SEARCH · Engineering Papers
Search indexed NASA NTRS and DOE OSTI research on propulsion, heat transfer, battery materials and energy systems. Follow report and document links to the original sources.
Quote a phrase for an exact phrase match. Source license links do not imply unrestricted reuse.
The Exploration Aerial Vehicles (EAV) Laboratory at NASA Ames Research Center leads research into intelligent autonomy and advanced control systems, bridging the gap between simulation and full-scale technology through flight test experimentation on unmanned sub-scale test vehicles.
Recent advancement in autonomous driving vehicles and V2X communication has attracted increasing attention towards Intelligent Transportation Systems to build a safe and reliable traffic intersection. However, most of the systems are still at the initial stages and require significant progress to become a reality. This paper presents an overview of NREL Infrastructure Perception and Control (IPC) framework which is an open-source track-data fusion engine which takes input from infrastructure-based perception sensors and cooperatively shared messages from Connected Autonomous Vehicles (CAVs) and Connected Vehicle (CVs) and the challenges associated with deploying such cooperative perception framework at a four-way traffic intersection in the city of Colorado Springs, CO, USA. The sensor data is collected by deploying two radars and two LiDAR sensors on the IPC mobile lab and two radars on diagonally opposite traffic poles at the proposed intersection. The sensor output results imply the need for rapid sensor calibration to bring the collective perception to a common coordinate frame, the importance of time synchronization between the sensors in order to capture accurate spatial and temporal alignment of the objects, and the need for a health monitoring system with fail safe closed-loop detection model for real-time deployment.
NASA and the U.S. Department of Defense are conducting programs which support the future vision of "intelligent" aircraft engines for enhancing the affordability, performance, operability, safety, and reliability of aircraft propulsion systems. Intelligent engines will have advanced control and health management capabilities enabling these engines to be self-diagnostic, self-prognostic, and adaptive to optimize performance based upon the current condition of the engine or the current mission of the vehicle. Sensors are a critical technology necessary to enable the intelligent engine vision as they are relied upon to accurately collect the data required for engine control and health management. This paper reviews the anticipated sensor requirements to support the future vision of intelligent engines from a control and health management perspective. Propulsion control and health management technologies are discussed in the broad areas of active component controls, propulsion health management and distributed controls. In each of these three areas individual technologies will be described, input parameters necessary for control feedback or health management will be discussed, and sensor performance specifications for measuring these parameters will be summarized.
Autonomous recognition of scientifically important information provides the capability of: 1) Prioritizing data return; 2) Intelligent data compression; 3) Reactive behavior onboard robotic vehicles. Such capabilities are desirable as mission scenarios include longer durations with decreasing interaction from mission control. To address such issues, we have implemented several computer algorithms, intended to autonomously recognize morphological shapes of scientific interest within a software architecture envisioned for future rover missions. Mars Exploration Rovers (MER) instrument payloads include a Panoramic Camera (PANCAM) and Microscopic Imager (MI). These provide a unique opportunity to evaluate our algorithms when applied to data obtained from the surface of Mars. Early in the mission we applied our algorithms to images available at the mission web site (http://marsrovers.jpl.nasa.gov/gallery/images.html), even though these are not at full resolution. Some algorithms would normally use ancillary information, e.g. camera pointing and position of the sun, but these data were not readily available. The initial results of applying our algorithms to the PANCAM and MI images are encouraging. The horizon is recognized in all images containing it; such information could be used to eliminate unwanted areas from the image prior to data transmission to Earth. Additionally, several rocks were identified that represent targets for the mini-thermal emission spectrometer. Our algorithms also recognize the layers, identified by mission scientists. Such information could be used to prioritize data return or in a decision-making process regarding future rover activities. The spherules seen in MI images were also autonomously recognized. Our results indicate that reliable recognition of scientifically relevant morphologies in images is feasible.
Unmanned aircraft systems (UAS) collaborate with humans to operate in diverse, safety-critical applications. However, assurance technologies need to be integrated into the design process in order to guarantee safe behavior, thereby enabling UAS operations in the National Airspace System (NAS). In this paper, formal methods are integrated with learning-enabled systems representations. The generation and representation of knowledge are captured via monadic second-order logic rules in the cognitive architecture Soar. These rules are translated into timed automata, and a proof of correctness for the translation is provided so that safety and liveness properties can be checked in the formal verification environment Uppaal. This approach is agnostic to the learning mechanism used to generate the learned rules (e.g., chunking, etc.). An example of a fault-tolerant, learning-enabled UAS deciding which of four contingency procedures to execute under a lost link scenario while overflying an urban area is used to illustrate the approach.
