Shihao Li
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Shihao Li has a total of 26 co-authors. Here are the top co-authors by number of shared publications:
- Boyang Wang
Beijing Institute of Technology
4 shared publications - Haiou Liu
Beijing Institute of Technology
3 shared publications - Wenshuo Wang
Beijing Institute of Technology
2 shared publications - Chao Lu
Beijing Institute of Technology
1 shared publication - Chen Lv
School of Mechanical and Aerospace Engineering Nanyang Technological University Singapore Singapore
1 shared publication Gege Cui
1 shared publication
Latest Publications
- 12 September 2026
- Published by Springer Nature
- p. 228-244
Optimization-Guided Diffusion for Interactive Scene Generation
- 12 September 2026
- Published by Springer Nature
- p. 228-244
Optimization-Guided Diffusion for Interactive Scene Generation
- 18 May 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Intelligent Transportation Systems
- Vol. 27 (7) , 7549-7567
Optimization-Based Trajectory Planning With Behavior Cells for Autonomous Driving
Safe and executable trajectory planning in urban environments requires jointly considering traffic-related elements, ego behavior, and vehicle kinematics, posing challenges to the real-time performance and convergence of optimization-based methods. This paper proposes a behavior-guided optimization framework that structures the solution space at the spatiotemporal drivable domain level to facilitate fast and stable convergence. The planning space is partitioned into modular spatiotemporal domains, termed Behavior Cells (BCs), which encode ego motion feasibility and traffic-induced decisions. Feasible high-level behaviors are systematically enumerated through structured BC combinations and evaluated via a finite-horizon Markov decision process. The selected BC combination defines a continuous, behavior-consistent solution space, within which a dynamic two-stage optimization progressively restores the full planning formulation, enabling efficient and robust trajectory generation. Extensive simulations across diverse traffic scenarios demonstrate consistent reliability and real-time performance under varying traffic densities. On-road experiments further validate effectiveness in real-world urban environments. More detailed results are available at: https://lshasd123.github.io/Behavior-Cells/
- 18 May 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Intelligent Transportation Systems
- Vol. 27 (7) , 7549-7567
Optimization-Based Trajectory Planning With Behavior Cells for Autonomous Driving
Safe and executable trajectory planning in urban environments requires jointly considering traffic-related elements, ego behavior, and vehicle kinematics, posing challenges to the real-time performance and convergence of optimization-based methods. This paper proposes a behavior-guided optimization framework that structures the solution space at the spatiotemporal drivable domain level to facilitate fast and stable convergence. The planning space is partitioned into modular spatiotemporal domains, termed Behavior Cells (BCs), which encode ego motion feasibility and traffic-induced decisions. Feasible high-level behaviors are systematically enumerated through structured BC combinations and evaluated via a finite-horizon Markov decision process. The selected BC combination defines a continuous, behavior-consistent solution space, within which a dynamic two-stage optimization progressively restores the full planning formulation, enabling efficient and robust trajectory generation. Extensive simulations across diverse traffic scenarios demonstrate consistent reliability and real-time performance under varying traffic densities. On-road experiments further validate effectiveness in real-world urban environments. More detailed results are available at: https://lshasd123.github.io/Behavior-Cells/
- Open Access
DiffPlace: Street View Generation via Place-Controllable Diffusion Model Enhancing Place Recognition
Generative models have advanced significantly in realistic image synthesis, with diffusion models excelling in quality and stability. Recent multi-view diffusion models improve 3D-aware street view generation, but they struggle to produce place-aware and background-consistent urban scenes from text, BEV maps, and object bounding boxes. This limits their effectiveness in generating realistic samples for place recognition tasks. To address these challenges, we propose DiffPlace, a novel framework that introduces a place-ID controller to enable place-controllable multi-view image generation. The place-ID controller employs linear projection, perceiver transformer, and contrastive learning to map place-ID embeddings into a fixed CLIP space, allowing the model to synthesize images with consistent background buildings while flexibly modifying foreground objects and weather conditions. Extensive experiments, including quantitative comparisons and augmented training evaluations, demonstrate that DiffPlace outperforms existing methods in both generation quality and training support for visual place recognition. Our results highlight the potential of generative models in enhancing scene-level and place-aware synthesis, providing a valuable approach for improving place recognition in autonomous driving
