kth.sePublications
Change search
CiteExportLink to record
Permanent link

Direct link
Cite
Citation style
  • apa
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Other style
More styles
Language
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Other locale
More languages
Output format
  • html
  • text
  • asciidoc
  • rtf
Long-term Prediction of Motion Trajectories Using Path Homology Clusters
KTH, School of Electrical Engineering and Computer Science (EECS), Intelligent systems, Robotics, Perception and Learning, RPL. KTH, School of Electrical Engineering and Computer Science (EECS), Centres, Centre for Autonomous Systems, CAS.ORCID iD: 0000-0002-8750-0897
CUNY College of Staten Island,Mathematics Department,New York,USA.ORCID iD: 0000-0001-6322-7542
KTH, School of Electrical Engineering and Computer Science (EECS), Intelligent systems, Robotics, Perception and Learning, RPL. KTH, School of Electrical Engineering and Computer Science (EECS), Centres, Centre for Autonomous Systems, CAS.ORCID iD: 0000-0003-1114-6040
KTH, School of Electrical Engineering and Computer Science (EECS), Intelligent systems, Robotics, Perception and Learning, RPL. KTH, School of Electrical Engineering and Computer Science (EECS), Centres, Centre for Autonomous Systems, CAS.ORCID iD: 0000-0003-2965-2953
2019 (English)In: 2019 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), Institute of Electrical and Electronics Engineers (IEEE), 2019Conference paper, Published paper (Refereed)
Abstract [en]

In order for robots to share their workspace with people, they need to reason about human motion efficiently. In this work we leverage large datasets of paths in order to infer local models that are able to perform long-term predictions of human motion. Further, since our method is based on simple dynamics, it is conceptually simple to understand and allows one to interpret the predictions produced, as well as to extract a cost function that can be used for planning. The main difference between our method and similar systems, is that we employ a map of the space and translate the motion of groups of paths into vector fields on that map. We test our method on synthetic data and show its performance on the Edinburgh forum pedestrian long-term tracking dataset [1] where we were able to outperform a Gaussian Mixture Model tasked with extracting dynamics from the paths.

Place, publisher, year, edition, pages
Institute of Electrical and Electronics Engineers (IEEE), 2019.
National Category
Computer Sciences
Identifiers
URN: urn:nbn:se:kth:diva-266956DOI: 10.1109/IROS40897.2019.8968125ISI: 000544658400089Scopus ID: 2-s2.0-85081156994OAI: oai:DiVA.org:kth-266956DiVA, id: diva2:1388795
Conference
IEEE/RSJ International Conference on Intelligent Robots and Systems,3-8 Nov. 2019, Macau, China, China
Funder
Knut and Alice Wallenberg Foundation
Note

QC 20200203  QC 20200903

Available from: 2020-01-27 Created: 2020-01-27 Last updated: 2022-06-26Bibliographically approved
In thesis
1. Topological Methods for Motion Prediction and Caging
Open this publication in new window or tab >>Topological Methods for Motion Prediction and Caging
2020 (English)Doctoral thesis, comprehensive summary (Other academic)
Abstract [en]

To fulfill the requirements of automation in unstructured environmentsit will be necessary to endow robots with the ability to plan actions thatcan handle the dynamic nature of changing environments and are robust toperceptual errors. This thesis focuses on the design of algorithms to facilitatemotion planning in human environments and rigid object manipulation.Understanding human motion is a necessary first step to be able to performmotion planning in spaces that are inhabited by humans. Specifically throughlong-term prediction a robot should be able to plan collision-avoiding paths tocarry out whatever tasks are required of it. In this thesis we present a methodto classify motions by clustering paths, together with a method to translatethe resulting clusters into motion patterns that can be used to predict motion.Another challenge of robotics is the manipulation of everyday objects.Even in the realm of rigid objects, safe object-manipulation by either grippersor dexterous robotic hands requires complex physical parameter estimation.Such estimations are often error-prone and misestimations may cause completefailure to execute the desired task. Caging is presented as an alternativeapproach to classical manipulation by employing topological invariants todetermine whether an object is secured with only bounded mobility. Wepresent a method to decide whether a rigid object is in fact caged by a givengrasp or not, relying only on a rough approximation of the object and thegripper.

Abstract [sv]

För att uppfylla kraven för automatisering i ostrukturerade miljöer ärdet nödvändigt att förse robotar med förmågan att planera i föränderligamiljöer. Denna avhandling fokuserar på design av algoritmer för att underlättarörelseplanering i mänskliga miljöer och manipulering av rigida objekt.För att planera handlingar i utrymmen där människor rör sig är detnödvändigt, som ett första steg, att förstå hur människor rör sig. Genom långsiktigaprognoser om människors rörelser kan en robot planera undvikande avkollisioner, samtidigt som en given uppgift kan planeras. Den här avhandlingenpresenterar både metoder för klassificering av rörelser, samt metoder för attanvända dessa klasser för förutsägelse av rörelser.En annan stor utmaning för robotik är manipulering av vardagliga objekt.För att manipulera rigida objekt med enkla gripdon, så väl som avanceraderobothänder, är det nödvändigt att uppskatta komplexa fysiska parametrar.Sådana uppskattningar innehar ofta fel som kan leda till misslyckande med attutföra den givna uppgiften. Caging är ett alternativ till klassisk manipulering,där topologiska invarianter används för att avgöra om ett objekt är säkratmed endast begränsad rörlighet. Vi presenterar en metod för att bestämmaom en konfiguration kan hålla ett objekt fast eller inte, som bara förlitar sigpå en förenklad modell av objekt och gripdon.

Place, publisher, year, edition, pages
KTH Royal Institute of Technology, 2020
Series
TRITA-EECS-AVL ; 2020:11
National Category
Robotics and automation
Research subject
Computer Science
Identifiers
urn:nbn:se:kth:diva-268370 (URN)978-91-7873-450-4 (ISBN)
Public defence
2020-03-17, F3, Lindstedtsvägen 26, 114 28 Stockholm, 10:00 (English)
Opponent
Supervisors
Note

QC 20200221

Available from: 2020-02-21 Created: 2020-02-18 Last updated: 2025-02-09Bibliographically approved

Open Access in DiVA

No full text in DiVA

Other links

Publisher's full textScopus

Authority records

Pinto Basto de Carvalho, Joao FredericoVejdemo-Johansson, MikaelPokorny, Florian T.Kragic, Danica

Search in DiVA

By author/editor
Pinto Basto de Carvalho, Joao FredericoVejdemo-Johansson, MikaelPokorny, Florian T.Kragic, Danica
By organisation
Robotics, Perception and Learning, RPLCentre for Autonomous Systems, CAS
Computer Sciences

Search outside of DiVA

GoogleGoogle Scholar

doi
urn-nbn

Altmetric score

doi
urn-nbn
Total: 172 hits
CiteExportLink to record
Permanent link

Direct link
Cite
Citation style
  • apa
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Other style
More styles
Language
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Other locale
More languages
Output format
  • html
  • text
  • asciidoc
  • rtf