Tiny Robot Learning: Challenges and Directions for Machine Learning in Resource-Constrained Robots

Sabrina M.  Neuman; Brian  Plancher; Bardienus P.  Duisterhof; Srivatsan  Krishnan; Colby  Banbury; Mark  Mazumder; Shvetank  Prakash; Jason  Jabbour; Aleksandra  Faust; Guido de Croon; Vijay Janapa  Reddi

doi:10.1109/AICAS54282.2022.9870000

Tiny Robot Learning: Challenges and Directions for Machine Learning in Resource-Constrained Robots

Sabrina M. Neuman, Brian Plancher, Bardienus P. Duisterhof, Srivatsan Krishnan, Colby Banbury, Mark Mazumder, Shvetank Prakash, Jason Jabbour, Aleksandra Faust, Guido de Croon, Vijay Janapa Reddi

Control & Simulation

Research output: Chapter in Book/Conference proceedings/Edited volume › Conference contribution › Scientific › peer-review

7 Citations (Scopus)

10 Downloads (Pure)

Abstract

Machine learning (ML) has become a pervasive tool across computing systems. An emerging application that stress-tests the challenges of ML system design is tiny robot learning, the deployment of ML on resource-constrained low-cost autonomous robots. Tiny robot learning lies at the intersection of embedded systems, robotics, and ML, compounding the challenges of these domains. Tiny robot learning is subject to challenges from size, weight, area, and power (SWAP) constraints; sensor, actuator, and compute hardware limitations; end-to-end system tradeoffs; and a large diversity of possible deployment scenarios. Tiny robot learning requires ML models to be designed with these challenges in mind, providing a crucible that reveals the necessity of holistic ML system design and automated end-to-end design tools for agile development. This paper gives a brief survey of the tiny robot learning space, elaborates on key challenges, and proposes promising opportunities for future work in ML system design.

Original language	English
Title of host publication	Proceedings of the 2022 IEEE 4th International Conference on Artificial Intelligence Circuits and Systems (AICAS)
Place of Publication	Danvers
Publisher	IEEE
Pages	296-299
Number of pages	4
ISBN (Electronic)	978-1-6654-0996-4
ISBN (Print)	978-1-6654-0997-1
DOIs	https://doi.org/10.1109/AICAS54282.2022.9870000
Publication status	Published - 2022
Event	2022 IEEE 4th International Conference on Artificial Intelligence Circuits and Systems - Incheon, Korea, Republic of Duration: 13 Jun 2022 → 15 Jun 2022 Conference number: 4th

Publication series

Name	Proceeding - IEEE International Conference on Artificial Intelligence Circuits and Systems, AICAS 2022

Conference

Conference	2022 IEEE 4th International Conference on Artificial Intelligence Circuits and Systems
Abbreviated title	AICAS 2022
Country/Territory	Korea, Republic of
City	Incheon
Period	13/06/22 → 15/06/22

Bibliographical note

Green Open Access added to TU Delft Institutional Repository ‘You share, we take care!’ – Taverne project https://www.openaccess.nl/en/you-share-we-take-care
Otherwise as indicated in the copyright section: the publisher is the copyright holder of this work and the author uses the Dutch legislation to make this work public.

Access to Document

10.1109/AICAS54282.2022.9870000

Tiny_Robot_Learning_Challenges_and_Directions_for_Machine_Learning_in_Resource_Constrained_RobotsFinal published version, 1.22 MB

Cite this

Neuman, S. M., Plancher, B., Duisterhof, B. P., Krishnan, S., Banbury, C., Mazumder, M., Prakash, S., Jabbour, J., Faust, A., de Croon, G., & Reddi, V. J. (2022). Tiny Robot Learning: Challenges and Directions for Machine Learning in Resource-Constrained Robots. In Proceedings of the 2022 IEEE 4th International Conference on Artificial Intelligence Circuits and Systems (AICAS) (pp. 296-299). Article 9870000 (Proceeding - IEEE International Conference on Artificial Intelligence Circuits and Systems, AICAS 2022). IEEE. https://doi.org/10.1109/AICAS54282.2022.9870000

