6,694 Hits in 5.3 sec

Combining Planning and Learning of Behavior Trees for Robotic Assembly [article]

Jonathan Styrud, Matteo Iovino, Mikael Norrlöf, Mårten Björkman, Christian Smith
2021 arXiv   pre-print
Experimental results confirm that the proposed method of combining planning and learning performs well on a variety of robotic assembly problems and outperforms both of the base methods used separately  ...  We propose a method for generating Behavior Trees using a Genetic Programming algorithm and combining the two branches by taking the result of an automated planner and inserting it into the population.  ...  Our contributions are a proposed method to combine planning and learning and showing that this enables learning of behavior trees to be done more efficiently for a variety of robotic assembly problems.  ... 
arXiv:2103.09036v1 fatcat:rxefqhrfkrd6phuunomgxa6bgq

Lessons Learned Developing an Assembly System for WRS 2020 Assembly Challenge [article]

Aayush Naik, Priyam Parashar, Jiaming Hu, Henrik I. Christensen
2021 arXiv   pre-print
We present our approach to assembly based on integration of machine vision, robust planning and execution using behavior trees and a hierarchy of recovery strategies to ensure robust operation.  ...  The World Robot Summit (WRS) 2020 Assembly Challenge is designed to allow teams to demonstrate how one can build flexible, robust systems for assembly of machined objects.  ...  ACKNOWLEDGMENT The authors would like to thank Nahid Sidki, Omar Aldughayem, and Hussam Alzahrani from RPD Innovations. We would also like to thank Jack Griffin for his help with the finger designs.  ... 
arXiv:2103.15236v1 fatcat:rw6i3vl7wbgspmdgvgmymjefbe

Interactive, Collaborative Robots: Challenges and Opportunities

Danica Kragic, Joakim Gustafson, Hakan Karaoguz, Patric Jensfelt, Robert Krug
2018 Proceedings of the Twenty-Seventh International Joint Conference on Artificial Intelligence  
Full robot autonomy, including natural interaction, learning from and with human, safe and flexible performance for challenging tasks in unstructured environments will remain out of reach for the foreseeable  ...  The challenge of developing flexible solutions where production lines can be quickly re-planned, adapted and structured for new or slightly changed products is still an important open problem.  ...  Acknowledgements This work was supported by the Swedish Foundation for Strategic Research (SSF) and Knut and Alice Wallenberg Foundation through the WASP project.  ... 
doi:10.24963/ijcai.2018/3 dblp:conf/ijcai/KragicGKJ018 fatcat:xhg22csfwbbifausf3o5xsoh24

Learning of Parameters in Behavior Trees for Movement Skills [article]

Matthias Mayr, Konstantinos Chatzilygeroudis, Faseeh Ahmad, Luigi Nardi, Volker Krueger
2021 arXiv   pre-print
Behavior Trees (BTs), on the other hand, can provide a policy representation that a) supports modular and composable skills, b) allows for easy interpretation of the robot actions, and c) provides an advantageous  ...  Reinforcement Learning (RL) is a powerful mathematical framework that allows robots to learn complex skills by trial-and-error.  ...  We want to thank Francesco Rovida, Bjarne Großmann, Alexander Dürr, Björn Olofsson and Julian Salt for the interesting discussions and the constructive feedback.  ... 
arXiv:2109.13050v1 fatcat:s5gt673dqzh6lldp4kcwntfq2u

Integration and learning in supervision of flexible assembly systems

L.M. Camarinha-Matos, L.S. Lopes, J. Barata
1996 IEEE Transactions on Robotics and Automation  
Absrhzct-A generic architecture for evolutive supervision of robotized assembly tasks, in a context of integrated manufacturing systems, is presented.  ...  Through the use of machine learning techniques, the supervision architecture will be given capabilities for improving its performance over time.  ...  Silva for his contribution to the experimental setup.  ... 
doi:10.1109/70.488941 fatcat:tdpobkvkwje4bkixtfjpgwt35i

Evaluating Methods for End-User Creation of Robot Task Plans [article]

Chris Paxton, Felix Jonathan, Andrew Hundt, Bilge Mutlu, Gregory D. Hager
2018 arXiv   pre-print
We conducted a 35-person user study with the Behavior Tree-based CoSTAR system to determine which strategies for end user creation of generalizable robot task plans are most usable and effective.  ...  How can we enable users to create effective, perception-driven task plans for collaborative robots?  ...  THE COSTAR SYSTEM CoSTAR is a Behavior Tree-based user interface that aims to facilitate user interaction through a combination of an intuitive user interface, robust perception, and integrated planning  ... 
arXiv:1811.02690v1 fatcat:dhwee4dhk5hhnfguhievvu7tzi

Constructing policies for supportive behaviors and communicative actions in human-robot teaming

Elena Corina Grigore, Brian Scassellati
2016 2016 11th ACM/IEEE International Conference on Human-Robot Interaction (HRI)  
For the robot to provide assistive behavior to a human co-worker, it needs to learn what actions it should perform at each time step depending upon the state of the task.  ...  Current state-of-the-art robotic systems deployed in industry work in isolation from humans and do not allow for collaboration.  ...  In the human-robot interaction field, work that focuses on human-robot teaming includes research in the area of search and rescue [5] , team coordination behaviors and action planning for human-robot  ... 
doi:10.1109/hri.2016.7451883 dblp:conf/hri/GrigoreS16 fatcat:pzoza7vdrbcurkz4s6rdzho3xa

CoSTAR: Instructing Collaborative Robots with Behavior Trees and Vision [article]

