Integrating Historical Learning and Multi-View Attention with Hierarchical Feature Fusion for Robotic Manipulation
Biomimetics · 20.11.2024 · 9 (11) · 712
DOI: 10.3390/biomimetics9110712 ↗Kurz gefasst
Fachartikel in der Zeitschrift Biomimetics, online erschienen am 20.11.2024. Verfasst von Gaoxiong Lu und 3 weiteren Autor:innen. Beteiligte Einrichtung: The Academy for Engineering and Technology, Fudan University, Shanghai 200433, China. Die Arbeit wurde bisher 3-mal zitiert (Crossref) und nennt 44 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Guangxi Key Laboratory of Brain-inspired Computing and Intelligent Chips, Shanghai Municipal Science and Technology Major Project, China.
Abstract (Originalsprache)
Humans typically make decisions based on past experiences and observations, while in the field of robotic manipulation, the robot’s action prediction often relies solely on current observations, which tends to make robots overlook environmental changes or become ineffective when current observations are suboptimal. To address this pivotal challenge in robotics, inspired by human cognitive processes, we propose our method which integrates historical learning and multi-view attention to improve the performance of robotic manipulation. Based on a spatio-temporal attention mechanism, our method not only combines observations from current and past steps but also integrates historical actions to better perceive changes in robots’ behaviours and their impacts on the environment. We also employ a mutual information-based multi-view attention module to automatically focus on valuable perspectives, thereby incorporating more effective information for decision-making. Furthermore, inspired by human visual system which processes both global context and local texture details, we have devised a method that merges semantic and texture features, aiding robots in understanding the task and enhancing their capability to handle fine-grained tasks. Extensive experiments in RLBench and real-world scenarios demonstrate that our method effectively handles various tasks and exhibits notable robustness and adaptability.
Schlagwörter
Stichwörter der Autor:innen
Autor:innen und Institutionen
- The Academy for Engineering and Technology, Fudan University, Shanghai 200433, China.
Förderung
- Guangxi Key Laboratory of Brain-inspired Computing and Intelligent Chips
- Shanghai Municipal Science and Technology Major Project, China
Zitieren
APA
Lu, G., Yan, Z., Luo, J., & Li, W. (2024). Integrating Historical Learning and Multi-View Attention with Hierarchical Feature Fusion for Robotic Manipulation. Biomimetics, 9(11), 712. https://doi.org/10.3390/biomimetics9110712
Vancouver
Lu G, Yan Z, Luo J, Li W. Integrating Historical Learning and Multi-View Attention with Hierarchical Feature Fusion for Robotic Manipulation. Biomimetics. 2024;9(11):712. doi:10.3390/biomimetics9110712
BibTeX
@article{Lu2024,
author = {Lu, Gaoxiong and Yan, Zeyu and Luo, Jianing and Li, Wei},
title = {Integrating Historical Learning and Multi-View Attention with Hierarchical Feature Fusion for Robotic Manipulation},
journal = {Biomimetics},
year = {2024},
volume = {9},
number = {11},
pages = {712},
doi = {10.3390/biomimetics9110712}
}
EUVIMED