On-the-Fly Knowledge Acquisition for Automated Planning Applications: Challenges and Lessons Learnt

Saumya Bhatnagar; Sumit Mund; Enrico Scala; Keith McCabe; Lee McCluskey; Mauro Vallati

doi:10.5220/0010857100003116

On-the-Fly Knowledge Acquisition for Automated Planning Applications: Challenges and Lessons Learnt

Saumya Bhatnagar, Sumit Mund, Enrico Scala, Keith McCabe, Lee McCluskey, Mauro Vallati

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

6 Citations (Scopus)

Abstract

Automated planning is a prominent AI challenge, and it is now exploited in a range of real-world applications. There are three crucial aspects of automated planning: the planning engine, the domain model, and the problem instance. While the planning engine and the domain model can be engineered and optimised offline, in many applications there is the need to generate problem instances on the fly. In this paper we focus on the challenges of on-the-fly knowledge acquisition for complex and variegated problem instances. We consider as a case study the application of planning to urban traffic control and we describe the designed and developed knowledge acquisition process. This allows us to discuss a range of lessons learned from the experience, and to point to important lines of research for support the knowledge acquisition process for automated planning applications.

Original language	English
Title of host publication	Proceedings of the 14th International Conference on Agents and Artificial Intelligence, ICAART 2022
Editors	Ana Paula Rocha, Luc Steels, Jaap van den Herik
Publisher	SciTePress
Pages	387-397
Number of pages	11
Volume	2 of 3
ISBN (Print)	9789897585470
DOIs	https://doi.org/10.5220/0010857100003116
Publication status	Published - 3 Feb 2022
Event	14th International Conference on Agents and Artificial Intelligence - Online Streaming, Virtual Duration: 3 Feb 2022 → 5 Feb 2022 Conference number: 14 https://icaart.scitevents.org/

Publication series

Name	International Conference on Agents and Artificial Intelligence
Publisher	SciTePress
ISSN (Print)	2184-433X

Conference

Conference	14th International Conference on Agents and Artificial Intelligence
Abbreviated title	ICAART 2022
City	Virtual
Period	3/02/22 → 5/02/22
Internet address	https://icaart.scitevents.org/

UN SDGs

This output contributes to the following UN Sustainable Development Goals (SDGs)

Access to Document

10.5220/0010857100003116Licence: CC BY-NC-ND

Cite this

Bhatnagar, S., Mund, S., Scala, E., McCabe, K., McCluskey, L., & Vallati, M. (2022). On-the-Fly Knowledge Acquisition for Automated Planning Applications: Challenges and Lessons Learnt. In A. P. Rocha, L. Steels, & J. van den Herik (Eds.), Proceedings of the 14th International Conference on Agents and Artificial Intelligence, ICAART 2022 (Vol. 2 of 3, pp. 387-397). (International Conference on Agents and Artificial Intelligence). SciTePress. https://doi.org/10.5220/0010857100003116

Bhatnagar, Saumya ; Mund, Sumit ; Scala, Enrico et al. / On-the-Fly Knowledge Acquisition for Automated Planning Applications : Challenges and Lessons Learnt. Proceedings of the 14th International Conference on Agents and Artificial Intelligence, ICAART 2022. editor / Ana Paula Rocha ; Luc Steels ; Jaap van den Herik. Vol. 2 of 3 SciTePress, 2022. pp. 387-397 (International Conference on Agents and Artificial Intelligence).

@inproceedings{112299ba89cb4cf4bf0a9d286bdc71f8,

title = "On-the-Fly Knowledge Acquisition for Automated Planning Applications: Challenges and Lessons Learnt",

abstract = "Automated planning is a prominent AI challenge, and it is now exploited in a range of real-world applications. There are three crucial aspects of automated planning: the planning engine, the domain model, and the problem instance. While the planning engine and the domain model can be engineered and optimised offline, in many applications there is the need to generate problem instances on the fly. In this paper we focus on the challenges of on-the-fly knowledge acquisition for complex and variegated problem instances. We consider as a case study the application of planning to urban traffic control and we describe the designed and developed knowledge acquisition process. This allows us to discuss a range of lessons learned from the experience, and to point to important lines of research for support the knowledge acquisition process for automated planning applications.",

keywords = "Automated planning applications, Automated planning (AI), Urban traffic control, Knowledge acquisition, Traffic control",

author = "Saumya Bhatnagar and Sumit Mund and Enrico Scala and Keith McCabe and Lee McCluskey and Mauro Vallati",

year = "2022",

month = feb,

day = "3",

doi = "10.5220/0010857100003116",

language = "English",

isbn = "9789897585470",

volume = "2 of 3",

series = "International Conference on Agents and Artificial Intelligence",

publisher = "SciTePress",

pages = "387--397",

editor = "Rocha, {Ana Paula} and Luc Steels and {van den Herik}, {Jaap }",

booktitle = "Proceedings of the 14th International Conference on Agents and Artificial Intelligence, ICAART 2022",