The ground processing and launch of Shuttle vehicles and their payloads is the primary task of Kennedy Space Center. It is a process which is largely manual and contains little inherent automation. Business is conducted today much as it was during previous NASA programs such as Apollo. In light of new programs and decreasing budgets, NASA must find more cost effective ways in which to do business while retaining the quality and safety of activities. Advanced technologies including artificial intelligence could cut manpower and processing time. This paper is an overview of the research and development in Al technology at KSC with descriptions of the systems which have been implemented, as well as a few under development which are promising additions to ground processing software. Projects discussed cover many facets of ground processing activities, including computer sustaining engineering, subsystem monitor and diagnosis tools and launch team assistants. The deployed Al applications have proven an effectiveness which has helped to demonstrate the benefits of utilizing intelligent software in the ground processing task.
In this article, we explore the technical details of the reinforcement learning (RL) algorithms that were deployed in the largest field test of automated vehicles designed to smooth traffic flow in history as of 2023, uncovering the challenges and breakthroughs that come with developing RL controllers for automated vehicles. We delve into the fundamental concepts behind RL algorithms and their application in the context of self-driving cars, discussing the developmental process from simulation to deployment in detail, from designing simulators to reward function shaping. We present the results in both simulation and deployment, discussing the flow-smoothing benefits of the RL controller. From understanding the basics of Markov decision processes to exploring advanced techniques such as deep RL, our article offers a comprehensive overview and deep dive of the theoretical foundations and practical implementations driving this rapidly evolving field. We also showcase real-world case studies and alternative research projects that highlight the impact of RL controllers in revolutionizing autonomous driving. From tackling complex urban environments to dealing with unpredictable traffic scenarios, these intelligent controllers are pushing the boundaries of what automated vehicles can achieve. Furthermore, we examine the safety considerations and hardware-focused technical details surrounding deployment of RL controllers into automated vehicles. As these algorithms learn and evolve through interactions with the environment, ensuring their behavior aligns with safety standards becomes crucial. Here, we explore the methodologies and frameworks being developed to address these challenges, emphasizing the importance of building reliable control systems for automated vehicles.
In this article, we explore the technical details of the reinforcement learning (RL) algorithms that were deployed in the largest field test of automated vehicles designed to smooth traffic flow in history as of 2023, uncovering the challenges and breakthroughs that come with developing RL controllers for automated vehicles. We delve into the fundamental concepts behind RL algorithms and their application in the context of self-driving cars, discussing the developmental process from simulation to deployment in detail, from designing simulators to reward function shaping. We present the results in both simulation and deployment, discussing the flow-smoothing benefits of the RL controller. From understanding the basics of Markov decision processes to exploring advanced techniques such as deep RL, our article offers a comprehensive overview and deep dive of the theoretical foundations and practical implementations driving this rapidly evolving field. We also showcase real-world case studies and alternative research projects that highlight the impact of RL controllers in revolutionizing autonomous driving. From tackling complex urban environments to dealing with unpredictable traffic scenarios, these intelligent controllers are pushing the boundaries of what automated vehicles can achieve. Furthermore, we examine the safety considerations and hardware-focused technical details surrounding deployment of RL controllers into automated vehicles. As these algorithms learn and evolve through interactions with the environment, ensuring their behavior aligns with safety standards becomes crucial. We explore the methodologies and frameworks being developed to address these challenges, emphasizing the importance of building reliable control systems for automated vehicles.
Abstract Delivery vehicle drivers are experiencing increasing challenges in finding available curb space to park in urban areas, which increases instances of cruising for parking and parking in unauthorized spaces. Policies traditionally used to reduce cruising for parking for passenger vehicles, such as parking fees and congestion pricing, are not effective at changing delivery drivers’ travel and parking behaviors. Intelligent parking systems that use real-time curb availability information to better route and park vehicles can reduce cruising for parking, but they have never been tested for delivery vehicle drivers. The current study tested whether providing real-time curb availability information to delivery drivers reduces the travel time and distance spent cruising for parking. A curb parking information system deployed in a study area in Seattle, Wash., displayed real-time curb availabilities on a mobile app called OpenPark. A controlled experiment assigned drivers’ deliveries in the study area with and without access to OpenPark. The data collected showed that when curb availability information was provided to drivers, their cruising for parking time significantly decreased by 27.9 percent, and their cruising distance decreased by 12.4 percent. These results demonstrate the potential for implementing intelligent parking systems to improve the efficiency of urban logistics systems.