Chris Paxton, Andrew Hundt, Felix Jonathan, Kelleher Guerin, and Gregory D. Hager
2016 arXiv   pre-print
Our Behavior Tree-based task editor integrates high-level information from known object segmentation and pose estimation with spatial reasoning and robot actions to create robust task plans.  ...  We describe the cross-platform design and implementation of this system on multiple industrial robots and evaluate its suitability for a wide variety of use cases.  ...  These characteristics make Behavior Trees ideal for representing collaborative robot task plans [2] .  ... 
arXiv:1611.06145v1 fatcat:tiwqkqwwwzegvmsplcrz2mtwtm

Envisioning cognitive robots for future space exploration

Terry Huntsberger, Adrian Stoica, Jerome J. Braun
2010 Multisensor, Multisource Information Fusion: Architectures, Algorithms, and Applications 2010  
CASPER, CAMPOUT) and a description of the architecture CARACaS (Control Architecture for Robotic Agent Command and Sensing) that combines these in the context of a cognitive robotic system operating in  ...  Cognitive robots in the context of space exploration are envisioned with advanced capabilities of model building, continuous planning/re-planning, self-diagnosis, as well as the ability to exhibit a level  ...  We would also like to thank members of the Mobility and Robotic Systems Section at JPL for their support in the development of CARACaS.  ... 
doi:10.1117/12.853284 fatcat:2gilxe5xovho7neogtsru3sm7u

A Survey on AI-Driven Digital Twins in Industry 4.0: Smart Manufacturing and Advanced Robotics

Ziqi Huang, Yang Shen, Jiayi Li, Marcel Fey, Christian Brecher
2021 Sensors  
in the fields of smart manufacturing and advanced robotics.  ...  Digital twin (DT) and artificial intelligence (AI) technologies have grown rapidly in recent years and are considered by both academia and industry to be key enablers for Industry 4.0.  ...  Planning (Section 3.3) Reinforcement Learning Proximal policy optimization Pick-and-place tasks for an industrial robotic arm [265] DDPG Control and trajectory planning of a planar 3- DOF  ... 
doi:10.3390/s21196340 pmid:34640660 fatcat:qy3qiazvqrejvfuixudd6ywqsq

User Experience of the CoSTAR System for Instruction of Collaborative Robots [article]

Chris Paxton, Felix Jonathan, Andrew Hundt, Bilge Mutlu, Gregory D. Hager
2017 arXiv   pre-print
How can we enable novice users to create effective task plans for collaborative robots? Must there be a tradeoff between generalizability and ease of use?  ...  Our study shows that users found Behavior Trees to be an effective way of specifying task plans.  ...  We generally expose operations to users as Behavior Tree leaf nodes, which can be parameterized and combined into a task plan capable of solving a wide range of problems.  ... 
arXiv:1703.07890v1 fatcat:ahkdc3jdb5horkdoxi5os5oi5u


Lei WANG, Yajie Tian, Tetsuo Sawaragi
2008 IFAC Proceedings Volumes  
The system improves the operating capability of the robot manipulator through observing, analyzing the skilled worker's assembling operation, and learning the assembling technique, that is, the tacit knowledge  ...  This paper describes a robot manipulator system currently under development which learns assembling technique from observation of skilled worker's demonstrations.  ...  However, other than the ARMS system that learns the physical realization and assembly plan to fulfill a mechanical behavior, our system is engaged in analyzing the assembly knowledge hidden in the skilled  ... 
doi:10.3182/20080706-5-kr-1001.00407 fatcat:vmug42w4rrgzjijeuyyrq2miqm

A Survey of Behavior Trees in Robotics and AI [article]

Matteo Iovino, Edvards Scukins, Jonathan Styrud, Petter Ögren, Christian Smith
2020 arXiv   pre-print
Behavior Trees (BTs) were invented as a tool to enable modular AI in computer games, but have received an increasing amount of attention in the robotics community in the last decade.  ...  In this paper we present a comprehensive survey of the topic of BTs in Artificial Intelligence and Robotic applications.  ...  Acknowledgments This work was partially supported by the Swedish Foundation for Strategic Research, Vinnova NFFP7 (grant no. 2017-04875) and by the Wallenberg AI, Autonomous Systems, and Software Program  ... 
arXiv:2005.05842v2 fatcat:sgtxsbtyczf7fagxsbtmjmusy4

Combining Task and Motion Planning: Challenges and Guidelines

Masoumeh Mansouri, Federico Pecora, Peter Schüller
2021 Frontiers in Robotics and AI  
Combined Task and Motion Planning (TAMP) is an area where no one-fits-all solution can exist.  ...  By doing so, this article aims to provide a guideline for designing combined TAMP solutions that are adequate and effective in the target scenario.  ...  AUTHOR CONTRIBUTIONS MM coordinated the research and the writing of the manuscript.  ... 
doi:10.3389/frobt.2021.637888 pmid:34095239 pmcid:PMC8170405 fatcat:4dmykcbhezbktfjzafv7t7wjfa

Digital Twin-Driven Control Method for Robotic Automatic Assembly System

Shaohua Meng, Shaolin Tang, Yahong Zhu, Changyu Chen
2019 IOP Conference Series: Materials Science and Engineering  
In order to improve the intelligent level of the robotic assembly system, a digital twin model is established to control the robot for automatic assembly of largescale spacecraft components.  ...  Then the behavior model is built based on the robot kinematics so that the state of the virtual simulation model can be consistent with the real robot.  ...  Behavior model In order to simulate the behavior of the robot in assembly process, kinematics is used for modelling.  ... 
doi:10.1088/1757-899x/493/1/012128 fatcat:z7h6liywpnd4veoukj25xlgeiu
« Previous Showing results 1 — 15 out of 6,694 results