Engineering Papers⌕ Search

Engineering topics

Rory Lipkis

Publications and source records attributed to Rory Lipkis.

10 records
All sourcesNASA NTRSDOE OSTI
NASA NTRS2024

Recommendations on Evidence and Process for Certification of Learning-enabled Components in Aerospace Systems

This report primarily identifies a collection of relevant and necessary evidence for assurance of machine learnt components (MLCs)—also known as learning-enabled components—integrated into aircraft systems, and gives preliminary suggestions on the elements of a certification process that invoke the identified evidence. The main focus is on feedforward neural networks that are static and trained offline through supervised learning. A brief background on the generic elements of the lifecycle of an MLC is given to contextualize the assurance considerations and, consequently, the evidence that is relevant and necessary to support certification. At the level of an MLC, those considerations relate to: (i) the consistency and correctness of MLC contributions to system functions in the context of a validated functional intent; and (ii) the absence of MLC contributions to aircraft-level failure conditions. At an ML model level, confidence in model and data properties contribute to assurance of the containing MLC, in particular: (a) generalizability and robustness of models, in the presence of inputs not previously seen during training, disturbances to inputs, and unexpected inputs; and (b) valid data, i.e., data that are at least representative, relevant, complete, and accurate. Evidence for the above span the elements of the ML lifecycle, and includes, at a minimum, lifecycle artifacts that pertain to: (1) properties of requirements capturing functional intent, safety constraints, and aspects of the intended use and operating environment; (2) model performance, model complexity and design, and algorithm choice; (3) achievement of required performance at the levels of a trained model during model development, a trained model after model development is complete, and a trained model that is transformed into an executable equivalent; (4) model implementation aspects necessary for transforming a trained model into the executable equivalent; (5) integration of the executable trained model into the containing MLC, and eventually the larger system; and, (6) lastly, the verification and validation (V&V) of each of the above. Such V&V lifecycle artifacts themselves include: aspects of coverage, e.g., of various levels of requirements by the input space of the model and the data; traceability (where applicable); application of formal methods for property specification, analysis, and checking. Examples of evidence generation methods and tools further ground the discussion on what constitutes evidence, and the contribution to assurance during certification. The identified assurance considerations and supporting evidence is not a comprehensive set. Additionally, neither what should be considered as sufficient evidence relative to the assigned criticality of an MLC, nor how criticality ought to be determined and adjusted, have been considered in this report. However, suggestions are made for potential activities of the ML lifecycle that are aimed at providing confidence that an MLC can be relied upon when integrated into its containing (aircraft) system. Those activities are proposed as candidate elements of a certification process for MLCs. The main purpose of this report to inform regulatory guidance and consensus standards that may be used to meet the safety intent of the applicable regulations.

Aviation safety↗
NASA NTRSDate not supplied

Adaptive Stress Testing of Collision Avoidance Systems for Small UASs with Deep Reinforcement Learning

The next-generation Airborne Collision Avoidance System for smaller UASs (ACAS sXu) is currently being developed and tested by the Federal Aviation Administration (FAA) to provide detect-and-avoid capability for small unmanned aircraft operating beyond line-of-sight. Due to the complexity and safety-critical nature of the system, safety validation is important not only for the certification of the final system, but also for informing changes during the iterative development process. In this paper, we analyze a prototype of ACAS sXu in simulated aircraft encounters to discover scenarios of small near mid-air collisions (sNMACs), an important safety event in which two aircraft come closer than 50 feet horizontally and 15 feet vertically. Due to the size and complexity of the system as well as rarity of sNMAC events, traditional methods such as Monte Carlo testing often require informed setup and targeting to elicit failures. However, such a dependence on domain knowledge can be incompatible with the independent verification and validation (IV&V) process, the aim of which is to discover unforeseen issues. To address these challenges, we apply an accelerated validation method called adaptive stress testing (AST) to find the most likely sNMAC scenarios without reliance on system introspection. AST uses reinforcement learning to adapt the search towards the most promising areas of the search space as it progresses. We use a state-of-the-art deep reinforcement learning algorithm, proximate policy optimization, to more efficiently search the large and continuous state space. We find that this approach significantly improves the performance of AST compared to a prior approach based on Monte Carlo tree search. We perform experiments using AST to find sNMAC events under various encounter configurations, varying parameters pertaining to dynamics and coordination. Our experiments show AST to be very effective at finding sNMAC scenarios. We summarize our findings, presenting high-level categories of discovered sNMACs and specific examples of encounters in each category.

