Access the full text.
Sign up today, get DeepDyve free for 14 days.
Ben Kehoe, Akihiro Matsukawa, S. Candido, J. Kuffner, Ken Goldberg (2013)
Cloud-based robot grasping with the google object recognition engine2013 IEEE International Conference on Robotics and Automation
Aakanksha Chowdhery, M. Chiang (2018)
Model Predictive Compression for Drone Video Analytics2018 IEEE International Conference on Sensing, Communication and Networking (SECON Workshops)
Florian Schroff, Dmitry Kalenichenko, James Philbin (2015)
FaceNet: A unified embedding for face recognition and clustering2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)
Brandon Amos, Bartosz Ludwiczuk, M. Satyanarayanan (2016)
OpenFace: A general-purpose face recognition library with mobile applications
Javier Salmerón-García, P. Iñigo-Blasco, F. Díaz-del-Río, D. Cagigas-Muñiz (2015)
A Tradeoff Analysis of a Cloud-Based Robot Navigation Assistant Using Stereo Image ProcessingIEEE Transactions on Automation Science and Engineering, 12
Ashesh Jain, Debarghya Das, Jayesh Gupta, Ashutosh Saxena (2014)
PlanIt: A crowdsourcing approach for learning to plan paths from large scale preference feedback2015 IEEE International Conference on Robotics and Automation (ICRA)
Csaba Szepesvari (2010)
Algorithms for Reinforcement Learning
Mohanarajah Gajamohan, V. Usenko, Mayank Singh, R. D’Andrea, M. Waibel (2015)
Cloud-Based Collaborative 3D Mapping in Real-Time With Low-Cost RobotsIEEE Transactions on Automation Science and Engineering, 12
Niko Sünderhauf, O. Brock, W. Scheirer, R. Hadsell, D. Fox, J. Leitner, B. Upcroft, P. Abbeel, Wolfram Burgard, Michael Milford, Peter Corke (2018)
The limits and potentials of deep learning for roboticsThe International Journal of Robotics Research, 37
Mobilenetv2: The next generation of on-device computer vision networks
Martín Abadi, P. Barham, Jianmin Chen, Z. Chen, Andy Davis, J. Dean, M. Devin, S. Ghemawat, G. Irving, M. Isard, M. Kudlur, J. Levenberg, R. Monga, Sherry Moore, D. Murray, Benoit Steiner, P. Tucker, Vijay Vasudevan, P. Warden, M. Wicke, Yuan Yu, Xiaoqiang Zhang (2016)
TensorFlow: A system for large-scale machine learning
Volodymyr Mnih, K. Kavukcuoglu, David Silver, Alex Graves, Ioannis Antonoglou, Daan Wierstra, Martin Riedmiller (2013)
Playing Atari with Deep Reinforcement LearningArXiv, abs/1312.5602
Joshua Achiam, David Held, Aviv Tamar, P. Abbeel (2017)
Constrained Policy OptimizationArXiv, abs/1705.10528
R. Bajcsy (1988)
Active perceptionProc. IEEE, 76
The physics of why bigger drones can fly longer
(2019)
The new robot kickstarter by anki is powered by qualcomm
C. Blundell, Julien Cornebise, K. Kavukcuoglu, Daan Wierstra (2015)
Weight Uncertainty in Neural Network
Tiffany Chen, Lenin Ravindranath, Shuo Deng, P. Bahl, H. Balakrishnan (2015)
Glimpse: Continuous, Real-Time Object Recognition on Mobile DevicesProceedings of the 13th ACM Conference on Embedded Networked Sensor Systems
A. Tanwani, Raghav Anand, Joseph Gonzalez, Ken Goldberg (2020)
RILaaS: Robot Inference and Learning as a ServiceIEEE Robotics and Automation Letters, 5
Sandeep Chinchali, Eyal Cidon, Evgenya Pergament, Tianshu Chu, S. Katti (2018)
Neural Networks Meet Physical Networks: Distributed Inference Between Edge Devices and the CloudProceedings of the 17th ACM Workshop on Hot Topics in Networks
Recommended upload encoding settings
R. Bellman (1957)
A Markovian Decision ProcessIndiana University Mathematics Journal, 6
Nan Tian, Jinfa Chen, Shikui Ma, Robert Zhang, Bill Huang, Ken Goldberg, S. Sojoudi (2018)
A Fog Robotic System for Dynamic Visual Servoing2019 International Conference on Robotics and Automation (ICRA)
S. Hochreiter, J. Schmidhuber (1997)
Long Short-Term MemoryNeural Computation, 9