This talk will present overviews of various intelligent control technologies currently being developed and studied at the NASA Ames Research Center as applicable to Unmanned Aerial Vehicles (UAVs), Mars flyers, and to the next generation of flight controllers for manned aircraft. The approaches being examined include: (a) direct adaptive dynamic inverse controller, (b) adaptive critic-based optimal trajectory generator; (c) optimal allocation technique based on linear programming; (4) immunized maneuvering using autopilot building blocks. These approaches can utilize, but do not require, fault detection and isolation information. Piloted and unmanned simulation studies are performed to examine if the intelligent flight control techniques adequately: 1) match flying qualities of modem fly-by-wire flight controllers under nominal conditions; 2) improve performance under failure conditions when sufficient control authority is available; and 3) achieve intelligent maneuvering capabilities for unmanned vehicles. Results obtained so far will be presented and discussed.
Abstract Neuromorphic computing offers the opportunity to implement extremely low power artificial intelligence at the edge. Control applications, such as autonomous vehicles and robotics, are also of great interest for neuromorphic systems at the edge. It is not clear, however, what the best neuromorphic training approaches are for control applications at the edge. In this work, we implement and compare the performance of evolutionary optimization and imitation learning approaches on an autonomous race car control task using an edge neuromorphic implementation. We show that the evolutionary approaches tend to achieve better performing smaller network sizes that are well-suited to edge deployment, but they also take significantly longer to train. We also describe a workflow to allow for future algorithmic comparisons for neuromorphic hardware on control applications at the edge.
This project aimed to enhance the range and reduce the operating costs of battery electric Class 8 trucks traveling over 250 miles daily. This was achieved through the development and implementation of an intelligent-Energy Management System (i-EMS) that leverages vehicle and operations data, physics-aware machine learning algorithms, and vehicle-to-cloud (V2C) connectivity. The project hypothesized that advanced machine learning algorithms and real-time data analytics could significantly improve the energy efficiency and range of these trucks. Key objectives included developing a physics-aware machine learning algorithm, implementing an i-EMS with V2C connectivity and physics-aware spatial data analytics (PSDA), and validating the system’s effectiveness with fleet partners HEB Companies and Murphy Logistics. Extensive data collection from vehicle operations, including vehicle characteristics, road conditions, and payload, was conducted. A machine learning algorithm was developed to predict energy consumption and enable proactive decision-making. The i-EMS was implemented on two Volvo VNR BEVs, with operators receiving charging and routing recommendations. Charging stations were installed at depot locations in Texas and Minnesota, with an additional on-route charger in Minnesota. Significant findings included a 14% range improvement for Murphy Logistics on a highway-driving eco-route and a 22% range improvement for HEB Companies on a city-driving eco-route. The i-EMS utilized rule-based methods and physics-based algorithms to predict and reduce energy consumption, with real-time monitoring and analysis through V2C connectivity enabling proactive decision-making. The project demonstrated the feasibility and economic viability of battery electric Class 8 trucks for long-haul operations, showcasing the potential of physics-aware machine learning in optimizing energy management. The successful implementation of the i-EMS in real-world scenarios validates its practical application and effectiveness, paving the way for the widespread adoption of battery electric vehicles in the freight transportation industry.
A rotary wing, unmanned air vehicle (UAV) is being developed as a research tool at the NASA Langley Research Center by the U.S. Army and NASA. This development program is intended to provide the rotorcraft research community an intermediate step between rotorcraft wind tunnel testing and full scale manned flight testing. The technologies under development for this vehicle are: adaptive electronic flight control systems incorporating artificial intelligence (AI) techniques, small-light weight sophisticated sensors, advanced telepresence-telerobotics systems and rotary wing UAV operational procedures. This paper briefly describes the system's requirements and the techniques used to integrate the various technologies to meet these requirements. The paper also discusses the status of the development effort. In addition to the original aeromechanics research mission, the technology development effort has generated a great deal of interest in the UAV community for related spin-off applications, as briefly described at the end of the paper. In some cases the technologies under development in the free flight program are critical to the ability to perform some applications.
A smart-divert capability has been added into the Powered Descent Guidance (PDG) software originally developed for Mars pinpoint and precision landing. The smart-divert algorithm accounts for the landing dispersions of the entry backshell, which separates from the lander vehicle at the end of the parachute descent phase and prior to powered descent. The smart-divert PDG algorithm utilizes the onboard fuel and vehicle thrust vectoring to mitigate landing error in an intelligent way: ensuring that the lander touches down with minimum- fuel usage at the minimum distance from the desired landing location that also avoids impact by the descending backshell. The smart-divert PDG software implements a computationally efficient, convex formulation of the powered-descent guidance problem to provide pinpoint or precision-landing guidance solutions that are fuel-optimal and satisfy physical thrust bound and pointing constraints, as well as position and speed constraints. The initial smart-divert implementation enforced a lateral-divert corridor parallel to the ground velocity vector; this was based on guidance requirements for MSL (Mars Science Laboratory) landings. This initial method was overly conservative since the divert corridor was infinite in the down-range direction despite the backshell landing inside a calculable dispersion ellipse. Basing the divert constraint instead on a local tangent to the backshell dispersion ellipse in the direction of the desired landing site provides a far less conservative constraint. The resulting enhanced smart-divert PDG algorithm avoids impact with the descending backshell and has reduced conservatism.