aircraft collision avoidance↗
NASA NTRSDate not supplied

AdaStress

This is a tutorial on AdaStress, a tool for finding and analyzing the likeliest failures in a simulated system under test. The presentation outlines the adaptive stress testing framework, provides a demonstration of use, and showcases several examples of failure detection in a complex real-world system.

Reinforcement learning↗
NASA NTRSDate not supplied

Discovery and Analysis of Rare High-Impact Failure Modes using Adversarial RL-Informed Sampling

Adaptive learning agents have tremendous potential to handle critical tasks currently performed by humans. Unfortunately, due to their complexity, it can be difficult to verify that these learning agents do not have critical failure modes. Standard verification and validation methods often do not apply directly to learning agents and Monte Carlo methods have difficulty covering even a small fraction of the state space, especially in multiagent systems or over long time horizons. To overcome this difficulty, we demonstrate an adaptive stress-testing method based on reinforcement learning of correlations that raise the probability of failure. This approach has three key properties: (1) it is able to find rare failure modes with far greater sample efficiency than Monte Carlo methods, (2) it can estimate the true probability of a failure mode despite the inherent bias in the learning method, and (3) it is capable of learning and resampling compact representations of multimodal failure spaces. These properties are important in practice as we need to find disparate failure modes while accounting for their actual relevance. This is a significant advantage over traditional adaptive stress testing methods that give abstract likelihoods of particular failure instances, but cannot estimate the probability of a broader failure mode. We test our algorithm on a simple problem from the aviation domain where an autonomous aircraft lands in gusty wind conditions. The results suggest that we can find failure modes with far fewer samples than the Monte Carlo approach and simultaneously estimate the probability of failure.

reinforcement learning↗
NASA NTRSDate not supplied

Discovery and Analysis of Rare High-Impact Failure Modes using Adversarial RL-Informed Sampling

Adaptive learning agents have tremendous potential to handle critical tasks currently performed by humans. Unfortunately, due to their complexity, it can be difficult to verify that these learning agents do not have critical failure modes. Standard verification and validation methods often do not apply directly to learning agents and Monte Carlo methods have difficulty covering even a small fraction of the state space, especially in multiagent systems or over long time horizons. To overcome this difficulty, we demonstrate an adaptive stress-testing method based on reinforcement learning of correlations that raise the probability of failure. This approach has three key properties: (1) it is able to find rare failure modes with far greater sample efficiency than Monte Carlo methods, (2) it can estimate the true probability of a failure mode despite the inherent bias in the learning method, and (3) it is capable of learning and resampling compact representations of multimodal failure spaces. These properties are important in practice as we need to find disparate failure modes while accounting for their actual relevance. This is a significant advantage over traditional adaptive stress testing methods that give abstract likelihoods of particular failure instances, but cannot estimate the probability of a broader failure mode. We test our algorithm on a simple problem from the aviation domain where an autonomous aircraft lands in gusty wind conditions. The results suggest that we can find failure modes with far fewer samples than the Monte Carlo approach and simultaneously estimate the probability of failure.

Validation↗
NASA NTRSDate not supplied

Discovery and Analysis of Rare High-Impact Failure Modes using Adversarial RL-Informed Sampling

Adaptive learning agents have tremendous potential to handle critical tasks currently performed by humans. Unfortunately, due to their complexity, it can be difficult to verify that these learning agents do not have critical failure modes. Standard verification and validation methods often do not apply directly to learning agents and Monte Carlo methods have difficulty covering even a small fraction of the state space, especially in multiagent systems or over long time horizons. To overcome this difficulty, we demonstrate an adaptive stress-testing method based on reinforcement learning of correlations that raise the probability of failure. This approach has three key properties: (1) it is able to find rare failure modes with far greater sample efficiency than Monte Carlo methods, (2) it can estimate the true probability of a failure mode despite the inherent bias in the learning method, and (3) it is capable of learning and resampling compact representations of multimodal failure spaces. These properties are important in practice as we need to find disparate failure modes while accounting for their actual relevance. This is a significant advantage over traditional adaptive stress testing methods that give abstract likelihoods of particular failure instances, but cannot estimate the probability of a broader failure mode. We test our algorithm on a simple problem from the aviation domain where an autonomous aircraft lands in gusty wind conditions. The results suggest that we can find failure modes with far fewer samples than the Monte Carlo approach and simultaneously estimate the probability of failure.

