Collaborative Perceptual Anchoring Across Static, Wearable and Robotic Sensors

Sune Lundø Sørensen

doi:10.21996/ag00-mj30

Collaborative Perceptual Anchoring Across Static, Wearable and Robotic Sensors

Sune Lundø Sørensen

Publikation: Afhandling › Ph.d.-afhandling

4 Downloads (Pure)

Abstract

Service-robotter er en stadig mere almindelig del af vores hverdag. Foruden produktion assisterer robotter os i mange forskellige opgaver, herunder rengøring, græsslåning og servering af drinks. En af de udfordringer som en robot møder er, at opbygge og vedligeholde en symbolsk verdensmodel af deres omgivelser, hvilket gør det muligt for robotten at kommunikere med mennesker omkring objekter og planlægge udførslen af opgaver. Processen hvorved den korrekte association mellem symbolerne i verdensmodellen og objekterne i den fysiske verden sikres, kaldes perceptual anchoring (perceptuel forankring). Adskillige videnskabelige arbejder har foreslået løsninger til denne udfordring, ved brug af data fra robot-monterede sensorer. Dette præsenterer endnu en udfordring, da robotten kun kan observere sine umiddelbare omgivelser. Dette motiverer en anden tilgang hvor andre sensorer, der ikke er på robotten, anvendes til at samarbejde om at observere omgivelserne. Denne tilgang kommer med sine egne udfordringer, som den seneste forskning endnu ikke har udforsket eller løst til fulde. Dette PhD-projekt adresserer udfordringerne i kollaborativ observering, på tværs af Internet-of-things (IoT) sensorer, sensorer båret af mennesker og robot-sensorer. Denne afhandling præsenterer fire tekniske bidrag. Det første bidrag er en sammenligning af fire metoder til at associere data fra IoT- og robot-sensorer. Det andet bidrag er et system til kollaborativ observering ved brug af IoT- og robot-sensorer, til manipuleringsopgaver. Det tredje bidrag er et komplet anchoring-system til robot-sensorer og sensorer båret af mennesker. Det sidste bidrag er et overblik over de tekniske innovationer og erfaringer opnået i FacilityCobot-projektet ved at anvende bidragene. Konklusionen er at dette PhD-projekt udgør et fundament for yderligere bedrifter i kollaborativ observation på tværs a IoT-sensorer, sensorer båret af mennesker og robot-sensorer.

Originalsprog	Engelsk
Bevilgende institution	Syddansk Universitet
Vejledere/rådgivere	Kjærgaard, Mikkel Baun, Hovedvejleder
Dato for forsvar	18. mar. 2024
Udgiver	Syddansk Universitet. Det Tekniske Fakultet
DOI	https://doi.org/10.21996/ag00-mj30
Status	Udgivet - 4. mar. 2024

Bibliografisk note

A print copy of the thesis can be accessed at the Library. 

Note vedr. afhandling

Afhandlingen kan læses på SDUs bibliotek. 

Dokumenter og links

10.21996/ag00-mj30

Open Access VersionForlagets udgivne version, 57,2 MB

Citationsformater

@misc{ebeaadd179a64840977bf62e1991bdd2,

title = "Collaborative Perceptual Anchoring Across Static, Wearable and Robotic Sensors",

abstract = "Service robots are increasingly becoming a common part of our everyday lives. Beside manufacturing, they can assists us in many tasks, including cleaning, lawn-moving, and serving drinks. One of the challenges that robots face is building and maintaining a symbolic world model of their environment, which enables the robot to communicate with a user about objects and to plan tasks. The process of securing the correct correspondence between the symbols in the world model and the objects in the physical world is called perceptual anchoring. Several works on perceptual anchoring have proposed solutions to this challenge, using data from robot-mounted sensors. This presents a challenge due to the fact that the robot can only sense its immediate surroundings. This motivates another approach, where other sensors, which are not on the robot, are used to achieve collaborative sensing of the environment. This approach comes with its own set of challenges, which the current state of the art has yet to fully explore and address. This PhD project address the challenges of collaborative sensing across Internetof-things (IoT), wearable and robotics sensors. The dissertation presents four technical contributions. Firstly, a comparison of methods for data association for IoT and robot sensors. Secondly, a framework for collaborative anchoring using IoT and robot sensors, for manipulation tasks. Thirdly, a complete anchoring pipeline for robot and wearable sensors. And finally, a review of the technical innovations and lessons learned in the FacilityCobot project applying the contributions in practice. In conclusion, this PhD project provides a foundation for further advancements in the field of collaborative sensing across IoT, wearable and robotic sensors.",

