liu.seSearch for publications in DiVA
Change search
CiteExportLink to record
Permanent link

Direct link
Cite
Citation style
  • apa
  • harvard1
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • oxford
  • 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
Methods for Scalable and Safe Robot Learning
Linköping University, Department of Computer and Information Science, Artificial Intelligence and Integrated Computer Systems. Linköping University, Faculty of Science & Engineering. (AIICS)
2017 (English)Licentiate thesis, comprehensive summary (Other academic)
Abstract [en]

Robots are increasingly expected to go beyond controlled environments in laboratories and factories, to enter real-world public spaces and homes. However, robot behavior is still usually engineered for narrowly defined scenarios. To manually encode robot behavior that works within complex real world environments, such as busy work places or cluttered homes, can be a daunting task. In addition, such robots may require a high degree of autonomy to be practical, which imposes stringent requirements on safety and robustness. \setlength{\parindent}{2em}\setlength{\parskip}{0em}The aim of this thesis is to examine methods for automatically learning safe robot behavior, lowering the costs of synthesizing behavior for complex real-world situations. To avoid task-specific assumptions, we approach this from a data-driven machine learning perspective. The strength of machine learning is its generality, given sufficient data it can learn to approximate any task. However, being embodied agents in the real-world, robots pose a number of difficulties for machine learning. These include real-time requirements with limited computational resources, the cost and effort of operating and collecting data with real robots, as well as safety issues for both the robot and human bystanders.While machine learning is general by nature, overcoming the difficulties with real-world robots outlined above remains a challenge. In this thesis we look for a middle ground on robot learning, leveraging the strengths of both data-driven machine learning, as well as engineering techniques from robotics and control. This includes combing data-driven world models with fast techniques for planning motions under safety constraints, using machine learning to generalize such techniques to problems with high uncertainty, as well as using machine learning to find computationally efficient approximations for use on small embedded systems.We demonstrate such behavior synthesis techniques with real robots, solving a class of difficult dynamic collision avoidance problems under uncertainty, such as induced by the presence of humans without prior coordination. Initially using online planning offloaded to a desktop CPU, and ultimately as a deep neural network policy embedded on board a 7 quadcopter.

Place, publisher, year, edition, pages
Linköping: Linköping University Electronic Press, 2017. , p. 37
Series
Linköping Studies in Science and Technology. Thesis, ISSN 0280-7971 ; 1780
Keywords [en]
Symbicloud, ELLIIT, WASP
National Category
Computer and Information Sciences Computer Vision and Robotics (Autonomous Systems)
Identifiers
URN: urn:nbn:se:liu:diva-138398DOI: 10.3384/lic.diva-138398ISBN: 978-91-7685-490-7 (print)OAI: oai:DiVA.org:liu-138398DiVA, id: diva2:1133724
Presentation
2017-09-15, Alan Turing, E-huset, Campus Valla, Linköping, 10:15 (English)
Opponent
Supervisors
Funder
ELLIIT - The Linköping‐Lund Initiative on IT and Mobile CommunicationsKnut and Alice Wallenberg FoundationSwedish Foundation for Strategic Research Available from: 2017-08-17 Created: 2017-08-16 Last updated: 2018-01-13Bibliographically approved
List of papers
1. Model-Based Reinforcement Learning in Continuous Environments Using Real-Time Constrained Optimization
Open this publication in new window or tab >>Model-Based Reinforcement Learning in Continuous Environments Using Real-Time Constrained Optimization
2015 (English)In: Proceedings of the Twenty-Ninth AAAI Conference on Artificial Intelligence (AAAI) / [ed] Blai Bonet and Sven Koenig, AAAI Press, 2015, p. 2497-2503Conference paper, Published paper (Refereed)
Abstract [en]

