Planning via model checking with decision-tree controllers

D 2022

Planning via model checking with decision-tree controllers

KIESBYE, Jonis; Kush GROVER; Pranav ASHOK a Jan KŘETÍNSKÝ

Základní údaje

Originální název

Planning via model checking with decision-tree controllers

Autoři

KIESBYE, Jonis; Kush GROVER; Pranav ASHOK a Jan KŘETÍNSKÝ

Vydání

2022 International Conference on Robotics and Automation, ICRA 2022, Philadelphia, PA, USA, May 23-27, 2022, od s. 4347-4354, 8 s. 2022

Nakladatel

IEEE

Další údaje

Typ výsledku

Stať ve sborníku

Označené pro přenos do RIV

Organizační jednotka

Fakulta informatiky

ISBN

9781728196817

ISSN

DOI

https://doi.org/10.1109/ICRA46639.2022.9811980

Změněno: 17. 3. 2025 14:43, RNDr. Pavel Šmerk, Ph.D.

Anotace

V originále

Planning problems can be solved not only by planners, but also by model checkers. While the former yield a plan that requires replanning as soon as any fault occurs, the latter provide a 'universal' plan (a.k.a. strategy, policy, or controller) able to make decisions under all circumstances. One of the prohibitive aspects of the latter approach is stemming from this very advantage: since it is defined for all possible states of the system, it is typically so large that it does not fit into small memories of embedded devices. As another consequence of the size, its execution may be slow. In this paper, we provide a solution to this issue by linking the model checkers with decision-tree learners, resulting in decision-tree representations of the synthesized strategies. Not only are they dramatically smaller, but also more explainable and orders-of-magnitude faster to execute than plans with replanning. In addition, we describe a method for model validation and debugging via the model checker and the decision-tree learner in the loop. We illustrate the approach on our case study of a robotic arm for picking items in a real industrial setting.

Citovat

KIESBYE, Jonis; Kush GROVER; Pranav ASHOK a Jan KŘETÍNSKÝ. Planning via model checking with decision-tree controllers. In 2022 International Conference on Robotics and Automation, ICRA 2022, Philadelphia, PA, USA, May 23-27, 2022. IEEE, 2022, s. 4347-4354. ISBN 9781728196817. Dostupné z: https://doi.org/10.1109/ICRA46639.2022.9811980.

@inproceedings{2484777,
   author = {Kiesbye, Jonis and Grover, Kush and Ashok, Pranav and Křetínský, Jan},
   booktitle = {2022 International Conference on Robotics and Automation, ICRA 2022, Philadelphia, PA, USA, May 23-27, 2022},
   doi = {https://doi.org/10.1109/ICRA46639.2022.9811980},
   isbn = {9781728196817},
   pages = {4347-4354},
   publisher = {IEEE},
   title = {Planning via model checking with decision-tree controllers},
   year = {2022}
}

TY  - CONF
ID  - 2484777
AU  - Kiesbye, Jonis - Grover, Kush - Ashok, Pranav - Křetínský, Jan
PY  - 2022
TI  - Planning via model checking with decision-tree controllers
PB  - IEEE
SN  - 9781728196817
N2  - Planning problems can be solved not only by planners, but also by model checkers. While the former yield a plan that requires replanning as soon as any fault occurs, the latter provide a 'universal' plan (a.k.a. strategy, policy, or controller) able to make decisions under all circumstances. One of the prohibitive aspects of the latter approach is stemming from this very advantage: since it is defined for all possible states of the system, it is typically so large that it does not fit into small memories of embedded devices. As another consequence of the size, its execution may be slow. In this paper, we provide a solution to this issue by linking the model checkers with decision-tree learners, resulting in decision-tree representations of the synthesized strategies. Not only are they dramatically smaller, but also more explainable and orders-of-magnitude faster to execute than plans with replanning. In addition, we describe a method for model validation and debugging via the model checker and the decision-tree learner in the loop. We illustrate the approach on our case study of a robotic arm for picking items in a real industrial setting.
ER  -

KIESBYE, Jonis; Kush GROVER; Pranav ASHOK a Jan KŘETÍNSKÝ. Planning via model checking with decision-tree controllers. In \textit{2022 International Conference on Robotics and Automation, ICRA 2022, Philadelphia, PA, USA, May 23-27, 2022}. IEEE, 2022, s.~4347-4354. ISBN~9781728196817. Dostupné z: https://doi.org/10.1109/ICRA46639.2022.9811980.

Přehled o publikaci