Real-Time Mobile Robot Perception Based on Deep Learning Detection Model
Апстракт
The recent advances in deep learning models have enabled the robotics community to utilize their potential. The mobile robot domain on which deep learning has the most influence is scene understanding. Scene understanding enables mobile robots to exist and execute their tasks through processes such as object detection, semantic segmentation, or instance segmentation. A perception system that can recognize and locate objects in the scene is of the highest importance for achieving autonomous behavior of robotic systems. Having that in mind, we develop the mobile robot perception system based on deep learning. More precisely, we utilize an accurate and fast Convolution Neural Network (CNN) model to enable a mobile robot to detect objects in its scene in a real-time manner. The integration of two CNN models (SSD and MobileNet) is performed and implemented on mobile robot RAICO (Robot with Artificial Intelligence based COgnition). The experimental results show that the proposed perception s...ystem enables a high degree of object recognition with satisfying inference speed, even with limited processing power provided by Nvidia Jetson Nano integrated within RACIO.
Кључне речи:
Perception system / Object detection / Mobile robots / Convolutional neural networksИзвор:
Lecture Notes in Networks and Systems, 2022, 472, 670-677Издавач:
- Springer Science and Business Media Deutschland GmbH
Финансирање / пројекти:
- Министарство науке, технолошког развоја и иновација Републике Србије, институционално финансирање - 200105 (Универзитет у Београду, Машински факултет) (RS-MESTD-inst-2020-200105)
- MISSION4.0 - Deep Machine Learning and Swarm Intelligence-Based Optimization Algorithms for Control and Scheduling of Cyber-Physical Systems in Industry 4.0 (RS-ScienceFundRS-AI-6523109)
Колекције
Институција/група
Mašinski fakultetTY - CONF AU - Jokić, Aleksandar AU - Petrović, Milica AU - Miljković, Zoran PY - 2022 UR - https://machinery.mas.bg.ac.rs/handle/123456789/3815 AB - The recent advances in deep learning models have enabled the robotics community to utilize their potential. The mobile robot domain on which deep learning has the most influence is scene understanding. Scene understanding enables mobile robots to exist and execute their tasks through processes such as object detection, semantic segmentation, or instance segmentation. A perception system that can recognize and locate objects in the scene is of the highest importance for achieving autonomous behavior of robotic systems. Having that in mind, we develop the mobile robot perception system based on deep learning. More precisely, we utilize an accurate and fast Convolution Neural Network (CNN) model to enable a mobile robot to detect objects in its scene in a real-time manner. The integration of two CNN models (SSD and MobileNet) is performed and implemented on mobile robot RAICO (Robot with Artificial Intelligence based COgnition). The experimental results show that the proposed perception system enables a high degree of object recognition with satisfying inference speed, even with limited processing power provided by Nvidia Jetson Nano integrated within RACIO. PB - Springer Science and Business Media Deutschland GmbH C3 - Lecture Notes in Networks and Systems T1 - Real-Time Mobile Robot Perception Based on Deep Learning Detection Model EP - 677 SP - 670 VL - 472 DO - 10.1007/978-3-031-05230-9_80 ER -
@conference{ author = "Jokić, Aleksandar and Petrović, Milica and Miljković, Zoran", year = "2022", abstract = "The recent advances in deep learning models have enabled the robotics community to utilize their potential. The mobile robot domain on which deep learning has the most influence is scene understanding. Scene understanding enables mobile robots to exist and execute their tasks through processes such as object detection, semantic segmentation, or instance segmentation. A perception system that can recognize and locate objects in the scene is of the highest importance for achieving autonomous behavior of robotic systems. Having that in mind, we develop the mobile robot perception system based on deep learning. More precisely, we utilize an accurate and fast Convolution Neural Network (CNN) model to enable a mobile robot to detect objects in its scene in a real-time manner. The integration of two CNN models (SSD and MobileNet) is performed and implemented on mobile robot RAICO (Robot with Artificial Intelligence based COgnition). The experimental results show that the proposed perception system enables a high degree of object recognition with satisfying inference speed, even with limited processing power provided by Nvidia Jetson Nano integrated within RACIO.", publisher = "Springer Science and Business Media Deutschland GmbH", journal = "Lecture Notes in Networks and Systems", title = "Real-Time Mobile Robot Perception Based on Deep Learning Detection Model", pages = "677-670", volume = "472", doi = "10.1007/978-3-031-05230-9_80" }
Jokić, A., Petrović, M.,& Miljković, Z.. (2022). Real-Time Mobile Robot Perception Based on Deep Learning Detection Model. in Lecture Notes in Networks and Systems Springer Science and Business Media Deutschland GmbH., 472, 670-677. https://doi.org/10.1007/978-3-031-05230-9_80
Jokić A, Petrović M, Miljković Z. Real-Time Mobile Robot Perception Based on Deep Learning Detection Model. in Lecture Notes in Networks and Systems. 2022;472:670-677. doi:10.1007/978-3-031-05230-9_80 .
Jokić, Aleksandar, Petrović, Milica, Miljković, Zoran, "Real-Time Mobile Robot Perception Based on Deep Learning Detection Model" in Lecture Notes in Networks and Systems, 472 (2022):670-677, https://doi.org/10.1007/978-3-031-05230-9_80 . .