research-article

Tradeoffs in Neuroevolutionary Learning-Based Real-Time Robotic Task Design in the Imprecise Computation Framework

Authors:

Chien-Liang Fok,

Aloysius K. Mok,

Risto MiikkulainenAuthors Info & Claims

ACM Transactions on Cyber-Physical Systems, Volume 3, Issue 2

Article No.: 14, Pages 1 - 29

https://doi.org/10.1145/3178903

Published: 10 October 2018 Publication History

Abstract

A cyberphysical avatar is a semi-autonomous robot that adjusts to an unstructured environment and performs physical tasks subject to critical timing constraints while under human supervision. This article first realizes a cyberphysical avatar that integrates three key technologies: body-compliant control, neuroevolution, and real-time constraints. Body-compliant control is essential for operator safety, because avatars perform cooperative tasks in close proximity to humans; neuroevolution (NEAT) enables “programming” avatars such that they can be used by non-experts for a large array of tasks, some unforeseen, in an unstructured environment; and real-time constraints are indispensable to provide predictable, bounded-time response in human-avatar interaction. Then, we present a study on the tradeoffs between three design parameters for robotic task systems that must incorporate at least three dimensions: (1) the amount of training effort for robot to perform the task, (2) the time available to complete the task when the command is given, and (3) the quality of the result of the performed task. A tradeoff study in this design space by using the imprecise computation as a framework is to perform a common robotic task, specifically, grasping of unknown objects. The results were validated with a real robot and contribute to the development of a systematic approach for designing robotic task systems that must function in environments like flexible manufacturing systems of the future.

References

[1]

Brenna D. Argall, Sonia Chernova, Manuela Veloso, and Brett Browning. 2009. A survey of robot learning from demonstration. Int. J. Robot. Auton. Syst. 57, 5 (2009), 469--483.

Digital Library

[2]

Martin Buss, Hideki Hashimoto, and John B. Moore. 1996. Dextrous hand grasping force optimization. IEEE Trans. Robot. Autom. 12, 3 (1996), 406--418.

[3]

Columbia University Robotics Groups. 2017. GraspIt&excl; Simulator. Retrieved from http://graspit-simulator.github.io/#.

[4]

Carlo Ferrari and John Canny. 1992. Planning optimal grasps. In Proceedings of the IEEE International Conference on Robotics and Automation, Vol. 3. 2290--2295.

[5]

Song Han, Aloysius K. Mok, Jianyong Meng, Yi-Hung Wei, Pei-Chi Huang, Quan Leng, Xiuming Zhu, Luis Sentis, Kwan Suk Kim, and Risto Miikkulainen. 2013. Architecture of a cyberphysical avatar. In Proceedings of the ACM/IEEE 4th International Conference on Cyber-Physical Systems. 189--198.

Digital Library

[6]

Simon S. Haykin. 2009. Neural Networks and Learning Machines (3 ed.). Prentice Hall, Upper Saddle River, NJ.

[7]

Kaijen Hsiao, Leslie Pack Kaelbling, and Tomás Lozano-Pérez. 2007. Grasping POMDPs. In Proceedings of the IEEE International Conference on Robotics and Automation. 4685--4692.

[8]

Kaijen Hsiao and Tomás Lozano-Pérez. 2006. Imitation learning of whole-body grasps. In Proceedings of the IEEE/RSJ International Conference on Intelligent Robots and Systems. 5657--5662.

[9]

Pei-Chi Huang, Joel Lehman, Aloysius K Mok, Risto Miikkulainen, and Luis Sentis. 2014. Grasping novel objects with a dexterous robotic hand through neuroevolution. In Proceedings of the 2014 IEEE Symposium on Computational Intelligence in Control and Automation. 1--8.

[10]

Pei-Chi Huang, Luis Sentis, Joel Lehman, Chien-Liang Fok, Aloysius K. Mok, and Risto Miikkulainen. 2015. Tradeoffs in real-time robotic task design with neuroevolution learning for imprecise computation. In Proceedings of the Real-Time Systems Symposium. IEEE, 206--215.