author = "S{\o}rensen, {Sune Lund{\o}}",

note = "A print copy of the thesis can be accessed at the Library.  ",

year = "2024",

month = mar,

day = "4",

doi = "10.21996/ag00-mj30",

language = "English",

publisher = "Syddansk Universitet. Det Tekniske Fakultet",

address = "Denmark",

school = "SDU",

}

TY - GEN

T1 - Collaborative Perceptual Anchoring Across Static, Wearable and Robotic Sensors

AU - Sørensen, Sune Lundø

N1 - A print copy of the thesis can be accessed at the Library. 

PY - 2024/3/4

Y1 - 2024/3/4

N2 - Service robots are increasingly becoming a common part of our everyday lives. Beside manufacturing, they can assists us in many tasks, including cleaning, lawn-moving, and serving drinks. One of the challenges that robots face is building and maintaining a symbolic world model of their environment, which enables the robot to communicate with a user about objects and to plan tasks. The process of securing the correct correspondence between the symbols in the world model and the objects in the physical world is called perceptual anchoring. Several works on perceptual anchoring have proposed solutions to this challenge, using data from robot-mounted sensors. This presents a challenge due to the fact that the robot can only sense its immediate surroundings. This motivates another approach, where other sensors, which are not on the robot, are used to achieve collaborative sensing of the environment. This approach comes with its own set of challenges, which the current state of the art has yet to fully explore and address. This PhD project address the challenges of collaborative sensing across Internetof-things (IoT), wearable and robotics sensors. The dissertation presents four technical contributions. Firstly, a comparison of methods for data association for IoT and robot sensors. Secondly, a framework for collaborative anchoring using IoT and robot sensors, for manipulation tasks. Thirdly, a complete anchoring pipeline for robot and wearable sensors. And finally, a review of the technical innovations and lessons learned in the FacilityCobot project applying the contributions in practice. In conclusion, this PhD project provides a foundation for further advancements in the field of collaborative sensing across IoT, wearable and robotic sensors.

AB - Service robots are increasingly becoming a common part of our everyday lives. Beside manufacturing, they can assists us in many tasks, including cleaning, lawn-moving, and serving drinks. One of the challenges that robots face is building and maintaining a symbolic world model of their environment, which enables the robot to communicate with a user about objects and to plan tasks. The process of securing the correct correspondence between the symbols in the world model and the objects in the physical world is called perceptual anchoring. Several works on perceptual anchoring have proposed solutions to this challenge, using data from robot-mounted sensors. This presents a challenge due to the fact that the robot can only sense its immediate surroundings. This motivates another approach, where other sensors, which are not on the robot, are used to achieve collaborative sensing of the environment. This approach comes with its own set of challenges, which the current state of the art has yet to fully explore and address. This PhD project address the challenges of collaborative sensing across Internetof-things (IoT), wearable and robotics sensors. The dissertation presents four technical contributions. Firstly, a comparison of methods for data association for IoT and robot sensors. Secondly, a framework for collaborative anchoring using IoT and robot sensors, for manipulation tasks. Thirdly, a complete anchoring pipeline for robot and wearable sensors. And finally, a review of the technical innovations and lessons learned in the FacilityCobot project applying the contributions in practice. In conclusion, this PhD project provides a foundation for further advancements in the field of collaborative sensing across IoT, wearable and robotic sensors.

U2 - 10.21996/ag00-mj30

DO - 10.21996/ag00-mj30

M3 - Ph.D. thesis

PB - Syddansk Universitet. Det Tekniske Fakultet

ER -

Collaborative Perceptual Anchoring Across Static, Wearable and Robotic Sensors

Abstract

Bibliografisk note

Note vedr. afhandling

Dokumenter og links

Fingeraftryk

Citationsformater