Akhlaqur Rahman, Jiong Jin, A. Cricenti, Ashfaqur Rahman, Dong Yuan (2016)
A Cloud Robotics Framework of Optimal Task Offloading for Smart City Applications2016 IEEE Global Communications Conference (GLOBECOM)
Haiyan Wu, L. Lou, Chih-Chung Chen, S. Hirche, K. Kühnlenz (2013)
Cloud-Based Networked Visual Servo ControlIEEE Transactions on Industrial Electronics, 60
Mohanarajah Gajamohan, D. Hunziker, R. D’Andrea, M. Waibel (2015)
Rapyuta: A Cloud Robotics PlatformIEEE Transactions on Automation Science and Engineering, 12
Mingxing Tan, Quoc Le (2019)
EfficientNet: Rethinking Model Scaling for Convolutional Neural NetworksArXiv, abs/1905.11946
(2017)
2017).Constrainedpolicy optimization. In International conferenceonmachine learning (pp. 22–31)
Song-Chen Han, William Shen, Zuozhen Liu (2016)
Deep Drone : Object Detection and Tracking for Smart Drones on Embedded System
Ben Kehoe, S. Patil, P. Abbeel, Ken Goldberg (2014)
Image Object Label 3 D CAD Model Candidate Grasps Google Object Recognition Engine Google Cloud Storage Select Feasible Grasp with Highest Success Probability Pose EstimationCamera Robots Cloud 3 D Sensor
L. Riazuelo, Javier Civera, J. Montiel (2014)
C2TAM: A Cloud framework for cooperative tracking and mappingRobotics Auton. Syst., 62
(2017)
Ros ate my network bandwidth! https://answers
Hongzi Mao, R. Netravali, Mohammad Alizadeh (2017)
Neural Adaptive Video Streaming with PensieveProceedings of the Conference of the ACM Special Interest Group on Data Communication
Daniel Kang, John Emmons, Firas Abuzaid, Peter Bailis, M. Zaharia (2017)
Optimizing Deep CNN-Based Queries over Video Streams at ScaleArXiv, abs/1703.02529
Starsky robotics unleashes its truly driverless truck in florida
N. NikhilK., M. Tech, T. Satheesha, C. Kishore (2014)
Cloud-Based Networked Visual Servo Control
James Harrison, Apoorva Sharma, M. Pavone (2018)
Meta-Learning Priors for Efficient Online Bayesian Regression
Shenglong Tang, Hehua Yan, Di Li, Shiyong Wang, A. Vasilakos (2016)
Cloud robotics: Current status and open issuesIEEE Access, 4
Y Kang, J Hauswald, C Gao, A Rovinski, T Mudge, J Mars, L Tang (2017)
Neurosurgeon: Collaborative intelligence between the cloud and mobile edgeACM SIGPLAN Notices, 52
Volodymyr Mnih, Adrià Badia, Mehdi Mirza, Alex Graves, T. Lillicrap, Tim Harley, David Silver, K. Kavukcuoglu (2016)
Asynchronous Methods for Deep Reinforcement Learning
Behrouz Forouzan (1999)
TCP/IP Protocol Suite
RS Sutton, AG Barto (1998)
Reinforcement learning: An introductionIEEE Transactions on Neural Networks, 9
(2013)
4g-lte-speeds-vs-your-home-network
Yinlam Chow, Ofir Nachum, Edgar Duéñez-Guzmán, M. Ghavamzadeh (2018)
A Lyapunov-based Approach to Safe Reinforcement Learning
Yiping Kang, Johann Hauswald, Cao Gao, A. Rovinski, T. Mudge, Jason Mars, Lingjia Tang (2017)
Neurosurgeon: Collaborative Intelligence Between the Cloud and Mobile EdgeProceedings of the Twenty-Second International Conference on Architectural Support for Programming Languages and Operating Systems
(2018)
Learn exactly how fast a wi-fi network can move
(2019)
Network offloading policies for cloud robotics: A learning-based approach
Chrisma Pakha, Aakanksha Chowdhery, Junchen Jiang (2018)
Reinventing Video Streaming for Distributed Vision Analytics
C. Blundell, Julien Cornebise, K. Kavukcuoglu, Daan Wierstra (2015)
Weight Uncertainty in Neural NetworksArXiv, abs/1505.05424
Ken Goldberg, Ben Kehoe (2013)
Cloud Robotics and Automation: A Survey of Related Work
Håkon Riiser, Paul Vigmostad, C. Griwodz, P. Halvorsen (2013)
Commute path bandwidth traces from 3G networks: analysis and applications
Tsung-Yi Lin, M. Maire, Serge Belongie, James Hays, P. Perona, Deva Ramanan, Piotr Dollár, C. Zitnick (2014)
Microsoft COCO: Common Objects in Context