Digital Library

[11]

Pei-Chi Huang, Luis Sentis, Joel Lehman, Chien-Liang Fok, Aloysius K. Mok, and Risto Miikkulainen. 2017. Tradeoffs in Neuroevolutionary Learning-Based Real-Time Robotic Task Design in the Imprecise Computation Framework. Technical Report. Department of Computer Science, The University of Texas at Austin. Retrieved from https://www.cs.utexas.edu/ peggy/techReport201701.pdf.

[12]

Joshua M. Inouye and Francisco J. Valero-Cuevas. 2014. Anthropomorphic tendon-driven robotic hands can exceed human grasping capabilities following optimization. Int. J. Robot. Res. 33, 5 (2014), 694--705.

Digital Library

[13]

Nick Jakobi. 1998. Minimal Simulations for Evolutionary Robotics. Ph.D. Dissertation. University of Sussex, School of Cognitive and Computing Sciences.

[14]

David Kirkpatrick, Bhubaneswar Mishra, and Chee-Keng Yap. 1992. Quantitative steinitz’s theorems with applications to multifingered grasping. Discr. Comput. Geom. 7, 3 (1992), 295--318.

Digital Library

[15]

Jens Kober, J. Andrew Bagnell, and Jan Peters. 2013. Reinforcement learning in robotics: A survey. Int. J. Robot. Res. 32, 11 (Jul. 2013), 1238--1274.

Digital Library

[16]

Nate Kohl, Kenneth Stanley, Risto Miikkulainen, and Rini Sherony. 2006. Evolving a real-world vehicle warning system. In Proceedings of the Genetic and Evolutionary Computation Conference. 1681--1688.

Digital Library

[17]

Quoc V. Le, David Kamm, Arda F. Kara, and Andrew Y. Ng. 2010. Learning to grasp objects with multiple contact points. In Proceedings of the IEEE International Conference on Robotics and Automation. 5062--5069.

[18]

Yann LeCun, Yoshua Bengio, and Geoffrey Hinton. 2015. Deep learning. Nature 521, 7553 (2015), 436--444.

[19]

Joel Lehman and Risto Miikkulainen. 2014. Overcoming deception in evolution of cognitive behaviors. In Proceedings of the 2014 Annual Conference on Genetic and Evolutionary Computation. ACM, 185--192.

Digital Library

[20]

Joel Lehman and Kenneth O. Stanley. 2011. Abandoning objectives: Evolution through the search for novelty alone. Evol. Comput. 19, 2 (2011), 189--223.

Digital Library

[21]

Hod Lipson, Josh C. Bongard, Victor Zykov, and Evan Malone. 2006. Evolutionary robotics for legged machines: From simulation to physical reality. In Proceedings of the 9th International Conference on Intelligent Autonomous Systems. 11--18.

[22]

Guanfeng Liu, Jijie Xu, and Zexiang Li. 2004. On geometric algorithms for real-time grasping force optimization. IEEE Trans. Contr. Syst. Technol. 12, 6 (2004), 843--859.

[23]

Jane W.-S. Liu, Kwei-Jay Lin, C. L. Liu, and C. W. Gear. 1992. Imprecise computations. Mission Critical Operating Systems. IOS Press, 159--169.

[24]

Jane W.-S. Liu, Wei-Kuan Shih, Kwei-Jay Lin, Riccardo Bettati, and Jen-Yao Chung. 1994. Imprecise computations. In Proceedings of the IEEE 82, 1 (Jan. 1994), 83--94.

[25]

Yun-Hui Liu. 1999. Qualitative test and force optimization of 3-D frictional form-closure grasps using linear programming. IEEE Trans. Robot. Autom. 15, 1 (1999), 163--173.