Neuman, Sabrina M. ; Plancher, Brian ; Duisterhof, Bardienus P. et al. / Tiny Robot Learning : Challenges and Directions for Machine Learning in Resource-Constrained Robots. Proceedings of the 2022 IEEE 4th International Conference on Artificial Intelligence Circuits and Systems (AICAS). Danvers : IEEE, 2022. pp. 296-299 (Proceeding - IEEE International Conference on Artificial Intelligence Circuits and Systems, AICAS 2022).

@inproceedings{4557b01595f64ff7beee25493cf7c9e9,

title = "Tiny Robot Learning: Challenges and Directions for Machine Learning in Resource-Constrained Robots",

abstract = "Machine learning (ML) has become a pervasive tool across computing systems. An emerging application that stress-tests the challenges of ML system design is tiny robot learning, the deployment of ML on resource-constrained low-cost autonomous robots. Tiny robot learning lies at the intersection of embedded systems, robotics, and ML, compounding the challenges of these domains. Tiny robot learning is subject to challenges from size, weight, area, and power (SWAP) constraints; sensor, actuator, and compute hardware limitations; end-to-end system tradeoffs; and a large diversity of possible deployment scenarios. Tiny robot learning requires ML models to be designed with these challenges in mind, providing a crucible that reveals the necessity of holistic ML system design and automated end-to-end design tools for agile development. This paper gives a brief survey of the tiny robot learning space, elaborates on key challenges, and proposes promising opportunities for future work in ML system design.",

author = "Neuman, {Sabrina M.} and Brian Plancher and Duisterhof, {Bardienus P.} and Srivatsan Krishnan and Colby Banbury and Mark Mazumder and Shvetank Prakash and Jason Jabbour and Aleksandra Faust and {de Croon}, Guido and Reddi, {Vijay Janapa}",

note = "Green Open Access added to TU Delft Institutional Repository {\textquoteleft}You share, we take care!{\textquoteright} – Taverne project https://www.openaccess.nl/en/you-share-we-take-care Otherwise as indicated in the copyright section: the publisher is the copyright holder of this work and the author uses the Dutch legislation to make this work public. ; 2022 IEEE 4th International Conference on Artificial Intelligence Circuits and Systems , AICAS 2022 ; Conference date: 13-06-2022 Through 15-06-2022",

year = "2022",

doi = "10.1109/AICAS54282.2022.9870000",

language = "English",

isbn = "978-1-6654-0997-1",

series = "Proceeding - IEEE International Conference on Artificial Intelligence Circuits and Systems, AICAS 2022",

publisher = "IEEE",

pages = "296--299",

booktitle = "Proceedings of the 2022 IEEE 4th International Conference on Artificial Intelligence Circuits and Systems (AICAS)",

address = "United States",

}

Neuman, SM, Plancher, B, Duisterhof, BP, Krishnan, S, Banbury, C, Mazumder, M, Prakash, S, Jabbour, J, Faust, A, de Croon, G & Reddi, VJ 2022, Tiny Robot Learning: Challenges and Directions for Machine Learning in Resource-Constrained Robots. in Proceedings of the 2022 IEEE 4th International Conference on Artificial Intelligence Circuits and Systems (AICAS)., 9870000, Proceeding - IEEE International Conference on Artificial Intelligence Circuits and Systems, AICAS 2022, IEEE, Danvers, pp. 296-299, 2022 IEEE 4th International Conference on Artificial Intelligence Circuits and Systems , Incheon, Korea, Republic of, 13/06/22. https://doi.org/10.1109/AICAS54282.2022.9870000

Tiny Robot Learning: Challenges and Directions for Machine Learning in Resource-Constrained Robots. / Neuman, Sabrina M. ; Plancher, Brian ; Duisterhof, Bardienus P. et al.
Proceedings of the 2022 IEEE 4th International Conference on Artificial Intelligence Circuits and Systems (AICAS). Danvers: IEEE, 2022. p. 296-299 9870000 (Proceeding - IEEE International Conference on Artificial Intelligence Circuits and Systems, AICAS 2022).

