Edge-Based Live Learning for Robot Survival
Open Access
- 17 October 2024
- journal article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Emerging Topics in Computing
- Vol. 13 (1) , 34-47
Abstract
We introduce survival-critical machine learning (SCML), in which a robot encounters dynamically evolving threats that it recognizes via machine learning (ML), and then neutralizes. We model survivability in SCML, and show the value of the recently developed approach of Live Learning. This edge-based ML technique embodies an iterative human-in-the-loop workflow that concurrently enlarges the training set, trains the next model in a sequence of “best-so-far” models, and performs inferencing for both threat detection and pseudo-labeling. We present experimental results using datasets from the domains of drone surveillance, planetary exploration, and underwater sensing to quantify the effectiveness of Live Learning as a mechanism for SCML.Keywords
Funding Information
- Army Research Office
- United States Army Futures Command (W519TC-23-C-0003)
- U.S. Navy (N00174-23-1-0001)
- National Science Foundation (CNS-2106862)
This publication has 27 references indexed in Scilit:
- Programmable microfluidics for dynamic multiband camouflageMicrosystems & Nanoengineering, 2023
- Spacecraft survivability in the natural debris environment near the stable Earth-Moon Lagrange pointsAdvances In Space Research, 2021
- Spacecraft design optimisation for demise and survivabilityAerospace Science and Technology, 2018
- A handbook of parametric survival models for actuarial useScandinavian Actuarial Journal, 2012
- Survival Analysis2012
- A practical guide to understanding Kaplan‐Meier curvesOtolaryngology–Head and Neck Surgery, 2010
- Application of survival analysis methods to long-term care insuranceInsurance: Mathematics and Economics, 2002
- Modeling Medical Prognosis: Survival Analysis TechniquesJournal of Biomedical Informatics, 2001
- Survival analysis: caveats and pitfallsEuropean Journal of Surgical Oncology, 1999
- The first life tableNotes and Records, 1938