Bridging the Resource Gap: Deploying Advanced Imitation Learning Models Onto Affordable Embedded Platforms

Advanced imitation learning with structures like the transformer is increasingly demonstrating its advantages in robotics. However, deploying these large-scale models on embedded platforms remains a major challenge. In this paper, we propose a pipeline that facilitates the migration of advanced imitation learning algorithms to edge devices. The process is achieved via an efficient model compression method and a practical asynchronous parallel method Temporal Ensemble with Dropped Actions (TEDA) that enhances the smoothness of operations. To show the efficiency of the proposed pipeline, large-scale imitation learning models are trained on a server and deployed on an edge device to complete various manipulation tasks.

Authors

Institutions

Publication Details

Published
2024-12-10
DOI
https://doi.org/10.1109/robio64047.2024.10907641
Primary Topic
Reinforcement Learning in Robotics
Type
article
Field-Weighted Citation Impact
0.00
Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
article

Bridging the Resource Gap: Deploying Advanced Imitation Learning Models Onto Affordable Embedded Platforms

Rui Deng, Zhuoyi Pang, Yuhang Dong, Genqing Zhou et al.
Reinforcement Learning in Robotics
article

Bridging the Resource Gap: Deploying Advanced Imitation Learning Models Onto Affordable Embedded Platforms

Rui Deng, Zhuoyi Pang, Yuhang Dong, Genqing Zhou, Hongrui Zhu, Huiyao Ge, Jian Zhang, Zhi Ping Xu, Ruixiang Wang, Shi Lu
article en

Abstract

Advanced imitation learning with structures like the transformer is increasingly demonstrating its advantages in robotics. However, deploying these large-scale models on embedded platforms remains a major challenge. In this paper, we propose a pipeline that facilitates the migration of advanced imitation learning algorithms to edge devices. The process is achieved via an efficient model compression method and a practical asynchronous parallel method Temporal Ensemble with Dropped Actions (TEDA) that enhances the smoothness of operations. To show the efficiency of the proposed pipeline, large-scale imitation learning models are trained on a server and deployed on an edge device to complete various manipulation tasks.

Jiangnan University (CN), Tongji University (CN), Harbin Institute of Technology (CN), California University of Pennsylvania (US), Zhejiang University (CN), Tsinghua University (CN)
Openalex Percentile: Top 74%
Reinforcement Learning in Robotics
DOISourceOpenAlex
AI Navigator

Ask Laika to Summarize, Analyze, and Connect papers live on the map.

Summarize Papers & Methodologies

Extract key findings, datasets, and comparative methods across publications.

Benchmark Rankings & Visual Analytics

Rank top research institutions, authors, funders, topics, and journals by Field-Weighted Citation Impact (FWCI) and paper volume with instant charts.

Connect Distant Disciplines

Bridge topological clusters on the map to find hidden collaborative intersections.

Bridging the Resource Gap: Deploying Advanced Imitation Learning Models Onto Affordable Embedded Platforms — Rui Deng, Zhuoyi Pang, et al. · (2024) | TGRS Research Map | TGRS