designing robot collectives
play

Designing Robot Collectives by Kirstin Petersen July 2017 - PowerPoint PPT Presentation

Designing Robot Collectives by Kirstin Petersen July 2017 Collective Embodied Intelligence Lab Collective Embodied Motivatio ion Intelligence Lab Distance to Mars: 34-250M miles Jan anuary 200 2004 Travel time: 39-289 days Cost: $1B


  1. Designing Robot Collectives by Kirstin Petersen July 2017 Collective Embodied Intelligence Lab

  2. Collective Embodied Motivatio ion Intelligence Lab Distance to Mars: 34-250M miles Jan anuary 200 2004 Travel time: 39-289 days Cost: $1B April 2 2009

  3. Collective Embodied Desi signing R Robot C Colle lectiv ives Intelligence Lab Instead o of s sending o one, w we could s send c collectives! s! • Robustness • Efficiency • Capability

  4. Collective Embodied Robot C Collect ectives es Intelligence Lab Success S Stori ries! Still challenging …to operate collectives …to make capable, expendable robots …to coordinate collectives Amazon Robotics, automated warehouses 1000 103 drones in flight Kilobots, Dr. Timothy Chung, DARPA Harvard, 2014

  5. Collective Embodied Desi signing R Robot C Colle lectiv ives Intelligence Lab Control ol Autonomy/ (Remote Controlled) Taskability Scalable (Exact number) HOLLISTIC DESIGN APPROACH Error Tolerance SOFTWARE Hardware HARDWARE ENVIRONMENT (Stationary) Capability RELIABILITY ERROR TOLERANCE Cost Maintenance

  6. Collective Embodied Desi signing R Robot C Colle lectiv ives Intelligence Lab Swarm Support Systems Coordination in Nature Collective Construction Natural Soft Mechanisms Robots

  7. Collective Embodied Desi signing R Robot C Colle lectiv ives Intelligence Lab Swarm Support Systems Coordination in Nature Collective Construction Natural Soft Mechanisms Robots

  8. Collective Embodied Macr croter ermes esStudies Intelligence Lab …with Dr. Paul Bardunias, Dr. Justin Werfel, Prof. Radhika Nagpal, Prof. Nils Napp, Prof. Scott Turner • Decentralized • Parallelism • Simple agents • Simple environment • Error tolerant • Guaranteed high- level outcome

  9. Collective Embodied Te Termite-Inspired Intelligence Lab Collecti tive C Constr tructi tion …with Dr. Justin Werfel and Prof. Radhika Nagpal, Harvard • Decentralized • Parallelism • Simple agents • Simple environment • Error tolerant • Guaranteed high- level outcome

  10. Collective Embodied TERMES A Algori rithms Intelligence Lab …with Dr. Justin Werfel and Prof. Radhika Nagpal, Harvard +internal rule set • No gaps • No cliffs user input (blueprint) Arbitrary number of robots Off-line compiler step generates traffic patterns compiler output decentralized construction Werfel, J, K Petersen , & R Nagpal. 2011. Distributed Multi-Robot Algorithms for the TERMES 3D Collective Construction System. Workshop, Intl. Conference on Robots and Systems (IROS).

  11. Collective Embodied TERME MES I Implementation Intelligence Lab …with Dr. Justin Werfel and Prof. Radhika Nagpal, Harvard Locomotion Co Co-Des esign & Erro ror T r Tolera rance Coordination Navigation Control Manipulation Fabrication 10cm Petersen, Kirstin, Radhika Nagpal, and Justin Werfel. "Termes: An autonomous robotic system for three- dimensional collective construction." Proc. Robotics: Science & Systems VII (2011).

  12. Collective Embodied TERMES L S Loco comotion Intelligence Lab …with Dr. Justin Werfel and Prof. Radhika Nagpal, Harvard

  13. Collective Embodied TERME MES N Navig igatio ion Intelligence Lab …with Dr. Justin Werfel and Prof. Radhika Nagpal, Harvard • 3 actuators • Infrared (pattern recognitioning) • Accelerometer (climbing) • Tactile sensing (brick manipulation) • Ultrasound (wall following/avoidance) • Control by simple FSM

  14. Collective Embodied TE TERMES S Summary Intelligence Lab …with Dr. Justin Werfel and Prof. Radhika Nagpal, Harvard Minimalist solution through embodied intelligence and error tolerant control Werfel, J, K Petersen, & R Nagpal. 2014. Designing collective behavior in a termite-inspired robot construction team. Science 343(6172):754-758 (2014).

  15. Collective Embodied Desi signing R Robot C Colle lectiv ives Intelligence Lab Andreen, D, P. Jenning, N. Napp, and K. Petersen. 2016. Emergent Structures Control ol Assembled by Large Swarms of Simple Robots. ACADIA // 2016, pp. 54-61. Autonomy/ (Remote Controlled) Taskability Scalable (Exact number) Error Tolerance Hardware (Stationary) Capability Cost Maintenance

  16. Collective Embodied Desi signing R Robot C Colle lectiv ives Intelligence Lab Spröwitz, A., Göttler, C., Sinha, A., Caer, C., Oztekin, M. U., Petersen, K., & Control ol Sitti, M. Scalable Pneumatic and Tendon Driven Robotic Joint Inspired by Jumping Spiders. ICRA 2017. Autonomy/ (Remote Controlled) Taskability Scalable (Exact number) Error Tolerance Hardware (Stationary) Capability Cost Maintenance

  17. Collective Embodied Desi signing R Robot C Colle lectiv ives Intelligence Lab Swarm Support Systems Coordination in Nature Collective Construction Natural Soft Mechanisms Robots

  18. Collective Embodied Soft t Robot C Collect ectives es Intelligence Lab • Operation in unstructured terrain • Resilient • Inexpensive • Compliant and safe D. discoideum (slime mold) Bonner, Princeton, 1984

  19. Collective Embodied Soft t Robot C Collect ectives es Intelligence Lab Compact, simple, soft actuator with large, stable, and repeatable shape changes. Dielectric Elastomer Actuators Compliant electrode OF F Elastomer F DEA ON Hines*, L, Petersen*, K. and Sitti, M. (2016) Inflated Soft Actuators with Reversible Stable Deformations. Advanced Materials , 28(19), 3690-3696. - "Asymmetric Stable Deformations in Inflated Dielectric Elastomer Hyperelastic Materials Actuators.“ Intl. Conf. of Robotics and Automation, 2017. Pressure ∆ V STABLE STATES Volume

  20. Collective Embodied Desi signing R Robot C Colle lectiv ives Intelligence Lab Control ol Autonomy/ (Remote Controlled) Taskability Scalable (Exact number) Error Tolerance Hardware (Stationary) Capability Cost Maintenance *Guestimates!

  21. Collective Embodied Intelligence Lab Daniel Kim, Ryan O’Hern, Claire Chen, Kirstin Petersen, Vaidehi Patel, Yanir Nulman, Aasta Gandhi, Asena Ulug, Yejing Wang, Tim Duggan, Owen Hua, Yawen Deng, Mateo Espinoza, and Lawrence Chen

Download Presentation
Download Policy: The content available on the website is offered to you 'AS IS' for your personal information and use only. It cannot be commercialized, licensed, or distributed on other websites without prior consent from the author. To download a presentation, simply click this link. If you encounter any difficulties during the download process, it's possible that the publisher has removed the file from their server.

Recommend


More recommend