{"title":"Architecting Systems for Assured Autonomy","authors":"R. D. Avila, Jason B. Clark","doi":"10.1109/ICAA58325.2023.00021","DOIUrl":"https://doi.org/10.1109/ICAA58325.2023.00021","url":null,"abstract":"The promise of autonomous systems can positively impact many facets of human endeavors. This new future does come with significant risks and challenges. There exists a good amount of literature and news about autonomous systems failures that are comic but also tragic. A driving principle for autonomous systems must be that they will cause no harm, that they will operate in a reliable manner and that they can be ultimately trusted. A key item is to develop assurance of a system throughout its architecture. This article provides an overview of the development of assurance architectures as part of the Defense Advanced Research Project Agency Assured Autonomy program.","PeriodicalId":190198,"journal":{"name":"2023 IEEE International Conference on Assured Autonomy (ICAA)","volume":"49 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133086362","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Example Applications of Formal Methods to Aerospace and Autonomous Systems","authors":"Laura R. Humphrey","doi":"10.1109/ICAA58325.2023.00018","DOIUrl":"https://doi.org/10.1109/ICAA58325.2023.00018","url":null,"abstract":"As systems become more complex, they become more difficult to verify. Testing is the most common verification approach, but testing can only cover a relatively small proportion of total system behaviors. In the aerospace domain, the time and cost required to run enough tests to adequately verify avionics is already a major issue, and it is anticipated to be an even bigger issue for autonomous systems. Formal methods, i.e. mathematically-based tools and approaches for system specification, design, and analysis-based verification, can potentially supplement test-based verification to provide better coverage of system behaviors in a more reasonable amount of time and at a more reasonable cost. However, the uptake of formal methods has been slow. Our experience interacting with several communities focused on verification and certification of aerospace and autonomous systems is that there are still frequently basic questions about what formal methods are, how they work, and what types of properties they can analyze, along with concerns that formal methods may not be realistic or mature. To help answer these questions and address these concerns, this paper provides a brief overview of formal methods and reviews a set of applications to aerospace and autonomous systems that demonstrate some types of systems and properties that formal methods are well-suited to verify, where they are mature, and where they are gaining in maturity.","PeriodicalId":190198,"journal":{"name":"2023 IEEE International Conference on Assured Autonomy (ICAA)","volume":"6 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127962595","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Sponsors","authors":"","doi":"10.1109/icaa58325.2023.00007","DOIUrl":"https://doi.org/10.1109/icaa58325.2023.00007","url":null,"abstract":"","PeriodicalId":190198,"journal":{"name":"2023 IEEE International Conference on Assured Autonomy (ICAA)","volume":"133 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123134486","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Ananya Trivedi, Salah Bazzi, Mark Zolotas, T. Padır
{"title":"Probabilistic Dynamic Modeling and Control for Skid-Steered Mobile Robots in Off-Road Environments","authors":"Ananya Trivedi, Salah Bazzi, Mark Zolotas, T. Padır","doi":"10.1109/ICAA58325.2023.00016","DOIUrl":"https://doi.org/10.1109/ICAA58325.2023.00016","url":null,"abstract":"Skid-Steered Mobile Robots (SSMRs) are commonly deployed for autonomous navigation across challenging off-road terrains due to their high maneuverability. However, modeling the tire-terrain interactions for these robots when operating at their dynamic limits is challenging, since slipping and skidding govern their movement. During nominal operation, the data collected from the deviation of the robot’s measured states from their commanded values can be informative of these hard-to-model dynamics. In this work-in-progress paper, we propose a probabilistic motion model for SSMRs by leveraging least squares and Sparse Gaussian Process Regression (SGPR) algorithms. This model allows for a nonlinear stochastic Model Predictive Control (MPC) formulation that can be solved in real-time. Initial results on the application of GPR to account for unmodeled dynamics of a physics-simulated quadrotor are shown, suggesting that it can similarly be put to good use for off-road autonomy applications. We explain how these results reinforce the promising application of an SGPR model to risk-averse motion planning for SSMRs.","PeriodicalId":190198,"journal":{"name":"2023 IEEE International Conference on Assured Autonomy (ICAA)","volume":"31 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127846472","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Space Booby Traps: Hacking Back and Assured Cyber Deterrence in Space","authors":"Jocelyn Hsu, Gregory Falco","doi":"10.1109/ICAA58325.2023.00024","DOIUrl":"https://doi.org/10.1109/ICAA58325.2023.00024","url":null,"abstract":"Critical infrastructure is becoming increasingly reliant on satellite services, yielding space systems as prime targets for adversaries. Space cyber defenses must be implemented to enable mission resilience. Hacking back (also called active defense) is an effective mechanism to defend digital systems but difficult to implement with attribution and escalation challenges. We propose a hackback architecture that engages a cyber booby trap facilitating autonomous, active defense against adversaries on space vehicles. The cyber booby trap ensures that only the attacker is impacted and imparts a proportionate response to a cyberattack.","PeriodicalId":190198,"journal":{"name":"2023 IEEE International Conference on Assured Autonomy (ICAA)","volume":"51 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130480244","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Keynotes","authors":"","doi":"10.1109/icaa58325.2023.00008","DOIUrl":"https://doi.org/10.1109/icaa58325.2023.00008","url":null,"abstract":"","PeriodicalId":190198,"journal":{"name":"2023 IEEE International Conference on Assured Autonomy (ICAA)","volume":"96 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115344834","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Cascading Negative