Reinforcement learning for robot control tasks in continuous environments is a challenging problem due to the dimensionality of the state and action spaces, time and resource costs for learning with a real robot as well as constraints imposed for its safe operation. In this paper we propose a model-based reinforcement learning approach for continuous environments with constraints. The approach combines model-based reinforcement learning with recent advances in approximate optimal control. This results in a bounded-rationality agent that makes decisions in real-time by efficiently solving a sequence of constrained optimization problems on learned sparse Gaussian process models. Such a combination has several advantages. No high-dimensional policy needs to be computed or stored while the learning problem often reduces to a set of lower-dimensional models of the dynamics. In addition, hard constraints can easily be included and objectives can also be changed in real-time to allow for multiple or dynamic tasks. The efficacy of the approach is demonstrated on both an extended cart pole domain and a challenging quadcopter navigation task using real data.

Place, publisher, year, edition, pages
AAAI Press, 2015
Keywords
Reinforcement Learning, Gaussian Processes, Optimization, Robotics
National Category
Computer Sciences Computer Vision and Robotics (Autonomous Systems)
Identifiers
urn:nbn:se:liu:diva-113385 (URN)978-1-57735-698-1 (ISBN)
Conference
Twenty-Ninth AAAI Conference on Artificial Intelligence (AAAI), January 25-30, 2015, Austin, Texas, USA.
Funder
Linnaeus research environment CADICSeLLIIT - The Linköping‐Lund Initiative on IT and Mobile CommunicationsSwedish Foundation for Strategic Research VINNOVAEU, FP7, Seventh Framework Programme
Available from: 2015-01-16 Created: 2015-01-16 Last updated: 2018-01-11Bibliographically approved
2. Model-Predictive Control with Stochastic Collision Avoidance using Bayesian Policy Optimization
Open this publication in new window or tab >>Model-Predictive Control with Stochastic Collision Avoidance using Bayesian Policy Optimization
2016 (English)In: IEEE International Conference on Robotics and Automation (ICRA), 2016, Institute of Electrical and Electronics Engineers (IEEE), 2016, p. 4597-4604Conference paper, Published paper (Refereed)
Abstract [en]

Robots are increasingly expected to move out of the controlled environment of research labs and into populated streets and workplaces. Collision avoidance in such cluttered and dynamic environments is of increasing importance as robots gain more autonomy. However, efficient avoidance is fundamentally difficult since computing safe trajectories may require considering both dynamics and uncertainty. While heuristics are often used in practice, we take a holistic stochastic trajectory optimization perspective that merges both collision avoidance and control. We examine dynamic obstacles moving without prior coordination, like pedestrians or vehicles. We find that common stochastic simplifications lead to poor approximations when obstacle behavior is difficult to predict. We instead compute efficient approximations by drawing upon techniques from machine learning. We propose to combine policy search with model-predictive control. This allows us to use recent fast constrained model-predictive control solvers, while gaining the stochastic properties of policy-based methods. We exploit recent advances in Bayesian optimization to efficiently solve the resulting probabilistically-constrained policy optimization problems. Finally, we present a real-time implementation of an obstacle avoiding controller for a quadcopter. We demonstrate the results in simulation as well as with real flight experiments.

Place, publisher, year, edition, pages
Institute of Electrical and Electronics Engineers (IEEE), 2016
Series
Proceedings of IEEE International Conference on Robotics and Automation, ISSN 1050-4729
Keywords
Robot Learning, Collision Avoidance, Robotics, Bayesian Optimization, Model Predictive Control
National Category
Robotics Computer Sciences
Identifiers
urn:nbn:se:liu:diva-126769 (URN)10.1109/ICRA.2016.7487661 (DOI)000389516203138 ()
Conference
IEEE International Conference on Robotics and Automation (ICRA), 2016, Stockholm, May 16-21
Projects
CADICSELLIITNFFP6CUASSHERPA
Funder
Linnaeus research environment CADICSELLIIT - The Linköping‐Lund Initiative on IT and Mobile CommunicationsEU, FP7, Seventh Framework ProgrammeSwedish Foundation for Strategic Research
Available from: 2016-04-04 Created: 2016-04-04 Last updated: 2018-01-10Bibliographically approved
3. Deep Learning Quadcopter Control via Risk-Aware Active Learning
Open this publication in new window or tab >>Deep Learning Quadcopter Control via Risk-Aware Active Learning
2017 (English)In: Proceedings of The Thirty-first AAAI Conference on Artificial Intelligence (AAAI) / [ed] Satinder Singh and Shaul Markovitch, AAAI Press, 2017, Vol. 5, p. 3812-3818Conference paper, Published paper (Refereed)
Abstract [en]

