Trajectory Prediction
Trajectory prediction focuses on forecasting the future movement of objects, particularly crucial for autonomous systems like self-driving cars and robots. Current research emphasizes improving prediction accuracy and robustness, especially in complex, uncertain environments, using diverse model architectures such as transformers, graph neural networks, and diffusion models, often incorporating multimodal data (e.g., images, LiDAR, maps) and addressing challenges like uncertainty quantification and out-of-distribution generalization. This field is vital for enhancing the safety and efficiency of autonomous systems and has significant implications for various applications, including robotics, traffic management, and assistive technologies.
Papers
Learning Citywide Patterns of Life from Trajectory Monitoring
Mark Tenzer, Zeeshan Rasheed, Khurram Shafique
Multiclass-SGCN: Sparse Graph-based Trajectory Prediction with Agent Class Embedding
Ruochen Li, Stamos Katsigiannis, Hubert P. H. Shum
TENET: Transformer Encoding Network for Effective Temporal Flow on Motion Prediction
Yuting Wang, Hangning Zhou, Zhigang Zhang, Chen Feng, Huadong Lin, Chaofei Gao, Yizhi Tang, Zhenting Zhao, Shiyu Zhang, Jie Guo, Xuefeng Wang, Ziyao Xu, Chi Zhang
Holistic Transformer: A Joint Neural Network for Trajectory Prediction and Decision-Making of Autonomous Vehicles
Hongyu Hu, Qi Wang, Zhengguang Zhang, Zhengyi Li, Zhenhai Gao
Diverse Multiple Trajectory Prediction Using a Two-stage Prediction Network Trained with Lane Loss
Sanmin Kim, Hyeongseok Jeon, Junwon Choi, Dongsuk Kum