Transfer in Networks of Machine Learning Systems","authors":"Tyler Cody, P. Beling","doi":"10.1109/ICAA58325.2023.00028","DOIUrl":"https://doi.org/10.1109/ICAA58325.2023.00028","url":null,"abstract":"Wide-spread use of transfer learning establishes inter-linkages between otherwise disparate parts of systems. These inter-linkages create systemic risks of cascading failure. This paper presents a formal framework for cascading negative transfer. A novel definition is provided for the efficiency of transfer learning networks. Catalysts and pre-conditions for cascading negative transfer are identified. Throughout, qualitative examples in unmanned aerial systems are used to clarify the presented theory. The conclusion is drawn that negative transfer can propagate among machine learning systems that are inter-linked by transfer learning, and that solution methods spanning algorithm design and systems engineering can address systemic risks from cascading negative transfer without eliminating transfer learning altogether.","PeriodicalId":190198,"journal":{"name":"2023 IEEE International Conference on Assured Autonomy (ICAA)","volume":"5 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128421919","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Bradley Potteiger, T. Dignan, Amber Mills, E. Pavelka, Caleb P. Frey, Ben Nathan, Milki Dagne, Violet Garibaldi, Ben Otter
{"title":"Live Virtual Constructive Environment for Assuring the Safety and Security of Complex Autonomous Vehicles","authors":"Bradley Potteiger, T. Dignan, Amber Mills, E. Pavelka, Caleb P. Frey, Ben Nathan, Milki Dagne, Violet Garibaldi, Ben Otter","doi":"10.1109/ICAA58325.2023.00015","DOIUrl":"https://doi.org/10.1109/ICAA58325.2023.00015","url":null,"abstract":"Autonomous and connected vehicle technologies are rapidly emerging and being introduced to society. Traditional vehicles are becoming more sophisticated with integrated driver-assist features incorporating AI algorithms, control systems, and communication interfaces. Modern vehicles are tightly-coupled into a system of systems more robust than the commonly leveraged physical world simulations used in the research community and industry today. This means that components beyond just the AI model effect the safety and security of operating vehicles. It is imperative to consider the complex and interconnected nature of these systems during pre-deployment development and testing. In this paper, we discuss our preliminary work on a multi-level simulation and hardware-in-the-loop (HITL) testbed capable of evaluating vehicle reactions to diverse driving situations based on virtually constructed worlds. Our framework is able to evaluate vehicle behavior at scale in a simulated world while seamlessly integrating physical hardware via a digital-twin approach.","PeriodicalId":190198,"journal":{"name":"2023 IEEE International Conference on Assured Autonomy (ICAA)","volume":"33 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115326628","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Driver Alerting in ADAS-Equipped Cars: A Field Study","authors":"M. L. Cummings, Ben Bauchwitz","doi":"10.1109/ICAA58325.2023.00012","DOIUrl":"https://doi.org/10.1109/ICAA58325.2023.00012","url":null,"abstract":"Driver distraction is a serious problem that directly contributes to rising deaths on US roadways, and is increasingly an issue in cars equipped with Advanced Driving Assist Systems (ADAS) that perform lateral and longitudinal control. To determine how driver alerting systems for two models of ADAS-equipped vehicles compared in a highway setting, a field experiment was conducted that measured the frequency of hands-on-the-wheel alerts, as well as how these alerts may be affected by low sun angles, which can cause camera washout and instabilities in lane tracking. Results show at least one model appears to increase alerting when in sun glare scenarios, but inconsistencies exist across cars of the same model. In addition, car models can vary widely and sometimes dangerously in driver alerting when hands are not detected on the steering wheel, and that dual coding through both audio and visual channels for such alerts is very inadequate.","PeriodicalId":190198,"journal":{"name":"2023 IEEE International Conference on Assured Autonomy (ICAA)","volume":"58 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127534805","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Assurance for Autonomy – JPL’s past research, lessons learned, and future directions","authors":"M. Feather, A. Pinto","doi":"10.1109/ICAA58325.2023.00022","DOIUrl":"https://doi.org/10.1109/ICAA58325.2023.00022","url":null,"abstract":"Robotic space missions have long depended on automation, defined in the 2015 NASA Technology Roadmaps as “the automatically-controlled operation of an apparatus, process, or system using a pre-planned set of instructions (e.g., a command sequence),” to react to events when a rapid response is required. Autonomy, defined there as “the capacity of a system to achieve goals while operating independently from external control,” is required when a wide variation in circumstances precludes responses being pre-planned, instead autonomy follows an onboard deliberative process to determine the situation, decide the response, and manage its execution. Autonomy is increasingly called for to support adventurous space mission concepts, as an enabling capability or as a significant enhancer of the science value that those missions can return. But if autonomy is to be allowed to control these missions’ expensive assets, all parties in the lifetime of a mission, from proposers through ground control, must have high confidence that autonomy will perform as intended to keep the asset safe to (if possible) accomplish the mission objectives. The role of mission assurance is a key contributor to providing this confidence, yet assurance practices honed over decades of spaceflight have relatively little experience with autonomy. To remedy this situation, researchers in JPL’s software assurance group have been involved in the development of techniques specific to the assurance of autonomy. This paper summarizes over two decades of this research, and offers a vision of where further work is needed to address open issues.","PeriodicalId":190198,"journal":{"name":"2023 IEEE International Conference on Assured Autonomy (ICAA)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-05-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129921608","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}