Data-Driven Motion Planning: A Survey on Deep Neural Networks, Reinforcement Learning, and Large Language Model Approaches

Motion planning is a fundamental challenge in robotics, involving the creation of trajectories from start to goal states while meeting constraints like collision avoidance and joint limits. Its complexity increases with the number of robot joints. Several traditional approaches tackle this problem,...

Full description

Saved in:
Bibliographic Details
Main Authors: Gabriel Peixoto de Carvalho, Tetsuya Sawanobori, Takato Horii
Format: Article
Language:English
Published: IEEE 2025-01-01
Series:IEEE Access
Subjects:
Online Access:https://ieeexplore.ieee.org/document/10930422/
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850046929694621696
author Gabriel Peixoto de Carvalho
Tetsuya Sawanobori
Takato Horii
author_facet Gabriel Peixoto de Carvalho
Tetsuya Sawanobori
Takato Horii
author_sort Gabriel Peixoto de Carvalho
collection DOAJ
description Motion planning is a fundamental challenge in robotics, involving the creation of trajectories from start to goal states while meeting constraints like collision avoidance and joint limits. Its complexity increases with the number of robot joints. Several traditional approaches tackle this problem, such as sampling motion planning, grid-based methods, potential fields, and optimization techniques. Recent advancements in deep neural networks, reinforcement learning, and large language models enable new possibilities for solving motion planning problems by improving sampling efficiency, optimizing control policies, and enabling task planning through natural language prompts. This survey comprehensively reviews these novel approaches, providing background knowledge, analyzing key contributions, and identifying common patterns, limitations, and research gaps. Our work is the first to integrate all three major data-driven approaches, discussing their applications and future research directions.
format Article
id doaj-art-201dbcbc0b2b4ebb89db743c69ec5e18
institution DOAJ
issn 2169-3536
language English
publishDate 2025-01-01
publisher IEEE
record_format Article
series IEEE Access
spelling doaj-art-201dbcbc0b2b4ebb89db743c69ec5e182025-08-20T02:54:22ZengIEEEIEEE Access2169-35362025-01-0113521955224510.1109/ACCESS.2025.355222510930422Data-Driven Motion Planning: A Survey on Deep Neural Networks, Reinforcement Learning, and Large Language Model ApproachesGabriel Peixoto de Carvalho0https://orcid.org/0000-0001-8770-573XTetsuya Sawanobori1Takato Horii2https://orcid.org/0000-0001-5374-0887Graduate School of Engineering Science, Osaka University, Osaka, JapanConnected Robotics Inc., Tokyo University of Agriculture and Technology Koganei Campus, Tokyo, JapanGraduate School of Engineering Science, Osaka University, Osaka, JapanMotion planning is a fundamental challenge in robotics, involving the creation of trajectories from start to goal states while meeting constraints like collision avoidance and joint limits. Its complexity increases with the number of robot joints. Several traditional approaches tackle this problem, such as sampling motion planning, grid-based methods, potential fields, and optimization techniques. Recent advancements in deep neural networks, reinforcement learning, and large language models enable new possibilities for solving motion planning problems by improving sampling efficiency, optimizing control policies, and enabling task planning through natural language prompts. This survey comprehensively reviews these novel approaches, providing background knowledge, analyzing key contributions, and identifying common patterns, limitations, and research gaps. Our work is the first to integrate all three major data-driven approaches, discussing their applications and future research directions.https://ieeexplore.ieee.org/document/10930422/Roboticsdeep learningsurveylarge language modelsneural networksreinforcement learning
spellingShingle Gabriel Peixoto de Carvalho
Tetsuya Sawanobori
Takato Horii
Data-Driven Motion Planning: A Survey on Deep Neural Networks, Reinforcement Learning, and Large Language Model Approaches
IEEE Access
Robotics
deep learning
survey
large language models
neural networks
reinforcement learning
title Data-Driven Motion Planning: A Survey on Deep Neural Networks, Reinforcement Learning, and Large Language Model Approaches
title_full Data-Driven Motion Planning: A Survey on Deep Neural Networks, Reinforcement Learning, and Large Language Model Approaches
title_fullStr Data-Driven Motion Planning: A Survey on Deep Neural Networks, Reinforcement Learning, and Large Language Model Approaches
title_full_unstemmed Data-Driven Motion Planning: A Survey on Deep Neural Networks, Reinforcement Learning, and Large Language Model Approaches
title_short Data-Driven Motion Planning: A Survey on Deep Neural Networks, Reinforcement Learning, and Large Language Model Approaches
title_sort data driven motion planning a survey on deep neural networks reinforcement learning and large language model approaches
topic Robotics
deep learning
survey
large language models
neural networks
reinforcement learning
url https://ieeexplore.ieee.org/document/10930422/
work_keys_str_mv AT gabrielpeixotodecarvalho datadrivenmotionplanningasurveyondeepneuralnetworksreinforcementlearningandlargelanguagemodelapproaches
AT tetsuyasawanobori datadrivenmotionplanningasurveyondeepneuralnetworksreinforcementlearningandlargelanguagemodelapproaches
AT takatohorii datadrivenmotionplanningasurveyondeepneuralnetworksreinforcementlearningandlargelanguagemodelapproaches