Baichuan Lou
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
Baichuan Lou has a total of 19 co-authors. Here are the top co-authors by number of shared publications:
- Chen Lv
School of Mechanical and Aerospace Engineering Nanyang Technological University Singapore Singapore
5 shared publications - Bohang Liang
School of Mechanical and Aerospace Engineering and the School of Electrical and Electronic Engineering, Nanyang Technological University, Singapore
1 shared publication - Domenico Campolo
School of Mechanical and Aerospace Engineering Nanyang Technological University Singapore
1 shared publication - Fei-Yue Wang
Institute of Automation, Chinese Academy of Sciences
1 shared publication - Hai-Tao Zhang
Huazhong University of Science and Technology
1 shared publication - Henglai Wei
School of Transportation Science and Engineering, Beihang University, Beijing, China
1 shared publication
Latest Publications
- 20 November 2025
- Published by Elsevier in Transportation Research Part C: Emerging Technologies
- Vol. 182
Adversarial traffic scene generation considering harm, rarity, and ambiguity for autonomous driving testing
- 20 November 2025
- Published by Elsevier in Transportation Research Part C: Emerging Technologies
- Vol. 182
Adversarial traffic scene generation considering harm, rarity, and ambiguity for autonomous driving testing
- 2 July 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Intelligent Transportation Systems
- Vol. 26 (10) , 16840-16853
Traffic Scene Representation and Encoding With Graph Structure Learning and Exploration
Effective scene representation is critical for trajectory generation tasks in autonomous driving. Existing attention-based methods often rely on fixed-length input elements, limiting their ability to adapt to dynamic traffic environments, and frequently overlook lane connectivity. Methods that consider lane connectivity often segment lanes into smaller pieces, which consequently creates a more complex graph structure with an increased number of nodes and edges. Additionally, many current approaches select agent interactions based on fixed distance thresholds, which may miss important long-range or indirect interactions and ignore the fact that proximity does not indicate interaction. In this paper, we propose SceneGNN, a novel framework for learning traffic scenario representation through interaction graph learning and lane graph exploration. SceneGNN constructs a single heterogeneous graph that integrates both agents and lanes, leveraging high-definition maps without over-segmentation. To model lane connectivity more effectively, we introduce LaneGNN, which combines an Omnidirectional Lane Aggregator (OLA) and Directional Lane Explorer (DLE) to explore lane-to-lane interdependencies. Additionally, instead of relying on proximity-based heuristics, our interaction graph learner dynamically constructs inter-agent edges based on learned features, allowing the model to capture meaningful interactions beyond mere distance. We evaluate SceneGNN on the Waymo Open Motion Dataset, where it achieves competitive performance. Our results demonstrate that by efficiently capturing both agent-lane relationships and inter-agent interactions, SceneGNN improves the accuracy and scalability of multi-agent trajectory prediction for real-world autonomous driving applications.
- 2 July 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Intelligent Transportation Systems
- Vol. 26 (10) , 16840-16853
Traffic Scene Representation and Encoding With Graph Structure Learning and Exploration
Effective scene representation is critical for trajectory generation tasks in autonomous driving. Existing attention-based methods often rely on fixed-length input elements, limiting their ability to adapt to dynamic traffic environments, and frequently overlook lane connectivity. Methods that consider lane connectivity often segment lanes into smaller pieces, which consequently creates a more complex graph structure with an increased number of nodes and edges. Additionally, many current approaches select agent interactions based on fixed distance thresholds, which may miss important long-range or indirect interactions and ignore the fact that proximity does not indicate interaction. In this paper, we propose SceneGNN, a novel framework for learning traffic scenario representation through interaction graph learning and lane graph exploration. SceneGNN constructs a single heterogeneous graph that integrates both agents and lanes, leveraging high-definition maps without over-segmentation. To model lane connectivity more effectively, we introduce LaneGNN, which combines an Omnidirectional Lane Aggregator (OLA) and Directional Lane Explorer (DLE) to explore lane-to-lane interdependencies. Additionally, instead of relying on proximity-based heuristics, our interaction graph learner dynamically constructs inter-agent edges based on learned features, allowing the model to capture meaningful interactions beyond mere distance. We evaluate SceneGNN on the Waymo Open Motion Dataset, where it achieves competitive performance. Our results demonstrate that by efficiently capturing both agent-lane relationships and inter-agent interactions, SceneGNN improves the accuracy and scalability of multi-agent trajectory prediction for real-world autonomous driving applications.