Open AccessDiffPlace: Street View Generation via Place-Controllable Diffusion Model Enhancing Place Recognition
Generative models have advanced significantly in realistic image synthesis, with diffusion models excelling in quality and stability. Recent multi-view diffusion models improve 3D-aware street view generation, but they struggle to produce place-aware and background-consistent urban scenes from text, BEV maps, and object bounding boxes. This limits their effectiveness in generating realistic samples for place recognition tasks. To address these challenges, we propose DiffPlace, a novel framework that introduces a place-ID controller to enable place-controllable multi-view image generation. The place-ID controller employs linear projection, perceiver transformer, and contrastive learning to map place-ID embeddings into a fixed CLIP space, allowing the model to synthesize images with consistent background buildings while flexibly modifying foreground objects and weather conditions. Extensive experiments, including quantitative comparisons and augmented training evaluations, demonstrate that DiffPlace outperforms existing methods in both generation quality and training support for visual place recognition. Our results highlight the potential of generative models in enhancing scene-level and place-aware synthesis, providing a valuable approach for improving place recognition in autonomous driving
- 27 June 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Vehicular Technology
- Vol. 73 (11) , 16238-16253
Hierarchical Trajectory Planning Based on Adaptive Motion Primitives and Bilevel Corridor
This paper presents an efficient and risk-aware search-optimization hierarchical trajectory planning method for automated vehicles in different road structures. The proposed approach incorporates a time-series motion risk field, capturing diverse road structures through a spatiotemporal map. Then, an adaptive motion primitive is developed, dynamically adjusting action time windows based on evolving risk and expected deviation during the search process. This enables efficient and accurate initial trajectory generation. Additionally, a bilevel corridor is introduced to extract the drivable area and re-represent the risk field, enabling trajectory smoothing to consider motion risk without resorting to non-convex optimization methods. Simulation results in structured and unstructured scenarios demonstrate that the proposed method improves efficiency, flexibility, and optimization quality compared to fixed-step search and single-level corridor-based optimization approaches. Real-world experiments on autonomous vehicles validated the dynamic characteristics and effectiveness of the proposed method in the actual environment.
- 27 June 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Vehicular Technology
- Vol. 73 (11) , 16238-16253
Hierarchical Trajectory Planning Based on Adaptive Motion Primitives and Bilevel Corridor
This paper presents an efficient and risk-aware search-optimization hierarchical trajectory planning method for automated vehicles in different road structures. The proposed approach incorporates a time-series motion risk field, capturing diverse road structures through a spatiotemporal map. Then, an adaptive motion primitive is developed, dynamically adjusting action time windows based on evolving risk and expected deviation during the search process. This enables efficient and accurate initial trajectory generation. Additionally, a bilevel corridor is introduced to extract the drivable area and re-represent the risk field, enabling trajectory smoothing to consider motion risk without resorting to non-convex optimization methods. Simulation results in structured and unstructured scenarios demonstrate that the proposed method improves efficiency, flexibility, and optimization quality compared to fixed-step search and single-level corridor-based optimization approaches. Real-world experiments on autonomous vehicles validated the dynamic characteristics and effectiveness of the proposed method in the actual environment.
- Open Access
- 20 February 2023
- Published by Elsevier in Green Energy and Intelligent Transportation
- Vol. 2 (2)
A non-uniform quadtree map building method including dead-end semantics extraction
- 20 February 2023
- Published by Elsevier in Green Energy and Intelligent Transportation
- Vol. 2 (2)
Open AccessA non-uniform quadtree map building method including dead-end semantics extraction