Crowd-Aware Mobile Robot Navigation Based on Improved Decentralized Structured RNN via Deep Reinforcement Learning
Efficient navigation in a socially compliant manner is an important and challenging task for robots working in dynamic dense crowd environments. With the development of artificial intelligence, deep reinforcement learning techniques have been widely used in the robot navigation. Previous model-free...
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2023-02-01
|
| Series: | Sensors |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1424-8220/23/4/1810 |
| _version_ | 1797618323103416320 |
|---|---|
| author | Yulin Zhang Zhengyong Feng |
| author_facet | Yulin Zhang Zhengyong Feng |
| author_sort | Yulin Zhang |
| collection | DOAJ |
| description | Efficient navigation in a socially compliant manner is an important and challenging task for robots working in dynamic dense crowd environments. With the development of artificial intelligence, deep reinforcement learning techniques have been widely used in the robot navigation. Previous model-free reinforcement learning methods only considered the interactions between robot and humans, not the interactions between humans and humans. To improve this, we propose a decentralized structured RNN network with coarse-grained local maps (LM-SRNN). It is capable of modeling not only Robot–Human interactions through spatio-temporal graphs, but also Human–Human interactions through coarse-grained local maps. Our model captures current crowd interactions and also records past interactions, which enables robots to plan safer paths. Experimental results show that our model is able to navigate efficiently in dense crowd environments, outperforming state-of-the-art methods. |
| first_indexed | 2024-03-11T08:12:24Z |
| format | Article |
| id | doaj.art-f74cee9cecb0417f9540d1c526f318e9 |
| institution | Directory Open Access Journal |
| issn | 1424-8220 |
| language | English |
| last_indexed | 2024-03-11T08:12:24Z |
| publishDate | 2023-02-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Sensors |
| spelling | doaj.art-f74cee9cecb0417f9540d1c526f318e92023-11-16T23:06:27ZengMDPI AGSensors1424-82202023-02-01234181010.3390/s23041810Crowd-Aware Mobile Robot Navigation Based on Improved Decentralized Structured RNN via Deep Reinforcement LearningYulin Zhang0Zhengyong Feng1School of Electronic Information Engineering, China West Normal University, Nanchong 637009, ChinaSchool of Electronic Information Engineering, China West Normal University, Nanchong 637009, ChinaEfficient navigation in a socially compliant manner is an important and challenging task for robots working in dynamic dense crowd environments. With the development of artificial intelligence, deep reinforcement learning techniques have been widely used in the robot navigation. Previous model-free reinforcement learning methods only considered the interactions between robot and humans, not the interactions between humans and humans. To improve this, we propose a decentralized structured RNN network with coarse-grained local maps (LM-SRNN). It is capable of modeling not only Robot–Human interactions through spatio-temporal graphs, but also Human–Human interactions through coarse-grained local maps. Our model captures current crowd interactions and also records past interactions, which enables robots to plan safer paths. Experimental results show that our model is able to navigate efficiently in dense crowd environments, outperforming state-of-the-art methods.https://www.mdpi.com/1424-8220/23/4/1810robot navigationdeep reinforcement learningRNNspatio-temporal graphscoarse-grained local maps |
| spellingShingle | Yulin Zhang Zhengyong Feng Crowd-Aware Mobile Robot Navigation Based on Improved Decentralized Structured RNN via Deep Reinforcement Learning Sensors robot navigation deep reinforcement learning RNN spatio-temporal graphs coarse-grained local maps |
| title | Crowd-Aware Mobile Robot Navigation Based on Improved Decentralized Structured RNN via Deep Reinforcement Learning |
| title_full | Crowd-Aware Mobile Robot Navigation Based on Improved Decentralized Structured RNN via Deep Reinforcement Learning |
| title_fullStr | Crowd-Aware Mobile Robot Navigation Based on Improved Decentralized Structured RNN via Deep Reinforcement Learning |
| title_full_unstemmed | Crowd-Aware Mobile Robot Navigation Based on Improved Decentralized Structured RNN via Deep Reinforcement Learning |
| title_short | Crowd-Aware Mobile Robot Navigation Based on Improved Decentralized Structured RNN via Deep Reinforcement Learning |
| title_sort | crowd aware mobile robot navigation based on improved decentralized structured rnn via deep reinforcement learning |
| topic | robot navigation deep reinforcement learning RNN spatio-temporal graphs coarse-grained local maps |
| url | https://www.mdpi.com/1424-8220/23/4/1810 |
| work_keys_str_mv | AT yulinzhang crowdawaremobilerobotnavigationbasedonimproveddecentralizedstructuredrnnviadeepreinforcementlearning AT zhengyongfeng crowdawaremobilerobotnavigationbasedonimproveddecentralizedstructuredrnnviadeepreinforcementlearning |