Interaction-aware trajectory prediction and planning for autonomous vehicles in forced merge scenarios
Merging is, in general, a challenging task for both human drivers and autonomous vehicles,
especially in dense traffic, because the merging vehicle typically needs to interact with other …
especially in dense traffic, because the merging vehicle typically needs to interact with other …
Dtpp: Differentiable joint conditional prediction and cost evaluation for tree policy planning in autonomous driving
Motion prediction and cost evaluation are vital components in the decision-making system of
autonomous vehicles. However, existing methods often ignore the importance of cost …
autonomous vehicles. However, existing methods often ignore the importance of cost …
AdaBoost maximum entropy deep inverse reinforcement learning with truncated gradient
L Song, D Li, X Wang, X Xu - Information Sciences, 2022 - Elsevier
Studying the representational capacity of neural networks to learn nonlinear rewards is
necessary in a complex and nonlinear environment. Over recent years, the maximum …
necessary in a complex and nonlinear environment. Over recent years, the maximum …
Risk-aware lane-change trajectory planning with rollover prevention for autonomous light trucks on curved roads
H Zhan, G Wang, X Shan, Y Liu - Mechanical Systems and Signal …, 2024 - Elsevier
Lane-change trajectory planning of autonomous light trucks is closely related to safety,
driving stability and transportation efficiency, especially in complex road and traffic …
driving stability and transportation efficiency, especially in complex road and traffic …
Ab-mapper: Attention and bicnet based multi-agent path planning for dynamic environment
Multi-agent path finding in dynamic environments is of great academic and practical value
for multi-robot systems in the real world. To improve the effectiveness and efficiency of the …
for multi-robot systems in the real world. To improve the effectiveness and efficiency of the …
How to not drive: Learning driving constraints from demonstration
K Rezaee, P Yadmellat - 2022 IEEE Intelligent Vehicles …, 2022 - ieeexplore.ieee.org
We propose a new scheme to learn motion planning constraints from human driving
trajectories. Behavioral and motion planning are the key components in an autonomous …
trajectories. Behavioral and motion planning are the key components in an autonomous …
Calibration of human driving behavior and preference using vehicle trajectory data
In a recent work (Dai et al., 2021) we proposed a multi-agent computational framework in
which each agent's driving policy at micro-level is derived by maximizing its own utility …
which each agent's driving policy at micro-level is derived by maximizing its own utility …
Pixel State Value Network for Combined Prediction and Planning in Interactive Environments
S Rosbach, SM Leupold, S Großjohann… - arXiv preprint arXiv …, 2023 - arxiv.org
Automated vehicles operating in urban environments have to reliably interact with other
traffic participants. Planning algorithms often utilize separate prediction modules forecasting …
traffic participants. Planning algorithms often utilize separate prediction modules forecasting …
逆强化学习算法, 理论与应用研究综述
宋莉， 李大字， 徐昕 - 自动化学报, 2023 - aas.net.cn
随着深度强化学习的研究与发展, 强化学习在博弈与优化决策, 智能驾驶等现实问题中的应用也
取得显著进展. 然而强化学习在智能体与环境的交互中存在人工设计奖励函数难的问题 …
取得显著进展. 然而强化学习在智能体与环境的交互中存在人工设计奖励函数难的问题 …
AB-Mapper: Attention and BicNet Based Multi-agent Path Finding for Dynamic Crowded Environment
Multi-agent path finding in dynamic crowded environments is of great academic and
practical value for multi-robot systems in the real world. To improve the effectiveness and …
practical value for multi-robot systems in the real world. To improve the effectiveness and …