Vehicles and systems in the field of aerospace have two major requirements: a high demand for a large quantity and an expectation to perform for their lifetime with little to no failures. Thus, there is a need for a fast production rate of aerospace products with high quality. Improvements to production rate have many benefits, including a reduction in energy consumption per unit manufactured. This would be from factory energy usage, which is required to build and verify a product. Manufacturing process specifications require inspection of parts to determine if any flaws are present. Depending on factory planning and product quality, especially at higher rates, the evaluation process can pose a production rate bottleneck. This project was comprised of using artificial intelligence and machine learning (AI/ML) methods on inspection evaluations with the objective of reducing the required time to produce an aerospace structure or product and without reducing the final quality.
This report summarizes activities performed during the second year of a three year cooperative agreement between NASA - Langley Research Center and Georgia Tech. Year 1 of the project resulted in the creation of a new Cost and Business Assessment Model (CABAM) for estimating the economic performance of advanced reusable launch vehicles including non-recurring costs, recurring costs, and revenue. The current year (second year) activities were focused on the evaluation of automated, collaborative design frameworks (computation architectures or computational frameworks) for automating the design process in advanced space vehicle design. Consistent with NASA's new thrust area in developing and understanding Intelligent Synthesis Environments (ISE), the goals of this year's research efforts were to develop and apply computer integration techniques and near-term computational frameworks for conducting advanced space vehicle design. NASA - Langley (VAB) has taken a lead role in developing a web-based computing architectures within which the designer can interact with disciplinary analysis tools through a flexible web interface. The advantages of this approach are, 1) flexible access to the designer interface through a simple web browser (e.g. Netscape Navigator), 2) ability to include existing 'legacy' codes, and 3) ability to include distributed analysis tools running on remote computers. To date, VAB's internal emphasis has been on developing this test system for the planetary entry mission under the joint Integrated Design System (IDS) program with NASA - Ames and JPL. Georgia Tech's complementary goals this year were to: 1) Examine an alternate 'custom' computational architecture for the three-discipline IDS planetary entry problem to assess the advantages and disadvantages relative to the web-based approach.and 2) Develop and examine a web-based interface and framework for a typical launch vehicle design problem.
The goal of this project was to utilize individual vehicle and systems-level transportation big data to develop real-world implementable techniques for energy efficiency. We collected a real world dataset in Fort Collins, CO using technology that is currently available. This dataset was used to (1) create individual vehicle prediction models and emissions models using cutting-edge artificial intelligence (AI) techniques, (2) create traffic prediction models, (3) create boundary condition constraints for optimal trajectory derivation, and (4) develop a novel Mobility Energy Productivity (MEP) model for Fort Collins, CO at a fidelity and flexibility which did not previously exist. Each of these techniques is novel but the most interesting results occurred from the intersection of all techniques. It was found that when optimal vehicle control is combined with optimal traffic light control, that significant energy efficiency improvements that do not compromise travel time are available.
The NASA Ames Research Center (Thermal Protection Materials and Systems Branch) is investigating new ceramic materials for the thermal protection of atmospheric entry vehicles. An incremental approach to proving the capabilities of these materials calls for a lifting entry flight test of a sharp leading edge component on the proposed SHARP (Slender Hypervelocity Aerothermodynamic Research Probe) vehicle. This flight test will establish the aerothermal performance constraint under real lifting entry conditions. NASA Ames has been developing the SHARP test flight with SSDL (responsible for the SHARP S I vehicle avionics), Montana State University (responsible for the SHARP S I vehicle airframe), the Wickman Spacecraft and Propulsion Company (responsible for the sounding rocket and launch operations), and with the SCU Intelligent Robotics Program, The SCU team was added well after the rest of the development team had formed. The SCU role was to assist with the development of a real-time video broadcast system which would relay onboard flight video to a communication groundstation. The SCU team would also assist with general vehicle preparation as well as flight operations. At the time of the submission of the original SCU proposal, a test flight in Wyoming was originally targeted for September 2000. This date was moved several times into the Fall of 2000. It was then postponed until the Spring of 2001, and later pushed into late Summer 2001. To date, the flight has still not taken place. These project delays resulted in SCU requesting several no-cost extensions to the project. Based on the most recent conversations with the project technical lead, Paul Kolodjiez, the current plan is for the overall SHARP team to assemble what exists of the vehicle, to document the system, and to 'mothball' the vehicle in anticipation of future flight and funding opportunities.