Zobrazeno 1 - 10
of 52
pro vyhledávání: '"Sean Sedwards"'
Publikováno v:
Rules and Reasoning (2022) 263-279
Autonomous vehicles require highly sophisticated decision-making to determine their motion. This paper describes how such functionality can be achieved with a practical rule engine learned from expert driving decisions. We propose an algorithm to cre
Externí odkaz:
http://arxiv.org/abs/2407.00460
Autor:
Danny Bøgsted Poulsen, Sean Sedwards, Axel Legay, Marius Mikučionis, Kim G. Larsen, Dehui Du, Alexandre David
Publikováno v:
Electronic Proceedings in Theoretical Computer Science, Vol 92, Iss Proc. HSB 2012, Pp 122-136 (2012)
This paper presents novel extensions and applications of the UPPAAL-SMC model checker. The extensions allow for statistical model checking of stochastic hybrid systems. We show how our race-based stochastic semantics extends to networks of hybrid sys
Externí odkaz:
https://doaj.org/article/c966dcac1e5b4dfdb933e9abf3c8f2cf
Publikováno v:
MT@CPSWeek
Optimization-based falsification employs stochastic optimization algorithms to search for error input of hybrid systems. In this paper we introduce a simple idea to enhance falsification, namely time staging, that allows the time-causal structure of
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::3fb21597456215c6070ab8dd70d5dc9a
https://doi.org/10.4204/eptcs.361.5
https://doi.org/10.4204/eptcs.361.5
Publikováno v:
ACM Transactions on Modeling and Computer Simulation. 31:1-26
Reinforcement learning (RL) is an attractive way to implement high-level decision-making policies for autonomous driving, but learning directly from a real vehicle or a high-fidelity simulator is variously infeasible. We therefore consider the proble
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::3926edc0d6d169d3eb81ac968c3fa5d1
https://doi.org/10.1145/3449356
https://doi.org/10.1145/3449356
Publikováno v:
ACM Transactions on Modeling and Computer Simulation. 31:1-22
We present and analyse an algorithm that quickly finds falsifying inputs for hybrid systems. Our method is based on a probabilistically directed tree search, whose distribution adapts to consider an increasingly fine-grained discretization of the inp
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::e95769af9157b2c8386de31ba8865134
https://doi.org/10.1145/3459605
https://doi.org/10.1145/3459605
Publikováno v:
Rules and Reasoning ISBN: 9783031215407
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::0ce970da40a9e4f9eb33f4d81017492f
https://doi.org/10.1007/978-3-031-21541-4_17
https://doi.org/10.1007/978-3-031-21541-4_17
Publikováno v:
IJCNN
We consider the problem of verifying complex learned controllers using distillation. In contrast to previous work, we require that the distilled model maintains behavioural fidelity with an oracle, defining the notion of non-divergent path length (NP
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::cac730fc0f44be626828814a43c9402a
https://doi.org/10.1109/ijcnn52387.2021.9533410
https://doi.org/10.1109/ijcnn52387.2021.9533410
Publikováno v:
ITSC
Semantic segmentation is an important perception function for automated driving (AD), but training a deep neural network for the task using supervised learning requires expensive manual labelling. Active learning (AL) addresses this challenge by auto
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::c292dc341f9cc5df700e7e87bf963e10
https://doi.org/10.1109/itsc45102.2020.9294260
https://doi.org/10.1109/itsc45102.2020.9294260
Publikováno v:
IJCNN
Deep neural networks are capable of solving complex control tasks in challenging environments, but their learned policies are hard to interpret. Not being able to explain or verify them limits their practical applicability. By contrast, decision tree
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::b1cafc060d589d36b60c32e42a1b3319
https://doi.org/10.1109/ijcnn48605.2020.9207648
https://doi.org/10.1109/ijcnn48605.2020.9207648
Publikováno v:
ADHS
Time delays pose an important challenge in networked control systems, which are now ubiquitous. Focusing on switched systems, we introduce a framework that provides an upper bound for errors caused by switching delays. Our framework is based on appro
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::445033968b279b39f6f31e6d6d246ebc
https://doi.org/10.1016/j.ifacol.2018.08.042
https://doi.org/10.1016/j.ifacol.2018.08.042