Show simple item record

dc.contributor.authorRamakrishna, Shreyas
dc.contributor.authorDubey, Abhishek
dc.contributor.authorBurruss, Matthew P.
dc.contributor.authorHartsell, Charles
dc.contributor.authorMahadevan, Nagabhushan
dc.contributor.authorNannapaneni, Saideep
dc.contributor.authorLaszka, Aron
dc.contributor.authorKarsai, Gabor
dc.date.accessioned2019-08-22T13:48:46Z
dc.date.available2019-08-22T13:48:46Z
dc.date.issued2019-05
dc.identifier.citationS. Ramakrishna et al., "Augmenting Learning Components for Safety in Resource Constrained Autonomous Robots," 2019 IEEE 22nd International Symposium on Real-Time Distributed Computing (ISORC), Valencia, Spain, 2019, pp. 108-117en_US
dc.identifier.isbn978-172810150-7
dc.identifier.urihttps://doi.org/10.1109/ISORC.2019.00032
dc.identifier.urihttp://hdl.handle.net/10057/16524
dc.descriptionClick on the DOI link to access the article (may not be free).en_US
dc.description.abstractLearning enabled components (LECs) trained using data-driven algorithms are increasingly being used in autonomous robots commonly found in factories, hospitals, and educational laboratories. However, these LECs do not provide any safety guarantees, and testing them is challenging. In this paper, we introduce a framework that performs weighted simplex strategy based supervised safety control, resource management and confidence estimation of autonomous robots. Specifically, we describe two weighted simplex strategies: (a) simple weighted simplex strategy (SW-Simplex) that computes a weighted controller output by comparing the decisions between a safety supervisor and an LEC, and (b) a context-sensitive weighted simplex strategy (CSW-Simplex) that computes a context-aware weighted controller output. We use reinforcement learning to learn the contextual weights. We also introduce a system monitor that uses the current state information and a Bayesian network model learned from past data to estimate the probability of the robotic system staying in the safe working region. To aid resource constrained robots in performing complex computations of these weighted simplex strategies, we describe a resource manager that offloads tasks to an available fog nodes. The paper also describes a hardware testbed called DeepNNCar, which is a low cost resource-constrained RC car, built to perform autonomous driving. Using the hardware, we show that both SW-Simplex and CSW-Simplex have 40% and 60% fewer safety violations, while demonstrating higher optimized speed during indoor driving ( 0.40 m/s) than the original system (using only LECs).en_US
dc.description.sponsorshipDARPA and Air Force Research Laboratory.en_US
dc.language.isoen_USen_US
dc.publisherIEEEen_US
dc.relation.ispartofseriesIEEE 22nd International Symposium on Real-Time Distributed Computing (ISORC);2019
dc.subjectAutonomous robotsen_US
dc.subjectConvolutional neural networksen_US
dc.subjectLECen_US
dc.subjectReinforcement learningen_US
dc.subjectSimplex architectureen_US
dc.titleAugmenting learning components for safety in resource constrained autonomous robotsen_US
dc.typeConference paperen_US
dc.rights.holder© 2019, IEEEen_US


Files in this item

FilesSizeFormatView

There are no files associated with this item.

This item appears in the following Collection(s)

Show simple item record