address = "Portugal",

note = "14th International Conference on Agents and Artificial Intelligence, ICAART 2022 ; Conference date: 03-02-2022 Through 05-02-2022",

url = "https://icaart.scitevents.org/",

}

Bhatnagar, S, Mund, S, Scala, E, McCabe, K, McCluskey, L & Vallati, M 2022, On-the-Fly Knowledge Acquisition for Automated Planning Applications: Challenges and Lessons Learnt. in AP Rocha, L Steels & J van den Herik (eds), Proceedings of the 14th International Conference on Agents and Artificial Intelligence, ICAART 2022. vol. 2 of 3, International Conference on Agents and Artificial Intelligence, SciTePress, pp. 387-397, 14th International Conference on Agents and Artificial Intelligence, Virtual, 3/02/22. https://doi.org/10.5220/0010857100003116

On-the-Fly Knowledge Acquisition for Automated Planning Applications : Challenges and Lessons Learnt. / Bhatnagar, Saumya; Mund, Sumit; Scala, Enrico et al.

Proceedings of the 14th International Conference on Agents and Artificial Intelligence, ICAART 2022. ed. / Ana Paula Rocha; Luc Steels; Jaap van den Herik. Vol. 2 of 3 SciTePress, 2022. p. 387-397 (International Conference on Agents and Artificial Intelligence).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

TY - GEN

T1 - On-the-Fly Knowledge Acquisition for Automated Planning Applications

T2 - 14th International Conference on Agents and Artificial Intelligence

AU - Bhatnagar, Saumya

AU - Mund, Sumit

AU - Scala, Enrico

AU - McCabe, Keith

AU - McCluskey, Lee

AU - Vallati, Mauro

N1 - Conference code: 14

PY - 2022/2/3

Y1 - 2022/2/3

N2 - Automated planning is a prominent AI challenge, and it is now exploited in a range of real-world applications. There are three crucial aspects of automated planning: the planning engine, the domain model, and the problem instance. While the planning engine and the domain model can be engineered and optimised offline, in many applications there is the need to generate problem instances on the fly. In this paper we focus on the challenges of on-the-fly knowledge acquisition for complex and variegated problem instances. We consider as a case study the application of planning to urban traffic control and we describe the designed and developed knowledge acquisition process. This allows us to discuss a range of lessons learned from the experience, and to point to important lines of research for support the knowledge acquisition process for automated planning applications.

AB - Automated planning is a prominent AI challenge, and it is now exploited in a range of real-world applications. There are three crucial aspects of automated planning: the planning engine, the domain model, and the problem instance. While the planning engine and the domain model can be engineered and optimised offline, in many applications there is the need to generate problem instances on the fly. In this paper we focus on the challenges of on-the-fly knowledge acquisition for complex and variegated problem instances. We consider as a case study the application of planning to urban traffic control and we describe the designed and developed knowledge acquisition process. This allows us to discuss a range of lessons learned from the experience, and to point to important lines of research for support the knowledge acquisition process for automated planning applications.

KW - Automated planning applications

KW - Automated planning (AI)

KW - Urban traffic control

KW - Knowledge acquisition

KW - Traffic control

UR - http://www.scopus.com/inward/record.url?scp=85151045546&partnerID=8YFLogxK

U2 - 10.5220/0010857100003116

DO - 10.5220/0010857100003116

M3 - Conference contribution

SN - 9789897585470

VL - 2 of 3

T3 - International Conference on Agents and Artificial Intelligence

SP - 387

EP - 397

BT - Proceedings of the 14th International Conference on Agents and Artificial Intelligence, ICAART 2022

A2 - Rocha, Ana Paula

A2 - Steels, Luc

A2 - van den Herik, Jaap

PB - SciTePress

Y2 - 3 February 2022 through 5 February 2022

ER -

Bhatnagar S, Mund S, Scala E, McCabe K, McCluskey L , Vallati M. On-the-Fly Knowledge Acquisition for Automated Planning Applications: Challenges and Lessons Learnt. In Rocha AP, Steels L, van den Herik J, editors, Proceedings of the 14th International Conference on Agents and Artificial Intelligence, ICAART 2022. Vol. 2 of 3. SciTePress. 2022. p. 387-397. (International Conference on Agents and Artificial Intelligence). doi: 10.5220/0010857100003116

On-the-Fly Knowledge Acquisition for Automated Planning Applications: Challenges and Lessons Learnt

Abstract

Publication series

Conference

UN SDGs

Access to Document

Other files and links

Fingerprint

Cite this