- Top Cited Papers
- 11 January 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Intelligent Vehicles
- Vol. 9 (2) , 4145-4171
Autonomous Navigation for eVTOL: Review and Future Perspectives
This survey paper explores the emergent domain of electric vertical takeoff and landing vehicles (eVTOLs), emphasizing the critical role of autonomous navigation capabilities essential for their effective integration and operation in complex urban environments. Pioneering in this review is the introduction of a novel six-level autonomy concept for eVTOLs, categorizing them based on their degree of intelligence. The paper offers a comprehensive review of state-of-the-art developments that together fortify the autonomous functionality of eVTOLs, with a special focus on enhanced perception, intelligent planning, and advanced control. Perception technologies empower eVTOLs with the environmental awareness crucial for navigating the intricate urban airspace, while advanced planning algorithms navigate their paths through densely populated skies, ensuring optimal routing and safety. Control strategies are developed for their ability to endow these eVTOLs with the stability and agility needed to execute complex flight dynamics. The synthesis of these elements forms the backbone of autonomous navigation for eVTOLs, outlining a clear direction for future eVTOL research. This comprehensive survey can serve as a vital resource for enhancing the autonomy of eVTOLs, steering them towards a future where they integrate effortlessly into intelligent urban transportation systems.
- 11 January 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Intelligent Vehicles
- Vol. 9 (2) , 4145-4171
Top Cited PapersAutonomous Navigation for eVTOL: Review and Future Perspectives
This survey paper explores the emergent domain of electric vertical takeoff and landing vehicles (eVTOLs), emphasizing the critical role of autonomous navigation capabilities essential for their effective integration and operation in complex urban environments. Pioneering in this review is the introduction of a novel six-level autonomy concept for eVTOLs, categorizing them based on their degree of intelligence. The paper offers a comprehensive review of state-of-the-art developments that together fortify the autonomous functionality of eVTOLs, with a special focus on enhanced perception, intelligent planning, and advanced control. Perception technologies empower eVTOLs with the environmental awareness crucial for navigating the intricate urban airspace, while advanced planning algorithms navigate their paths through densely populated skies, ensuring optimal routing and safety. Control strategies are developed for their ability to endow these eVTOLs with the stability and agility needed to execute complex flight dynamics. The synthesis of these elements forms the backbone of autonomous navigation for eVTOLs, outlining a clear direction for future eVTOL research. This comprehensive survey can serve as a vital resource for enhancing the autonomy of eVTOLs, steering them towards a future where they integrate effortlessly into intelligent urban transportation systems.
- Open Access
A Planning Framework for Robotic Insertion Tasks via Hydroelastic Contact Model
Robotic contact-rich insertion tasks present a significant challenge for motion planning due to the complex force interaction between robots and objects. Although many learning-based methods have shown success in contact tasks, most methods need sampling or exploring to gather sufficient experimental data. However, it is both time-consuming and expensive to conduct real-world experiments repeatedly. On the other hand, while the virtual world enables low cost and fast computations by simulators, there still exists a huge sim-to-real gap due to the inaccurate point contact model. Although finite element analysis might generate accurate results for contact tasks, it is computationally expensive. As such, this study proposes a motion planning framework with bilevel optimization to leverage relatively accurate force information with fast computation time. This framework consists of Dynamic Movement Primitives (DMPs) used to parameterize motion trajectories, Black-Box Optimization (BBO), a derivative-free approach, integrated to improve contact-rich insertion policy with hydroelastic contact model, and simulated variability to account for visual uncertainty in the real world. The accuracy of the simulated model is then validated by comparing our contact results with a benchmark Peg-in-Hole task. Using these integrated DMPs and BBO with hydroelastic contact model, the motion trajectory generated in planning is capable of guiding the robot towards successful insertion with iterative refinement.
Open AccessA Planning Framework for Robotic Insertion Tasks via Hydroelastic Contact Model
Robotic contact-rich insertion tasks present a significant challenge for motion planning due to the complex force interaction between robots and objects. Although many learning-based methods have shown success in contact tasks, most methods need sampling or exploring to gather sufficient experimental data. However, it is both time-consuming and expensive to conduct real-world experiments repeatedly. On the other hand, while the virtual world enables low cost and fast computations by simulators, there still exists a huge sim-to-real gap due to the inaccurate point contact model. Although finite element analysis might generate accurate results for contact tasks, it is computationally expensive. As such, this study proposes a motion planning framework with bilevel optimization to leverage relatively accurate force information with fast computation time. This framework consists of Dynamic Movement Primitives (DMPs) used to parameterize motion trajectories, Black-Box Optimization (BBO), a derivative-free approach, integrated to improve contact-rich insertion policy with hydroelastic contact model, and simulated variability to account for visual uncertainty in the real world. The accuracy of the simulated model is then validated by comparing our contact results with a benchmark Peg-in-Hole task. Using these integrated DMPs and BBO with hydroelastic contact model, the motion trajectory generated in planning is capable of guiding the robot towards successful insertion with iterative refinement.
