Evo-ROS: integrating evolution and the robot operating system

ABSTRACT

In this paper, we describe the Evo-ROS framework, which is intended to help bridge the gap between the evolutionary and traditional robotics communities. Evo-ROS combines an evolutionary algorithm with individual physics-based evaluations conducted using the Robot Operating System (ROS) and the Gazebo simulation environment. Our goals in developing Evo-ROS are to (1) provide researchers in evolutionary robotics with access to the extensive support for real-world components and capabilities developed by the ROS community and (2) enable ROS developers, and more broadly robotics researchers, to take advantage of evolutionary search during design and testing. We describe the details of the Evo-ROS structure and operation, followed by presentation of a case study using Evo-ROS to optimize placement of sonar sensors on unmanned ground vehicles that can experience reduced sensing capability due to component failures and physical damage. The case study provides insights into the current capabilities and identifies areas for future enhancements.

References

1. ArduPilot. Developer website, http://ardupilot.org/about, 2018. Online; accessed 31 January 2018.
2. ArduPilot Dev Team. Auto Mode, http://ardupilot.org/copter/docs/auto-mode.html, 2016. Online; accessed 30 January 2018.
3. K. Balakrishnan and V. Honavar. On sensor evolution in robotics. In Proceedings of the 1st Annual Conference on Genetic Programming, pages 455--460, Stanford, California, 1996. MIT Press.
4. J. Bongard, V. Zykov, and H. Lipson. Resilient machines through continuous self-modeling. Science, 17, November 2006.
5. J. C Bongard, A. Bernatskiy, K. Livingston, N. Livingston, J. Long, and M. Smith. Evolving robot morphology facilitates the evolution of neural modularity and evolvability. In Proceedings of the 2015 Genetic and Evolutionary Computation Conference, pages 129--136, Madrid, Spain, 2015. ACM.
6. Buyval, Alex. Aurélien, Roy. Maxime, Lafleur. Ardupilot SITL Gazebo Plugin. https://github.com/AurelienRoy/ardupilot_sitl_gazebo_plugin/tree/master/ardupilot_sitl_gazebo_plugin, 2015. Online; accessed 31 January 2018.
7. A. J. Clark. Evolving Adabot: A mobile robot with adjustable wheel extensions. In 2017 IEEE Symposium Series on Computational Intelligence (SSCI), pages 1--8, Honolulu, HI, USA, 2017.
8. A. J. Clark, X. Tan, and P. K. McKinley. Evolutionary multiobjective design of a flexible caudal fin for robotic fish. Bioinspiration & Biomimetics, special issue on Bioinspired Soft Robotics, 10(6), November 2015.
9. A. Cully, J. Clune, and J. Mouret. Robots that can adapt like natural animals. ArXiv Preprint, 2014.
10. D. Duckworth, B. Shrewsbury, and R. Murphy. Run the robot backward. In 2013 IEEE International Symposium on Safety, Security, and Rescue Robotics (SSRR), pages 1--6. IEEE, 2013.
11. Erie Robotics. Erie-Rover, http://erlerobotics.com/blog/erle-rover/, 2018. Online; accessed 31 January 2018.
12. Erie Robotics. Simulation Introduction, http://docs.erlerobotics.com/simulation/intro, 2018. Online; accessed 31 January 2018.
13. D. Floreano, P. Husbands, and S. Nolfi. Evolutionary Robotics. In Handbook of Robotics. Springer Verlag, Berlin, 2008.
14. N. Koenig and A. Howard. Design and use paradigms for gazebo, an open-source multi-robot simulator, 04 2004.
15. S. Koos, J. B. Mouret, and S. Doncieux. Crossing the reality gap in evolutionary robotics by promoting transferable controllers. In Proceedings of the 2010 ACM Genetic and Evolutionary Computation Conference, pages 119--126, Portland, Oregon, USA, 2010. ACM.
16. H. Lipson and J. B. Pollack. Automatic design and manufacture of robotic lifeforms. Nature, 406(6799):974--978, August 2000.
17. J. M. Moore and P. K. McKinley. Evolution of joint-level control for quadrupedal locomotion. Artificial Life, 23(1):58--79, January 2017.
18. M. J. Rose, A. J. Clark, J. M. Moore, and P. K. McKinley. Just keep swimming: Accounting for uncertainty in self-modeling aquatic robots. In Proceedings of the 6th International Workshop on Evolutionary and Reinforcement Learning for Autonomous Robot Systems, Taormina, Italy, September 2013.
19. F. Silva, M. Duarte, L. Correia, S. M. Oliveira, and. A. L. Christensen. Open issues in evolutionary robotics. Evolutionary Computation, 24(2):205--236, 2016.
20. Tim Smith. About ROS. http://www.ros.Org/about-ros/t, 2018. Online; accessed 31 January 2018.
21. X. Wang, S. X. Yang, W. Shi, and M. Q. H. Meng. A co-evolution approach to sensor placement and control design for robot obstacle avoidance. In 2004 International Conference on Information Acquisition, pages 107--112, Hefei, China, 2004.
22. Y. Zhang and J. Jiang. Bibliographical review on reconfigurable fault-tolerant control systems. Annual reviews in control, 32(2):229--252, 2008.

Index Terms

• Computer systems organization

  • Embedded and cyber-physical systems

    • Robotics

      • Robotic control

        • Evolutionary robotics