Rethinking integration of prediction and planning in deep learning-based automated driving systems: a review

S Hagedorn, M Hallgarten, M Stoll… - arXiv preprint arXiv …, 2023 - arxiv.org
Automated driving has the potential to revolutionize personal, public, and freight mobility.
Besides the enormous challenge of perception, ie accurately perceiving the environment …

Uncovering the missing pattern: Unified framework towards trajectory imputation and prediction

Y Xu, A Bazarjani, H Chi, C Choi… - Proceedings of the IEEE …, 2023 - openaccess.thecvf.com
Trajectory prediction is a crucial undertaking in understanding entity movement or human
behavior from observed sequences. However, current methods often assume that the …

The Integration of Prediction and Planning in Deep Learning Automated Driving Systems: A Review

S Hagedorn, M Hallgarten, M Stoll… - IEEE Transactions on …, 2024 - ieeexplore.ieee.org
Automated driving has the potential to revolutionize personal, public, and freight mobility.
Beside accurately perceiving the environment, automated vehicles must plan a safe …

Adapting to length shift: Flexilength network for trajectory prediction

Y Xu, Y Fu - Proceedings of the IEEE/CVF Conference on …, 2024 - openaccess.thecvf.com
Trajectory prediction plays an important role in various applications including autonomous
driving robotics and scene understanding. Existing approaches mainly focus on developing …

On a Connection between Differential Games, Optimal Control, and Energy-based Models for Multi-Agent Interactions

C Diehl, T Klosek, M Krüger, N Murzyn… - arXiv preprint arXiv …, 2023 - arxiv.org
Game theory offers an interpretable mathematical framework for modeling multi-agent
interactions. However, its applicability in real-world robotics applications is hindered by …

MixCycle: Mixup Assisted Semi-Supervised 3D Single Object Tracking with Cycle Consistency

Q Wu, J Yang, K Sun, C Zhang… - Proceedings of the …, 2023 - openaccess.thecvf.com
Abstract 3D single object tracking (SOT) is an indispensable part of automated driving.
Existing approaches rely heavily on large, densely labeled datasets. However, annotating …

Do large language models pay similar attention like human programmers when generating code?

B Kou, S Chen, Z Wang, L Ma, T Zhang - Proceedings of the ACM on …, 2024 - dl.acm.org
Large Language Models (LLMs) have recently been widely used for code generation. Due
to the complexity and opacity of LLMs, little is known about how these models generate …

Deciphering Movement: Unified Trajectory Generation Model for Multi-Agent

Y Xu, Y Fu - arXiv preprint arXiv:2405.17680, 2024 - arxiv.org
Understanding multi-agent behavior is critical across various fields. The conventional
approach involves analyzing agent movements through three primary tasks: trajectory …

MixFormer: A Self-Attentive Convolutional Network for 3D Mesh Object Recognition

L Huang, J Zhao, Y Chen - Algorithms, 2023 - mdpi.com
3D mesh as a complex data structure can provide effective shape representation for 3D
objects, but due to the irregularity and disorder of the mesh data, it is difficult for …

Nonlinear modeling between steering wheel angle and front wheel angle for unmanned vehicle

K Liu, Y Zeng, M Zhu, Q Yang, L Tao… - 2023 China Automation …, 2023 - ieeexplore.ieee.org
Unmanned vehicles have attracted notable attention in recent years. Trajectory control is
one of the core problems of unmanned vehicles. It is meaningful to establish a precise …