國立虎尾科技大學 |

Safe and Interactive Autonomy : = Control, Learning, and Verification.

紀錄類型:	書目-語言資料,手稿 : Monograph/item
正題名/作者:	Safe and Interactive Autonomy :/
其他題名:	Control, Learning, and Verification.
作者:	Sadigh, Dorsa.
面頁冊數:	1 online resource (195 pages)
附註:	Source: Dissertation Abstracts International, Volume: 79-05(E), Section: B.
Contained By:	Dissertation Abstracts International79-05B(E).
標題:	Engineering. -
電子資源:	click for full text (PQDT)
ISBN:	9780355572247

Safe and Interactive Autonomy : = Control, Learning, and Verification.
Sadigh, Dorsa.

Safe and Interactive Autonomy :Control, Learning, and Verification. - 1 online resource (195 pages)

Source: Dissertation Abstracts International, Volume: 79-05(E), Section: B.

Thesis (Ph.D.)

Includes bibliographical references

The goal of my research is to enable safe and reliable integration of human-robot systems in our society by providing a unified framework for modeling and design of these systems. Today's society is rapidly advancing towards autonomous systems that interact and collaborate with humans, e.g., semiautonomous vehicles interacting with drivers and pedestrians, medical robots used in collaboration with doctors, or service robots interacting with their users in smart homes. The safety-critical nature of these systems require us to provide provably correct guarantees about their performance. In this dissertation, we develop a formalism for the design of algorithms and mathematical models that enable correct-by-construction control and verification of human-robot systems.

Electronic reproduction.
Ann Arbor, Mich. :
ProQuest,
2018

Mode of access: World Wide Web

ISBN: 9780355572247Subjects--Topical Terms:

561152
Engineering.
Index Terms--Genre/Form:

554714
Electronic books.

Safe and Interactive Autonomy : = Control, Learning, and Verification.
LDR:03394ntm a2200385Ki 4500 001 910551
005 20180517123957.5
006 m o u
007 cr mn||||a|a||
008 190606s2017 xx obm 000 0 eng d
020 $a 9780355572247
035 $a (MiAaPQ)AAI10620045
035 $a (MiAaPQ)berkeley:17300
035 $a AAI10620045
040 $a MiAaPQ $b eng $c MiAaPQ
099 $a TUL $f hyy $c available through World Wide Web
100 1 $a Sadigh, Dorsa. $3 1181896
245 1 0 $a Safe and Interactive Autonomy : $b Control, Learning, and Verification.
264 0 $c 2017
300 $a 1 online resource (195 pages)
336 $a text $b txt $2 rdacontent
337 $a computer $b c $2 rdamedia
338 $a online resource $b cr $2 rdacarrier
500 $a Source: Dissertation Abstracts International, Volume: 79-05(E), Section: B.
500 $a Advisers: Sanjit Seshia; Shankar Sastry.
502 $a Thesis (Ph.D.) $c University of California, Berkeley $d 2017.
504 $a Includes bibliographical references
520 $a The goal of my research is to enable safe and reliable integration of human-robot systems in our society by providing a unified framework for modeling and design of these systems. Today's society is rapidly advancing towards autonomous systems that interact and collaborate with humans, e.g., semiautonomous vehicles interacting with drivers and pedestrians, medical robots used in collaboration with doctors, or service robots interacting with their users in smart homes. The safety-critical nature of these systems require us to provide provably correct guarantees about their performance. In this dissertation, we develop a formalism for the design of algorithms and mathematical models that enable correct-by-construction control and verification of human-robot systems.
520 $a We focus on two natural instances of this agenda. In the first part, we study interaction-aware control, where we use algorithmic HRI to be mindful of the effects of autonomous systems on humans' actions, and further leverage these effects for better safety, efficiency, coordination, and estimation. We further use active learning techniques to update and better learn human models, and study the accuracy and robustness of these models. In the second part, we address the problem of providing correctness guarantees, while taking into account the uncertainty arising from the environment or human models. Through this effort, we introduce Probabilistic Signal Temporal Logic (PrSTL), an expressive specification language that allows representing Bayesian graphical models as part of its predicates. Further, we provide a solution for synthesizing controllers that satisfy temporal logic specifications in probabilistic and reactive settings, and discuss a diagnosis and repair algorithm for systematic transfer of control to the human in unrealizable settings. While the algorithms and techniques introduced can be applied to many human-robot systems, in this dissertation, we will mainly focus on the implications of my work for semiautonomous driving.
533 $a Electronic reproduction. $b Ann Arbor, Mich. : $c ProQuest, $d 2018
538 $a Mode of access: World Wide Web
650 4 $a Engineering. $3 561152
650 4 $a Computer engineering. $3 569006
650 4 $a Robotics. $3 561941
650 4 $a Artificial intelligence. $3 559380
655 7 $a Electronic books. $2 local $3 554714
690 $a 0537
690 $a 0464
690 $a 0771
690 $a 0800
710 2 $a ProQuest Information and Learning Co. $3 1178819
710 2 $a University of California, Berkeley. $b Electrical Engineering & Computer Sciences. $3 845564
773 0 $t Dissertation Abstracts International $g 79-05B(E).
856 4 0 $u http://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=10620045 $z click for full text (PQDT)