Modern optimization-based approaches to control increasingly allow automatic generation of complex behavior from only a model and an objective. Recent years has seen growing interest in fast solvers to also allow real-time operation on robots, but the computational cost of such trajectory optimization remains prohibitive for many applications. In this paper we examine a novel deep neural network approximation and validate it on a safe navigation problem with a real nano-quadcopter. As the risk of costly failures is a major concern with real robots, we propose a risk-aware resampling technique. Contrary to prior work this active learning approach is easy to use with existing solvers for trajectory optimization, as well as deep learning. We demonstrate the efficacy of the approach on a difficult collision avoidance problem with non-cooperative moving obstacles. Our findings indicate that the resulting neural network approximations are least 50 times faster than the trajectory optimizer while still satisfying the safety requirements. We demonstrate the potential of the approach by implementing a synthesized deep neural network policy on the nano-quadcopter microcontroller.

Place, publisher, year, edition, pages
AAAI Press, 2017
Series
Proceedings of the AAAI Conference on Artificial Intelligence, ISSN 2159-5399, E-ISSN 2374-3468 ; 5
National Category
Computer Vision and Robotics (Autonomous Systems) Computer Sciences
Identifiers
urn:nbn:se:liu:diva-132800 (URN)978-1-57735-784-1 (ISBN)
Conference
Thirty-First AAAI Conference on Artificial Intelligence (AAAI), 2017, San Francisco, February 4–9.
Projects
ELLIITCADICSNFFP6SYMBICLOUDCUGS
Funder
Linnaeus research environment CADICSELLIIT - The Linköping‐Lund Initiative on IT and Mobile CommunicationsEU, FP7, Seventh Framework ProgrammeCUGS (National Graduate School in Computer Science)Swedish Foundation for Strategic Research
Available from: 2016-11-25 Created: 2016-11-25 Last updated: 2018-01-13Bibliographically approved

Open Access in DiVA

fulltext(4444 kB)106 downloads
File information
File name FULLTEXT03.pdfFile size 4444 kBChecksum SHA-512
4baaf11ce2255edd918cab4f9bdf747ca34061b3303c9a32b4e5f6fb702e580be92eef63ef7e5ec59d472b8ec64561f131d78ca1a7721808c7458b271da4ade4
Type fulltextMimetype application/pdf
omslag(2701 kB)20 downloads
File information
File name COVER02.pdfFile size 2701 kBChecksum SHA-512
60dbc74e3dca50c3ac7e4afb89c4a2f82a72aa485d28687bfa77cff9d0096de829099888d57fd5ce8d29905dbb09f4ba62503f5894e23bcc18dcf820380d5692
Type coverMimetype application/pdf

Other links

Publisher's full text

Search in DiVA

By author/editor
Andersson, Olov
By organisation
Artificial Intelligence and Integrated Computer SystemsFaculty of Science & Engineering
Computer and Information SciencesComputer Vision and Robotics (Autonomous Systems)

Search outside of DiVA

GoogleGoogle Scholar
Total: 112 downloads
The number of downloads is the sum of all downloads of full texts. It may include eg previous versions that are now no longer available

doi
isbn
urn-nbn

Altmetric score

doi
isbn
urn-nbn
Total: 2454 hits
CiteExportLink to record
Permanent link

Direct link
Cite
Citation style
  • apa
  • harvard1
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • oxford
  • 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