Application of Reinforcement Learning in Open Space Planner for Apollo Auto

Ivanov D., Panov A.I.
Тип документаBook Chapter
Дата публикации2022-01-01
Название журналаLecture Notes in Networks and Systems
ИздательSpringer Nature
КвартильQ4
ISSN23673370, 23673389
Краткое описание
Local planner makes a trajectory physically executable for an agent. Open Space Planner of Apollo framework based on nonlinear optimization methods smooths the trajectory received from a global planner. Such dependency on a global planner forces an agent to relaunch both planners when local changes occur (e.g., when an environment has dynamic obstacles), what can waste too much time. In this article, we consider a different approach which is based on reinforcement learning. This method allows agent generate a trajectory using information about environment (the current and goal state, lidar sensors, etc.). Experiments conducted on the simplified environment show that such algorithm can be implemented as the local planner in Apollo infrastructure.
Пристатейные ссылки: 13
Цитируется в публикациях: 1
Learning Embodied Agents with Policy Gradients to Navigate in Realistic Environments
Staroverov A., Vetlin V., Makarenko S., Naumov A., Panov A.I.
Q4 Studies in Computational Intelligence 2021 цитирований: 1
Real-Time Object Navigation With Deep Neural Networks and Hierarchical Reinforcement Learning
Staroverov A., Yudin D.A., Belkin I., Adeshkin V., Solomentsev Y.K., Panov A.I.
Q1 IEEE Access 2020 цитирований: 11
Open Access
Open access
Q-Learning of Spatial Actions for Hierarchical Planner of Cognitive Agents
Kiselev G., Panov A.
Q3 Lecture Notes in Computer Science 2020 цитирований: 2
Open Access
Open access
Hierarchical actor-critic with hindsight for mobile robot with continuous state space
Aleksey S., Panov A.I.
Q4 Studies in Computational Intelligence 2020 цитирований: 1
RL-RRT: Kinodynamic Motion Planning via Learning Reachability Estimators From RL Policies
Chiang H.L., Hsu J., Fiser M., Tapia L., Faust A.
2019 цитирований: 22
Robotics, Vision and Control
Corke P.
Q2 Springer Tracts in Advanced Robotics 2011 цитирований: 475
Probabilistic roadmaps for path planning in high-dimensional configuration spaces
Kavraki L.E., Svestka P., Latombe J.-., Overmars M.H.
IEEE Transactions on Robotics and Automation 1996 цитирований: 3015
Метрики
Поделиться
Цитировать
ГОСТ |
Цитировать
1. Ivanov D., Panov A.I. Application of Reinforcement Learning in Open Space Planner for Apollo Auto // Proceedings of the Fifth International Scientific Conference “Intelligent Information Technologies for Industry” (IITI’21). 2021. С. 35–43.
RIS |
Цитировать

TY - GENERIC

DO - 10.1007/978-3-030-87178-9_4

UR - http://dx.doi.org/10.1007/978-3-030-87178-9_4

TI - Application of Reinforcement Learning in Open Space Planner for Apollo Auto

T2 - Lecture Notes in Networks and Systems

AU - Ivanov, Dmitriy

AU - Panov, Aleksandr I.

PY - 2021

DA - 2021/09/16

PB - Springer International Publishing

SP - 35-43

SN - 2367-3370

SN - 2367-3389

ER -

BibTex |
Цитировать

@incollection{Ivanov_2021,

doi = {10.1007/978-3-030-87178-9_4},

url = {https://doi.org/10.1007%2F978-3-030-87178-9_4},

year = 2021,

month = {sep},

publisher = {Springer International Publishing},

pages = {35--43},

author = {Dmitriy Ivanov and Aleksandr I. Panov},

title = {Application of Reinforcement Learning in Open Space Planner for Apollo Auto},

booktitle = {Lecture Notes in Networks and Systems}

}

MLA
Цитировать
Ivanov, Dmitriy, and Aleksandr I. Panov. “Application of Reinforcement Learning in Open Space Planner for Apollo Auto.” Proceedings of the Fifth International Scientific Conference “Intelligent Information Technologies for Industry” (IITI’21) (2021): 35–43. Crossref. Web.