Nature Machine Intelligence - March 2019
A tendon-driven robotic limb learns movements autonomously from sparse experience, by a short period of ‘motor babbling’ (that is, repeated exploratory movements), followed by a phase of reinforcement learning. In this video, the limb is learning to make cyclic movements to propel the treadmill. The approach is a step towards designing robots with the versatility and robustness of vertebrates, which can adapt quickly to everyday environments.
Marjaninejad, Ali, et al. “Autonomous functional movements in a tendon-driven limb via limited experience.” Nature Machine Intelligence 1.3 (2019): 144.
Research reported in this publication was supported in part by the National Institute of Arthritis and Musculoskeletal and Skin Diseases of the National Institutes of Health under award numbers R01 AR-050520, R01 AR-052345, the Department of Defense CDMRP Grant MR150091, and Award W911NF1820264 from the DARPA’s Lifelong Learning Machines (L2M) program.
We’d be happy to help you apply these methods to your work. Send us a message: [email protected]
USC Viterbi School of Engineering
Defense Advanced Research Projects Agency (DARPA)
Voice of America (VoA)
CHIPS: The department of the Navy’s information technology magazine
USC Stevens Innovation Center
MathWorks - Technical Articles and Newsletters
MathWorks - MATLAB Central Blogs
Google News: Stories
In other languages:
Gaceta Facultad de Ingeniería UNAM
Talks and workshops:
1- “Understanding learning in the context of neuromechanics: The real problem the brain faces.” School of Engineering, Queen’s University, Kingston, Ontario. August 1, 2019.
2- “A neuromorphic approach to understand learning in the context of neuromechanics.” Department of Biomedical Engineering, Johns Hopkins University, Baltimore, MD. April 28, 2019.
3- “Neuromorphic systems for mechanical function and biologically-plausible machine learning algorithms” Chiba University, Japan. April 28, 2019.
4- “A NeuRoBot that learns without forgetting” DARPA L2M PI meeting. DARPA headquarters, Arlington, VA. March 26, 2019. “Neuromorphic simulation of spinal circuitry for sensorimotor function” Society for Brain Mapping and Therapeutics, March 17, 2019.
5- “Principios de neuomecánica y su aplicación a neurociencia, rehabilitación y robotica” Instituto de Neurobiología, Universidad Nacional Autónoma de México, Juriquilla, Querétaro, México. March 17, 2019.
6- “Neuromorphic testbeds of the mammalian spinal cord” University of California at Davis, January 7, 2019 7- “Bio-plausible mechanics, learning, and control for robots” – Google Brain / Robotics, Mountain View, Ca. April 17, 2019. by Ali Marjaninejad
8- “Autonomous Functional Movements in a Tendon-Driven Limb via Limited Experience” USC Biomedical Graduate Talks series. University of Southern California, Los Angeles, Ca. January 9, 2019. by Ali Marjaninejad
9- “On the new generation of bio-inspired robots” – MATLAB EXPO 2019
10- “Autonomous Functional Locomotor Movements in a Tendon-Driven Limb via Limited Experience” Dynamic Walking 2019 - Coast Canmore Hotel & Conference Center, Canmore, Alberta. June 3, 2019 – June 6, 2019
1- Marjaninejad A, Urbina-Meléndez D , Cohn BA, Valero-Cuevas FJ “Autonomous Functional Locomotor Movements in a Tendon-Driven Limb via Limited Experience” The 9th International Symposium on Adaptive Motion of Animals and Machines EPFL, Lausanne, August 20th–23rd, 2019.
2- 19th Yale workshop on Learning and Adaptive Systems. “Learning in the Context of Neuromechanics: The Real Problem the Brain Faces.” Yale University, New Haven, CT. June 10, 2019.
3- DARPA Electronics Resurgence Initiative (ERI) Summit. “Seedling: A NeuRoBot that learns locomotion online, and generalizes/learns variations autonomously without forgetting.” Detroit, MI, July 15-17, 2019.
4- DARPA Electronics Resurgence Initiative (ERI) Summit. “Learning without forgetting in real-time with limited experience: A bio-inspired approach.” Detroit, MI, July 15-17, 2019.
5- BIRS Optimal Neuroethology of Movement and Motor Control. “The nervous system controls afferented muscles, which makes t a simultaneously over- and under-determined problem.” The BIRS Center, Banff, Alberta, Canada. May 245, 2019.
6- Tokyo Hand Meeting. “Neuromorphic controls for neuromuscular systems.” University of Tokyo, Japan. April 23, 2019.
7- 31st Annual CSU Biotechnology Symposium, Hyatt Regency Orange County, Breakout Session: Bioengineering Workshop. Garden Grove, CA. January 3-5, 2019.
USC Stevens Best Commercial Potential Award 2019 (link)
Publications and abstracts
1- Marjaninejad A, Urbina-Meléndez D, Cohn BA, and Valero-Cuevas FJ, Autonomous functional movements in a tendon-driven limb via limited experience Nature Machine Intelligence, 2019 (preprint version available on arXiv)
2- Marjaninejad A, Urbina-Meléndez D,Valero-Cuevas FJ, Simple Kinematic Feedback Enhances Autonomous Learning in Bio-Inspired Tendon-Driven Systems, 42th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC), 2020 (preprint version available on arXiv:1907.04539)
3- Marjaninejad A, Jie T, Valero-Cuevas FJ, Autonomous Control of a Tendon-driven Robotic Limb with Elastic Elements Reveals that Added Elasticity can Enhance Learning, 42th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC), 2020 (preprint version available on arXiv:1909.12436)
4- Hagen DA, Marjaninejad A, Valero-Cuevas FJ A Bio-Inspired Framework for Joint Angle Estimation from Non-Collocated Sensors in Tendon-driven Systems IEEE International Conference on Intelligent Robots and Systems (IROS), 2020
1- Marjaninejad A, Urbina-Meléndez D, Cohn BA, and Valero-Cuevas FJ, Bioinspired few-shot learning in robotic systems, Society for Neuroscience (SfN) annual meeting, Chicago, 2019
2- Marjaninejad A, Urbina-Meléndez D, Cohn BA, and Valero-Cuevas FJ, New generation of bio-inspired robots that learn and adapt using limited experience, The 23rd Grodins Biomedical Engineering Symposium, University of Southern California, 2019
Supplemental site prepared by: Brian A. Cohn and Ali Marjaninejad