Research output: Chapter in Book/Conference proceedings/Edited volume › Conference contribution › Scientific › peer-review

TY - GEN

T1 - Tiny Robot Learning

T2 - 2022 IEEE 4th International Conference on Artificial Intelligence Circuits and Systems

AU - Neuman, Sabrina M.

AU - Plancher, Brian

AU - Duisterhof, Bardienus P.

AU - Krishnan, Srivatsan

AU - Banbury, Colby

AU - Mazumder, Mark

AU - Prakash, Shvetank

AU - Jabbour, Jason

AU - Faust, Aleksandra

AU - de Croon, Guido

AU - Reddi, Vijay Janapa

N1 - Conference code: 4th

PY - 2022

Y1 - 2022

N2 - Machine learning (ML) has become a pervasive tool across computing systems. An emerging application that stress-tests the challenges of ML system design is tiny robot learning, the deployment of ML on resource-constrained low-cost autonomous robots. Tiny robot learning lies at the intersection of embedded systems, robotics, and ML, compounding the challenges of these domains. Tiny robot learning is subject to challenges from size, weight, area, and power (SWAP) constraints; sensor, actuator, and compute hardware limitations; end-to-end system tradeoffs; and a large diversity of possible deployment scenarios. Tiny robot learning requires ML models to be designed with these challenges in mind, providing a crucible that reveals the necessity of holistic ML system design and automated end-to-end design tools for agile development. This paper gives a brief survey of the tiny robot learning space, elaborates on key challenges, and proposes promising opportunities for future work in ML system design.

AB - Machine learning (ML) has become a pervasive tool across computing systems. An emerging application that stress-tests the challenges of ML system design is tiny robot learning, the deployment of ML on resource-constrained low-cost autonomous robots. Tiny robot learning lies at the intersection of embedded systems, robotics, and ML, compounding the challenges of these domains. Tiny robot learning is subject to challenges from size, weight, area, and power (SWAP) constraints; sensor, actuator, and compute hardware limitations; end-to-end system tradeoffs; and a large diversity of possible deployment scenarios. Tiny robot learning requires ML models to be designed with these challenges in mind, providing a crucible that reveals the necessity of holistic ML system design and automated end-to-end design tools for agile development. This paper gives a brief survey of the tiny robot learning space, elaborates on key challenges, and proposes promising opportunities for future work in ML system design.

UR - http://www.scopus.com/inward/record.url?scp=85139025976&partnerID=8YFLogxK

U2 - 10.1109/AICAS54282.2022.9870000

DO - 10.1109/AICAS54282.2022.9870000

M3 - Conference contribution

SN - 978-1-6654-0997-1

T3 - Proceeding - IEEE International Conference on Artificial Intelligence Circuits and Systems, AICAS 2022

SP - 296

EP - 299

BT - Proceedings of the 2022 IEEE 4th International Conference on Artificial Intelligence Circuits and Systems (AICAS)

PB - IEEE

CY - Danvers

Y2 - 13 June 2022 through 15 June 2022

ER -

Neuman SM, Plancher B, Duisterhof BP, Krishnan S, Banbury C, Mazumder M et al. Tiny Robot Learning: Challenges and Directions for Machine Learning in Resource-Constrained Robots. In Proceedings of the 2022 IEEE 4th International Conference on Artificial Intelligence Circuits and Systems (AICAS). Danvers: IEEE. 2022. p. 296-299. 9870000. (Proceeding - IEEE International Conference on Artificial Intelligence Circuits and Systems, AICAS 2022). doi: 10.1109/AICAS54282.2022.9870000

Tiny Robot Learning: Challenges and Directions for Machine Learning in Resource-Constrained Robots

Abstract

Publication series

Conference

Bibliographical note

Access to Document

Other files and links

Fingerprint

Cite this