[26]

Andrew T. Miller and Peter K. Allen. 1999. Examples of 3D grasp quality computations. In Proceedings of the IEEE International Conference on Robotics and Automation, Vol. 8. 1240--1246.

[27]

Andrew T. Miller and Peter K. Allen. 2004. GraspIt&excl;: A versatile simulator for robotic grasping. IEEE Robot. Autom. Mag. 11, 4 (Dec. 2004), 110--122.

[28]

Andrew T. Miller, Steffen Knoop, Henrik I. Christensen, and Peter K. Allen. 2003. Automatic grasp planning using shape primitives. In Proceedings of the IEEE International Conference on Robotics and Automation. 1824--1829.

[29]

Javier Molina-Vilaplana, J. Feliu-Batlle, and J. López-Coronado. 2007. A modular neural network architecture for step-wise learning of grasping tasks. Int. J. Neur. Netw. 20, 5 (2007), 631--645.

Digital Library

[30]

Saigopal Nelaturi, Arvind Rangarajan, Christian Fritz, and Tolga Kurtoglu. 2014. Automated fixture configuration for rapid manufacturing planning. Comput.-Aid. Des. 46, 1 (2014), 160--169.

Digital Library

[31]

Leonardo M. Pedro, Valdinei L. Belini, and Glauco A. P. Caurin. 2013. Learning how to grasp based on neural network retraining. Adv. Robot. 27, 10 (2013), 785--797.

[32]

Raphael Pelossof, Andrew T. Miller, Peter K. Allen, and Tony Jebara. 2004. An SVM learning approach to robotic grasping. In Proceedings of the IEEE International Conference on Robotics and Automation. 3512--3518.

[33]

Deepak Rao, Quoc V. Le, Thanathorn Phoka, Morgan Quigley, Attawith Sudsang, and Andrew Y. Ng. 2010. Grasping novel objects with depth segmentation. In Proceedings of the IEEE/RSJ International Conference on Intelligent Robots and Systems. 2578--2585.

[34]

Nasser Rezzoug and Philippe Gorce. 2006. Robotic Grasping: A Generic Neural Network Architecture. Mobile Robots Towards New Applications. Pro Literatur Verlag Robert MayerScholz, Berlin, Germany.

[35]

Sebastian Risi, Charles E. Hughes, and Kenneth O. Stanley. 2010. Evolving plastic neural networks with novelty search. Adapt. Behav. 18, 6 (2010), 470--491.

Digital Library

[36]

Máximo A. Roa and Raúl Suárez. 2015. Grasp quality measures: Review and performance. Auton. Robots 38, 1 (2015), 65--88.

Digital Library

[37]

Ashutosh Saxena. 2009. Monocular Depth Perception and Robotic Grasping of Novel Objects. Ph.D. Dissertation. Stanford University.

Digital Library

[38]

Ashutosh Saxena, Justin Driemeyer, and Andrew Y. Ng. 2008. Robotic grasping of novel objects using vision. Int. J. Robot. Res. 27, 2 (2008), 157--173.

Digital Library

[39]

Luis Sentis, Jaeheung Park, and Oussama Khatib. 2010. Compliant control of multi-contact and center of mass behaviors in humanoid robots. IEEE Trans. Robot. 26, 3 (Jun. 2010), 483--501.

Digital Library

[40]

Luis Sentis, Josh Petersen, and Roland Philippsen. 2013. Implementation and stability analysis of prioritized whole-body compliant controllers on a wheeled humanoid robot in uneven terrains. Auton Robot 35, 4 (Nov. 2013), 301--319.

Digital Library

[41]

Karun B. Shimoga. 1996. Robot grasp synthesis algorithms: A survey. Int. J. Robot. Res. 15, 3 (1996), 230--266.

Digital Library

[42]

David Silver, Aja Huang, Chris J. Maddison, Arthur Guez, Laurent Sifre, George Van Den Driessche, Julian Schrittwieser, Ioannis Antonoglou, Veda Panneershelvam, Marc Lanctot, et al. 2016. Mastering the game of go with deep neural networks and tree search. Nature 529, 7587 (2016), 484--489.

