Network offloading policies for cloud robotics: a learning-based approach

Today’s robotic systems are increasingly turning to computationally expensive models such as deep neural networks (DNNs) for tasks like localization, perception, planning, and object detection. However, resource-constrained robots, like low-power drones, often have insufficient on-board compute reso...

Full description

Saved in:
Bibliographic Details
Published in:Autonomous robots Vol. 45; no. 7; pp. 997 - 1012
Main Authors: Chinchali, Sandeep, Sharma, Apoorva, Harrison, James, Elhafsi, Amine, Kang, Daniel, Pergament, Evgenya, Cidon, Eyal, Katti, Sachin, Pavone, Marco
Format: Journal Article
Language:English
Published: New York Springer US 01.10.2021
Springer Nature B.V
Subjects:
Accuracy
Artificial Intelligence
Artificial neural networks
Cloud computing
Communication
Computer Imaging
Control
Decision making
Deep learning
Engineering
Machine learning
Mechatronics
Multiple robots
Network latency
Neural networks
Object recognition
Pattern Recognition and Graphics
Robotics
Robotics and Automation
Robots
Special Issue on Robotics: Science and Systems 2019
Vision
Wireless networks
Robot perception
Multi-robot systems
Cloud robotics
Edge computing
ISSN:0929-5593, 1573-7527
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Today’s robotic systems are increasingly turning to computationally expensive models such as deep neural networks (DNNs) for tasks like localization, perception, planning, and object detection. However, resource-constrained robots, like low-power drones, often have insufficient on-board compute resources or power reserves to scalably run the most accurate, state-of-the art neural network compute models. Cloud robotics allows mobile robots the benefit of offloading compute to centralized servers if they are uncertain locally or want to run more accurate, compute-intensive models. However, cloud robotics comes with a key, often understated cost: communicating with the cloud over congested wireless networks may result in latency or loss of data. In fact, sending high data-rate video or LIDAR from multiple robots over congested networks can lead to prohibitive delay for real-time applications, which we measure experimentally. In this paper, we formulate a novel Robot Offloading Problem —how and when should robots offload sensing tasks, especially if they are uncertain, to improve accuracy while minimizing the cost of cloud communication? We formulate offloading as a sequential decision making problem for robots, and propose a solution using deep reinforcement learning. In both simulations and hardware experiments using state-of-the art vision DNNs, our offloading strategy improves vision task performance by between 1.3 and 2.3 × of benchmark offloading strategies, allowing robots the potential to significantly transcend their on-board sensing accuracy but with limited cost of cloud communication.
Bibliography:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
ISSN:0929-5593
1573-7527
DOI:10.1007/s10514-021-09987-4