- Open Access
Nonlinear Predictive Motion Control for Autonomous Mobile Robots Considering Active Fault-Tolerant Control and Regenerative Braking
To further advance the performance and safety of autonomous mobile robots (AMRs), an integrated chassis control framework is proposed. In the longitudinal motion control module, a velocity-tracking controller was designed with the integrated feedforward and feedback control algorithm. Besides, the nonlinear model predictive control (NMPC) method was applied to the four-wheel steering (4WS) path-tracking controller design. To deal with the failure of key actuators, an active fault-tolerant control (AFTC) algorithm was designed by reallocating the driving or braking torques of the remaining normal actuators, and the weighted least squares (WLS) method was used for torque reallocation. The simulation results show that AMRs can advance driving stability and braking safety in the braking failure condition with the utilization of AFTC and recapture the braking energy during decelerations.
Open AccessNonlinear Predictive Motion Control for Autonomous Mobile Robots Considering Active Fault-Tolerant Control and Regenerative Braking
To further advance the performance and safety of autonomous mobile robots (AMRs), an integrated chassis control framework is proposed. In the longitudinal motion control module, a velocity-tracking controller was designed with the integrated feedforward and feedback control algorithm. Besides, the nonlinear model predictive control (NMPC) method was applied to the four-wheel steering (4WS) path-tracking controller design. To deal with the failure of key actuators, an active fault-tolerant control (AFTC) algorithm was designed by reallocating the driving or braking torques of the remaining normal actuators, and the weighted least squares (WLS) method was used for torque reallocation. The simulation results show that AMRs can advance driving stability and braking safety in the braking failure condition with the utilization of AFTC and recapture the braking energy during decelerations.
- 26 May 2021
- Published by SAGE Publications in Proceedings of the Institution of Mechanical Engineers, Part D: Journal of Automobile Engineering
- Vol. 235 (14) , 3358-3374
Research on vehicle critical condition prediction and optimal yaw moment intervention based on nonlinear dynamics and Monte Carlo simulation
Timely and effective yaw moment intervention is required to suppress the instability tendency of vehicle under critical conditions, which is mainly caused by the overshoot of state parameters. As the development of vehicle nonlinear dynamics, the prediction of vehicle critical condition enables the vehicle to stabilize in this condition by timely yaw moment intervention. The yaw moment intervention law based on the prediction of critical conditions cannot be solely investigated by the initial motion states, since the online iterative optimization is an indispensable part in the predictive control. In this paper, the combination of threshold model, quadratic optimal yaw moment prediction method and Monte Carlo simulation provides a new approach to investigate the optimal open loop yaw moment intervention law based on initial motion states, which can be used to maintain the stability of vehicle plane motion in critical situations and optimize the predictive control method. Specifically, a total of 480,000 samples of quadratic yaw moment intervention parameters and corresponding system responses are obtained and analysed. It is certified that the optimized quadratic yaw moment can effectively suppress the overshoot of system responses. Specifically, statistics indicate that the initial value of yaw moment intervention plays an important role in preventing instability, but with the increase of speed and steering angle, the final yaw moment will be the decisive factor to maintain the lateral stability.
- 26 May 2021
- Published by SAGE Publications in Proceedings of the Institution of Mechanical Engineers, Part D: Journal of Automobile Engineering
- Vol. 235 (14) , 3358-3374
Research on vehicle critical condition prediction and optimal yaw moment intervention based on nonlinear dynamics and Monte Carlo simulation
Timely and effective yaw moment intervention is required to suppress the instability tendency of vehicle under critical conditions, which is mainly caused by the overshoot of state parameters. As the development of vehicle nonlinear dynamics, the prediction of vehicle critical condition enables the vehicle to stabilize in this condition by timely yaw moment intervention. The yaw moment intervention law based on the prediction of critical conditions cannot be solely investigated by the initial motion states, since the online iterative optimization is an indispensable part in the predictive control. In this paper, the combination of threshold model, quadratic optimal yaw moment prediction method and Monte Carlo simulation provides a new approach to investigate the optimal open loop yaw moment intervention law based on initial motion states, which can be used to maintain the stability of vehicle plane motion in critical situations and optimize the predictive control method. Specifically, a total of 480,000 samples of quadratic yaw moment intervention parameters and corresponding system responses are obtained and analysed. It is certified that the optimized quadratic yaw moment can effectively suppress the overshoot of system responses. Specifically, statistics indicate that the initial value of yaw moment intervention plays an important role in preventing instability, but with the increase of speed and steering angle, the final yaw moment will be the decisive factor to maintain the lateral stability.