Under extreme conditions, vehicles may encounter critical instability and cause traffic accidents due to the tire force saturation. In such cases, accurately predicting the vehicle instability is conducive to vehicle safety because drivers or vehicle controllers can be alerted and take early interventions to ensure driving safety. However, the existing stability assessment methods tend to be conservative, hard to quantify, and often ignore the coupled longitudinal and lateral dynamics, as well as the nonlinear characteristics of tires. Simultaneously, under extreme operating conditions, the assessment of vehicle potential risk imposes higher demands on the prediction accuracy of vehicle motion states. To address these 2 issues, this paper proposes a predictive vehicle stability assessment method using 3-dimensional Lyapunov exponents (3D-LEs) for a nonlinear vehicle system. Firstly, a nonlinear 8-degree-of-freedom vehicle dynamics model is constructed for an electric vehicle, aiming to capture the coupling dynamic characteristics and the tire force saturation under extreme conditions. To minimize the simulation-reality disparities, the vehicle parameters are automatically calibrated through Bayesian optimization using field test data. Secondly, to predict the potential risk of vehicle instability precisely, a physics-informed neural network based state prediction module is established for the vehicle stability assessment system. The ordinary differential equations of the vehicle system are integrated into neural networks to obtain physically consistent predictions of vehicle dynamic motion. Finally, the 3D-LEs, encompassing lateral motion, yaw motion, and roll motion, are employed to concurrently evaluate vehicle stability. Experimental results demonstrate that the predictive vehicle stability assessment method accurately evaluates the stability of predicted state sequences, enabling safer and more stable control under extreme conditions.
- 4 October 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Intelligent Transportation Systems
- Vol. 25 (12) , 21559-21571
Predictive Vehicle Stability Assessment Using Lyapunov Exponent Under Extreme Conditions
Under extreme conditions, vehicles may encounter critical instability and cause traffic accidents due to the tire force saturation. In such cases, accurately predicting the vehicle instability is conducive to vehicle safety because drivers or vehicle controllers can be alerted and take early interventions to ensure driving safety. However, the existing stability assessment methods tend to be conservative, hard to quantify, and often ignore the coupled longitudinal and lateral dynamics, as well as the nonlinear characteristics of tires. Simultaneously, under extreme operating conditions, the assessment of vehicle potential risk imposes higher demands on the prediction accuracy of vehicle motion states. To address these 2 issues, this paper proposes a predictive vehicle stability assessment method using 3-dimensional Lyapunov exponents (3D-LEs) for a nonlinear vehicle system. Firstly, a nonlinear 8-degree-of-freedom vehicle dynamics model is constructed for an electric vehicle, aiming to capture the coupling dynamic characteristics and the tire force saturation under extreme conditions. To minimize the simulation-reality disparities, the vehicle parameters are automatically calibrated through Bayesian optimization using field test data. Secondly, to predict the potential risk of vehicle instability precisely, a physics-informed neural network based state prediction module is established for the vehicle stability assessment system. The ordinary differential equations of the vehicle system are integrated into neural networks to obtain physically consistent predictions of vehicle dynamic motion. Finally, the 3D-LEs, encompassing lateral motion, yaw motion, and roll motion, are employed to concurrently evaluate vehicle stability. Experimental results demonstrate that the predictive vehicle stability assessment method accurately evaluates the stability of predicted state sequences, enabling safer and more stable control under extreme conditions.
- 20 August 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Intelligent Transportation Systems Magazine
- Vol. 17 (3) , 58-66
Boosting the Training of Deep Reinforcement Learning Traffic Control by Using the World Model
Deep reinforcement learning (DRL) traffic control attracts increasing interest since it is widely viewed as a powerful tool for alleviating congestion that significantly impacts people’s daily lives. However, traditional DRL models require a substantial amount of interactive data that are difficult to collect in both field and simulation tests. To overcome these challenges, this article adopts a world model for better training of DRL models for traffic control. The proposed world model can quickly learn traffic dynamics and the influence of traffic control based on limited field and simulation data. The DRL control model can then be established based on the training data generated by the world model instead. Experimental results demonstrate that DRL traffic control using world models can achieve a noticeably better signal control strategy, providing a promising solution to optimize urban traffic.
- 20 August 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Intelligent Transportation Systems Magazine
- Vol. 17 (3) , 58-66
Boosting the Training of Deep Reinforcement Learning Traffic Control by Using the World Model
Deep reinforcement learning (DRL) traffic control attracts increasing interest since it is widely viewed as a powerful tool for alleviating congestion that significantly impacts people’s daily lives. However, traditional DRL models require a substantial amount of interactive data that are difficult to collect in both field and simulation tests. To overcome these challenges, this article adopts a world model for better training of DRL models for traffic control. The proposed world model can quickly learn traffic dynamics and the influence of traffic control based on limited field and simulation data. The DRL control model can then be established based on the training data generated by the world model instead. Experimental results demonstrate that DRL traffic control using world models can achieve a noticeably better signal control strategy, providing a promising solution to optimize urban traffic.
- 15 May 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Intelligent Vehicles
- Vol. 9 (12) , 7724-7737
Life-Long Learning and Testing for Automated Vehicles via Adaptive Scenario Sampling as a Continuous Optimization Process
Sampling critical testing scenarios is an essential step in intelligence testing for Automated Vehicles (AVs). However, due to the lack of prior knowledge on the distribution of critical scenarios in sampling space, we can hardly efficiently find the critical scenarios or accurately evaluate the intelligence of AVs. To solve this problem, we formulate the testing as a continuous optimization process which iteratively generates potential critical scenarios and meanwhile evaluates these scenarios. A bi-level loop is proposed for such life-long learning and testing. In the outer loop, we iteratively learn space knowledge by evaluating AV in the already sampled scenarios and then sample new scenarios based on the retained knowledge. Outer loop stops when all generated samples cover the whole space. While to maximize the coverage of the space in each outer loop, we set an inner loop which receives newly generated samples in outer loop and outputs the updated positions of these samples. We assume that points in a small sphere-like subspace can be covered (or represented) by the point in the center of this sphere. Therefore, we can apply a multi-rounds heuristic strategy to move and pack these spheres in space to find the best covering solution. The simulation results show that faster and more accurate evaluation of AVs can be achieved with more critical scenarios.
- 15 May 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Intelligent Vehicles
- Vol. 9 (12) , 7724-7737
Life-Long Learning and Testing for Automated Vehicles via Adaptive Scenario Sampling as a Continuous Optimization Process
Sampling critical testing scenarios is an essential step in intelligence testing for Automated Vehicles (AVs). However, due to the lack of prior knowledge on the distribution of critical scenarios in sampling space, we can hardly efficiently find the critical scenarios or accurately evaluate the intelligence of AVs. To solve this problem, we formulate the testing as a continuous optimization process which iteratively generates potential critical scenarios and meanwhile evaluates these scenarios. A bi-level loop is proposed for such life-long learning and testing. In the outer loop, we iteratively learn space knowledge by evaluating AV in the already sampled scenarios and then sample new scenarios based on the retained knowledge. Outer loop stops when all generated samples cover the whole space. While to maximize the coverage of the space in each outer loop, we set an inner loop which receives newly generated samples in outer loop and outputs the updated positions of these samples. We assume that points in a small sphere-like subspace can be covered (or represented) by the point in the center of this sphere. Therefore, we can apply a multi-rounds heuristic strategy to move and pack these spheres in space to find the best covering solution. The simulation results show that faster and more accurate evaluation of AVs can be achieved with more critical scenarios.