Efficient Language-Guided Reinforcement Learning for Resource Constrained Autonomous Systems

Simple item page
dc.contributor.authorShiri, Aidin
dc.contributor.authorNavardi, Mozhgan
dc.contributor.authorManjunath, Tejaswini
dc.contributor.authorWaytowich, Nicholas R.
dc.contributor.authorMohsenin, Tinoosh
dc.date.accessioned2022-10-14T15:40:02Z
dc.date.available2022-10-14T15:40:02Z
dc.date.issued2022-09-23
dc.description.abstractIn this paper, we propose an energy-efficient architecture which is designed to receive both images and text inputs as a step towards designing reinforcement learning agents that can understand human language and act in real-world environments. We evaluate our proposed method on three different software environments and a low power drone named Crazyflie to navigate towards specified goals and avoid obstacles successfully. To find the most efficient language-guided RL model, we implemented the model with various configurations of image input sizes and text instruction sizes on the Crazyflie drone GAP8 which consists of 8 RISC-V cores. The task completion success rate and onboard power consumption, latency, and memory usage of GAP8 are measured and compared with Jetson TX2 ARM CPU and Raspberry Pi 4. The results show that by decreasing 20% of input image size we achieve up to 78% energy improvement while achieving an 82% task completion success rateen_US
dc.description.sponsorshipWe thank Bharat Prakash, Edward Humes and Prakhar Dixit at EEHPC lab for discussion and initial results. We also thank Dr. Vijay Reddi and his team at the Edge Computing Lab, Harvard University for their initial help with the Air-Learning environment. This project was sponsored by the U.S. Army Research Laboratory under Cooperative Agreement Number W911NF2120076.en_US
dc.description.urihttps://ieeexplore.ieee.org/document/9901456en_US
dc.format.extent9 pagesen_US
dc.genrejournal articlesen_US
dc.genrepostprintsen_US
dc.identifierdoi:10.13016/m2cdcw-ydhr
dc.identifier.citationA. Shiri, M. Navardi, T. Manjunath, N. R.Waytowich and T. Mohsenin, "Efficient Language-Guided Reinforcement Learning for Resource Constrained Autonomous Systems," in IEEE Micro, 2022, doi: 10.1109/MM.2022.3199686.en_US
dc.identifier.urihttps://doi.org/10.1109/MM.2022.3199686
dc.identifier.urihttp://hdl.handle.net/11603/26186
dc.language.isoen_USen_US
dc.publisherIEEEen_US
dc.relation.isAvailableAtThe University of Maryland, Baltimore County (UMBC)
dc.relation.ispartofUMBC Computer Science and Electrical Engineering Department Collection
dc.relation.ispartofUMBC Faculty Collection
dc.relation.ispartofUMBC Student Collection
dc.rightsThis work was written as part of one of the author's official duties as an Employee of the United States Government and is therefore a work of the United States Government. In accordance with 17 U.S.C. 105, no copyright protection is available for such works under U.S. Law.en_US
dc.rightsPublic Domain Mark 1.0*
dc.rights.urihttp://creativecommons.org/publicdomain/mark/1.0/*
dc.titleEfficient Language-Guided Reinforcement Learning for Resource Constrained Autonomous Systemsen_US
dc.typeTexten_US
dcterms.creatorhttps://orcid.org/0000-0001-5402-0988en_US
dcterms.creatorhttps://orcid.org/0000-0001-9690-5047en_US

Files

Original bundle
Now showing 1 - 1 of 1
Thumbnail Image
Name:
Efficient_Language-Guided_Reinforcement_Learning_for_Resource_Constrained_Autonomous_Systems.pdf
Size:
2.78 MB
Format:
Adobe Portable Document Format
Description:
Download
License bundle
Now showing 1 - 1 of 1
No Thumbnail Available
Name:
license.txt
Size:
2.56 KB
Format:
Item-specific license agreed upon to submission
Description:
Download

Collections

UMBC Computer Science and Electrical Engineering Department
UMBC Faculty Collection
UMBC Student Collection