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

TL;DR

This paper presents a pipeline for deploying advanced imitation learning models, like transformers, on affordable embedded platforms by combining model compression and a novel asynchronous parallel method to improve efficiency and smoothness.

Contribution

It introduces a new deployment pipeline that includes an efficient model compression technique and the TEDA asynchronous parallel method for better edge device performance.

Findings

Successful deployment of large-scale models on embedded devices

Enhanced operational smoothness with TEDA

Effective model compression enabling edge deployment

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.