[43]

Avishai Sintov and Amir Shapiro. 2017. An analysis of grasp quality measures for the application of sheet metal parts grasping. Auton. Robots 41, 1 (2017), 145--161.

Digital Library

[44]

Kenneth O. Stanley and Risto Miikkulainen. 2002. Evolving neural networks through augmenting topologies. Evol. Comput. 10, 2 (2002), 99--127.

Digital Library

[45]

Kenneth O. Stanley and Risto Miikkulainen. 2004. Competitive coevolution through evolutionary complexification. Int. J. Artif. Intell. Res. 21 (2004), 63--100.

Digital Library

[46]

Marek Teichmann and Bud Mishra. 1997. The power of friction: Quantifying the “goodness” of frictional grasps. Algorithms for Robotic Motion and Manipulation. 311--320.

[47]

Jianwei Zhang and Bernd Rössler. 2004. Self-valuing learning and generalization with application in visually guided grasping of complex objects. Robot. Auton. Syst. 47, 2 (2004), 117--127.

Cited By

Colombathanthri AJomaa WChinniah Y(2025)Human-centered cyber-physical systems in manufacturing industry: a systematic search and reviewThe International Journal of Advanced Manufacturing Technology10.1007/s00170-024-14959-w136:5-6(2107-2141)Online publication date: 15-Jan-2025
https://doi.org/10.1007/s00170-024-14959-w
Vitiuk ADoroshenko A(2023)Novelty search in neuroevolution for end effector positioningPROBLEMS IN PROGRAMMING10.15407/pp2023.03.049(49-57)Online publication date: Sep-2023
https://doi.org/10.15407/pp2023.03.049
A VA D(2023)Use of neuroevolution for neural network policies search for robotic armArtificial Intelligence10.15407/jai2023.02.05628:AI.2023.28(2))(56-64)Online publication date: 15-Sep-2023
https://doi.org/10.15407/jai2023.02.056
Show More Cited By

Index Terms

Tradeoffs in Neuroevolutionary Learning-Based Real-Time Robotic Task Design in the Imprecise Computation Framework
1. Computer systems organization
  1. Embedded and cyber-physical systems
    1. Robotics
2. Computing methodologies
  1. Machine learning
    1. Machine learning approaches
      1. Bio-inspired approaches
        Evolutionary robotics

Recommendations

Tradeoffs in Real-Time Robotic Task Design with Neuroevolution Learning for Imprecise Computation
RTSS '15: Proceedings of the 2015 IEEE Real-Time Systems Symposium (RTSS)

We present a study on the tradeoffs between three design parameters for robotic task systems that function in partially unknown and unstructured environments, and under timing constraints. The design space of these robotic tasks must incorporate at ...
Real-Time Performance Evaluation for Robotics: An Approach using the Robotstone Benchmark
Abstract
This paper discusses a novel approach to evaluate the real-time performance of computing platforms embedded in robotic systems. The motivation behind this work is the need for the robotic systems to meet their timing constraints, thus requiring ...
A Real-Time Reconfigurable Collision Avoidance System for Robot Manipulation
ICMRE 2017: Proceedings of the 3rd International Conference on Mechatronics and Robotics Engineering

Intelligent robotic systems are becoming fundamental actors in industrial and hazardous facilities scenarios. Aiming to increase personnel safety and machine availability, robots can help perform repetitive and dangerous tasks which humans either prefer ...

Comments

Please enable JavaScript to view thecomments powered by Disqus.

Information & Contributors

Information

Published In

cover image ACM Transactions on Cyber-Physical Systems

ACM Transactions on Cyber-Physical Systems Volume 3, Issue 2

April 2019

283 pages

ISSN:2378-962X

EISSN:2378-9638

DOI:10.1145/3284746

Editor:
Tei-Wei Kuo
National Taiwan University, and Academia Sinica, Taiwan

Issue’s Table of Contents

Copyright © 2018 ACM.