Validation↗
NASA NTRSDate not supplied

Improving Sim-to-Real Transfer in Vision-Based Robot Navigation Via Instance-Level GAN-Based Data Augmentation

Achieving robust vision-based robotic tasks requires large amounts of data, which are often difficult to obtain in real-world scenarios. Simulators and synthetic data offer a cost-effective alternative, but the visual gap between simulation and reality hinders the performance of models when deployed in real-world environments. In this paper, we present a data augmentation pipeline that integrates a foundation model (Segment Anything Model) with an unsupervised image-to-image translation model (CycleGAN) for instance-level domain transfer from simulation to reality. This pipeline enables the generation of realistic labeled data from synthetic images for training supervised machine learning models in vision-based navigation tasks. We evaluate our approach on real-world data for ego-vehicle pose estimation, a critical autonomous navigation task involving the prediction of cross-track position and heading angle relative to road center line markings. The results of our tests show that our GAN-based data augmentation pipeline significantly outperforms models trained solely on simulation data or on data processed with standard image augmentation methods for sim-to-real transfer, enhancing model robustness and generalizability in real-world scenarios. Our method provides a scalable and flexible data augmentation tool for leveraging large synthetic datasets to enhance vision-based robotic navigation tasks.

artificial intelligence↗
NASA NTRSDate not supplied

From Simulation to Reality With Random Noise

The challenging environment of autonomous vehicle (AV) navigation necessitates certain functions be performed by deep neural networks. Optimizing these models involves collecting vast quantities of domain-specific training data and ensuring that the dataset is representative of expected conditions. High-fidelity simulation plays a vital role in making this process feasible, allowing a wide range of scenarios to be explored at low cost. However, learning from simulation introduces subtle biases into models, which can degrade real-world performance in unpredictable ways. This effect can be mitigated with learning schemes specialized to bridge distributional shifts (transfer learning). Given the complex nature of these methods, the underlying models, and their environments, meaningfully evaluating performance is notstraight forward. Many unrelated factors can effect an improvement in generalization accuracy, but a full ablation analysis is often difficult. To tease out signal from noise, it is necessary to understand how transfer learning performance is affected by noise itself. The goals of this paper are (i) to establish a domain randomization baseline for a simple classification transfer learning task and (ii) to validate the RRAV testbed as a platform for further research in sim-to-real learning. We generate imagery from a simulation of NASA Ames Research Center and train a small convolutional neural network (ConvNet) to classify position relative to a centerline. Further models are trained with different types of noise progressively added to the data. The models are deployed aboard the on-site test vehicle to test real-world performance. In our experiments, we find that such naive domain randomization raises sim-to-real accuracy from 64% to 79%, while training directly on real data yields an 89% accuracy ceiling. These results suggest that the isolated mechanism of domain randomization can significantly improve generalization.

simulation↗
NASA NTRSDate not supplied

AmesDT: Digital Twin and Autonomy Validation Environment

A simulation of NASA Ames Research Center was developed to provide a common testbed for multiple areas of research within the Intelligent Systems Division, primarily related to verification and validation of autonomous technologies, machine learning, and digital twin systems. AmesSim corresponds a physical rover that is capable of navigation in the real-world environment; in this way, the same experiments can be run in both settings, with the same software and hardware stacks in the loop. The simulation is built in Unreal Engine 4 and uses the AirSim plugin for API convenience. Several custom modifications allow deterministic, faster-than-realtime execution, which enables consistent testing of on-line algorithms and large-scale data collection. This paper describes the architecture and capabilities of the simulation and discusses development challenge.

simulation↗