J. Higuera, Anqi Xu, F. Shkurti, G. Dudek (2012)
Socially-Driven Collective Path Planning for Robot Missions2012 Ninth Conference on Computer and Robot Vision
E. Altman (1999)
Constrained Markov Decision Processes
A. Bozcuoğlu, Gayane Kazhoyan, Yuki Furuta, Simon Stelter, M. Beetz, K. Okada, M. Inaba (2018)
The Exchange of Knowledge Using Cloud RoboticsIEEE Robotics and Automation Letters, 3
J. Wan, Minglun Yi, Di Li, Chunhua Zhang, Shiyong Wang, Keliang Zhou (2016)
Mobile Services for Customization Manufacturing Systems: An Example of Industry 4.0IEEE Access, 4
J. Padhye, V. Firoiu, D. Towsley (1999)
A Stochastic Model of TCP Reno Congestion Avoidence and Control
Greg Brockman, Vicki Cheung, Ludwig Pettersson, Jonas Schneider, J. Schulman, Jie Tang, Wojciech Zaremba (2016)
OpenAI GymArXiv, abs/1606.01540
H. Kalva (2006)
The H.264 Video Coding StandardIEEE MultiMedia, 13
(2010)
Cloud-enabled robots
A. Tanwani, Nitesh Mor, J. Kubiatowicz, Joseph Gonzalez, Ken Goldberg (2019)
A Fog Robotics Approach to Deep Robot Learning: Application to Object Recognition and Grasp Planning in Surface Decluttering2019 International Conference on Robotics and Automation (ICRA)
Y. Gal, Riashat Islam, Zoubin Ghahramani (2017)
Deep Bayesian Active Learning with Image DataArXiv, abs/1703.02910
(2019)
Data is the new oil in the future of automated driving
Manoj Penmetcha, B. Min (2021)
A Deep Reinforcement Learning-Based Dynamic Computational Offloading Method for Cloud RoboticsIEEE Access, 9
C Szepesvári (2010)
Algorithms for reinforcement learningSynthesis Lectures on Artificial Intelligence and Machine Learning, 4
M. Alamir, Frank Allgöwer (2008)
Model Predictive ControlInternational Journal of Robust and Nonlinear Control, 18
M. Quigley (2009)
ROS: an open-source Robot Operating System
(2018)
Amazon alexa crashes after christmas day overload
Xiangyu Zhang, Xinyu Zhou, Mengxiao Lin, Jian Sun (2017)
ShuffleNet: An Extremely Efficient Convolutional Neural Network for Mobile Devices2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition
Lochan Verma, M. Fakharzadeh, Sunghyun Choi (2013)
Wifi on steroids: 802.11AC and 802.11ADIEEE Wireless Communications, 20
B Kehoe, S Patil, P Abbeel, K Goldberg (2015)
A survey of research on cloud robotics and automationIEEE Transactions on Automation Science and Engineering, 12
K. Sugiura, K. Zettsu (2015)
Rospeex: A cloud robotics platform for human-robot spoken dialogues2015 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)
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×\documentclass[12pt]{minimal}\usepackage{amsmath}\usepackage{wasysym}\usepackage{amsfonts}\usepackage{amssymb}\usepackage{amsbsy}\usepackage{mathrsfs}\usepackage{upgreek}\setlength{\oddsidemargin}{-69pt}\begin{document}$$\times $$\end{document} of benchmark offloading strategies, allowing robots the potential to significantly transcend their on-board sensing accuracy but with limited cost of cloud communication.
Autonomous Robots – Springer Journals
Published: Oct 1, 2021
Keywords: Cloud robotics; Edge computing; Multi-robot systems; Robot perception
Read and print from thousands of top scholarly journals.
Already have an account? Log in
Bookmark this article. You can see your Bookmarks on your DeepDyve Library.
To save an article, log in first, or sign up for a DeepDyve account if you don’t already have one.
Copy and paste the desired citation format or use the link below to download a file formatted for EndNote
Access the full text.
Sign up today, get DeepDyve free for 14 days.
All DeepDyve websites use cookies to improve your online experience. They were placed on your computer when you launched this website. You can change your cookie settings through your browser.