Permission to make digital or hard copies of all or part of this work for personal or classroom use is granted without fee provided that copies are not made or distributed for profit or commercial advantage and that copies bear this notice and the full citation on the first page. Copyrights for components of this work owned by others than the author(s) must be honored. Abstracting with credit is permitted. To copy otherwise, or republish, to post on servers or to redistribute to lists, requires prior specific permission and/or a fee. Request permissions from [email protected].

Publisher

Association for Computing Machinery

New York, NY, United States

Journal Family

ACM Journals for the Design of Smart and Connected Systems

Publication History

Published: 10 October 2018

Accepted: 01 January 2018

Revised: 01 January 2018

Received: 01 February 2017

Published in TCPS Volume 3, Issue 2

Permissions

Request permissions for this article.

Request Permissions

Check for updates

Author Tags

Qualifiers

Research-article
Research
Refereed

Contributors

Other Metrics

View Article Metrics

Bibliometrics & Citations

Bibliometrics

Article Metrics

7
Total Citations
View Citations
289
Total Downloads

Downloads (Last 12 months)13
Downloads (Last 6 weeks)1

Reflects downloads up to 14 Feb 2025

Other Metrics

View Author Metrics

Citations

Cited By

Colombathanthri AJomaa WChinniah Y(2025)Human-centered cyber-physical systems in manufacturing industry: a systematic search and reviewThe International Journal of Advanced Manufacturing Technology10.1007/s00170-024-14959-w136:5-6(2107-2141)Online publication date: 15-Jan-2025
https://doi.org/10.1007/s00170-024-14959-w
Vitiuk ADoroshenko A(2023)Novelty search in neuroevolution for end effector positioningPROBLEMS IN PROGRAMMING10.15407/pp2023.03.049(49-57)Online publication date: Sep-2023
https://doi.org/10.15407/pp2023.03.049
A VA D(2023)Use of neuroevolution for neural network policies search for robotic armArtificial Intelligence10.15407/jai2023.02.05628:AI.2023.28(2))(56-64)Online publication date: 15-Sep-2023
https://doi.org/10.15407/jai2023.02.056
Napoleone ANegri EMacchi MPozzetti A(2022)How the technologies underlying cyber-physical systems support the reconfigurability capability in manufacturing: a literature reviewInternational Journal of Production Research10.1080/00207543.2022.207432361:9(3122-3144)Online publication date: 18-May-2022
https://doi.org/10.1080/00207543.2022.2074323
Ma YXie Y(2022)Evolutionary neural networks for deep learning: a reviewInternational Journal of Machine Learning and Cybernetics10.1007/s13042-022-01578-813:10(3001-3018)Online publication date: 10-Jun-2022
https://doi.org/10.1007/s13042-022-01578-8
Lankin RKim KHuang P(2020)ROS-Based Robot Simulation for Repetitive Labor-Intensive Construction Tasks2020 IEEE 18th International Conference on Industrial Informatics (INDIN)10.1109/INDIN45582.2020.9442192(206-213)Online publication date: 20-Jul-2020
https://doi.org/10.1109/INDIN45582.2020.9442192
Hsieh YHuang PHuang QMok A(2019)LASSO: Location Assistant for Seeking and Searching Objects2019 IEEE International Conference on Industrial Cyber Physical Systems (ICPS)10.1109/ICPHYS.2019.8780249(94-100)Online publication date: May-2019
https://doi.org/10.1109/ICPHYS.2019.8780249

View Options

Login options

Check if you have access through your login credentials or your institution to get full access on this article.

Full Access

Get this Article

View options

PDF

View or Download as a PDF file.

eReader

View online with eReader.

HTML Format

View this article in HTML Format.

Figures

Tables

Media

View Issue’s Table of Contents