Shreyas Ramakrishna, Abhishek Dubey, Matthew P. Burruss, Charles Hartsell, Nagabhushan Mahadevan, Saideep Nannapaneni, Aron Laszka, Gabor Karsai
IEEE 22nd International Symposium on Real-Time Distributed Computing, ISORC 2019, Valencia, Spain, May 7-9, 2019 2019
Learning-enabled components in autonomous systems offer improved performance but lack formal safety guarantees, while traditional control systems are predictable but less adaptive. Resource-constrained robots cannot run complex learning models continuously. This work enables safe autonomous operation by combining neural network controllers with safety supervisors using weighted simplex strategies that account for system state and resource constraints.
This paper presents a framework for augmenting learning-enabled components with safety guarantees in resource-constrained autonomous robots. The work introduces weighted simplex strategies and context-sensitive weighted simplex approaches that enable integration of high-performance neural network controllers with safety supervisors.
The paper demonstrates the approach on an autonomous driving platform (DeepNNCar). Results show that weighted simplex strategies reduce safety violations by 40% compared to using LECs alone while maintaining performance improvement over pure safety supervisors. The framework successfully balances safety and performance through context-aware controller selection.
@inproceedings{Ramakrishna2019,
author = {Ramakrishna, Shreyas and Dubey, Abhishek and Burruss, Matthew P. and Hartsell, Charles and Mahadevan, Nagabhushan and Nannapaneni, Saideep and Laszka, Aron and Karsai, Gabor},
booktitle = {IEEE} 22nd International Symposium on Real-Time Distributed Computing, {ISORC} 2019, Valencia, Spain, May 7-9, 2019},
title = {Augmenting Learning Components for Safety in Resource Constrained Autonomous Robots},
year = {2019},
pages = {108--117},
abstract = {Learning 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 around 0.40m/s than the original system (using only LECs).},
bibsource = {dblp computer science bibliography, https://dblp.org},
biburl = {https://dblp.org/rec/bib/conf/isorc/RamakrishnaDBHM19},
category = {selectiveconference},
contribution = {lead},
doi = {10.1109/ISORC.2019.00032},
file = {:Ramakrishna2019-Augmenting_Learning_Components_for_Safety_in_Resource_Constrained_Autonomous_Robots.pdf:PDF},
keywords = {learning-enabled components, safety, autonomous robots, neural networks, simplex architecture, resource constraints},
project = {cps-autonomy},
tag = {ai4cps},
timestamp = {Wed, 16 Oct 2019 14:14:53 +0200},
url = {https://doi.org/10.1109/ISORC.2019.00032}
}