SEARCH · Search NASA

Results for “software reliability engineering”

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.

SourceResearch connectionFrom yearThrough year

Quote a phrase for an exact phrase match. Source license links do not imply unrestricted reuse.

At least 307 records · Page 17

All sources NASA NTRS DOE OSTI

NASA NTRS2008

Reconfigurable HIL Testing of Earth Satellites

In recent years, hardware-in-the-loop (HIL) testing has carved a strong niche in several industries, such as automotive, aerospace, telecomm, and consumer electronics. As desktop computers have realized gains in speed, memory size, and data storage capacity, hardware/software platforms have evolved into high performance, deterministic HIL platforms, capable of hosting the most demanding applications for testing components and subsystems. Using simulation software to emulate the digital and analog I/O signals of system components, engineers of all disciplines can now test new systems in realistic environments to evaluate their function and performance prior to field deployment. Within the Aerospace industry, space-borne satellite systems are arguably some of the most demanding in terms of their requirement for custom engineering and testing. Typically, spacecraft are built one or few at a time to fulfill a space science or defense mission. In contrast to other industries that can amortize the cost of HIL systems over thousands, even millions of units, spacecraft HIL systems have been built as one-of-a-kind solutions, expensive in terms of schedule, cost, and risk, to assure satellite and spacecraft systems reliability. The focus of this paper is to present a new approach to HIL testing for spacecraft systems that takes advantage of a highly flexible hardware/software architecture based on National Instruments PXI reconfigurable hardware and virtual instruments developed using LabVIEW. This new approach to HIL is based on a multistage/multimode spacecraft bus emulation development model called Reconfigurable Hardware In-the-Loop or RHIL.

Source record↗

NASA NTRS1989

A perspective on future directions in aerospace propulsion system simulation

The design and development of aircraft engines is a lengthy and costly process using today's methodology. This is due, in large measure, to the fact that present methods rely heavily on experimental testing to verify the operability, performance, and structural integrity of components and systems. The potential exists for achieving significant speedups in the propulsion development process through increased use of computational techniques for simulation, analysis, and optimization. This paper outlines the concept and technology requirements for a Numerical Propulsion Simulation System (NPSS) that would provide capabilities to do interactive, multidisciplinary simulations of complete propulsion systems. By combining high performance computing hardware and software with state-of-the-art propulsion system models, the NPSS will permit the rapid calculation, assessment, and optimization of subcomponent, component, and system performance, durability, reliability and weight-before committing to building hardware.

Miller, Brent A.↗

NASA NTRS1995

Adaptive Optimization of Aircraft Engine Performance Using Neural Networks

Preliminary results are presented on the development of an adaptive neural network based control algorithm to enhance aircraft engine performance. This work builds upon a previous National Aeronautics and Space Administration (NASA) effort known as Performance Seeking Control (PSC). PSC is an adaptive control algorithm which contains a model of the aircraft's propulsion system which is updated on-line to match the operation of the aircraft's actual propulsion system. Information from the on-line model is used to adapt the control system during flight to allow optimal operation of the aircraft's propulsion system (inlet, engine, and nozzle) to improve aircraft engine performance without compromising reliability or operability. Performance Seeking Control has been shown to yield reductions in fuel flow, increases in thrust, and reductions in engine fan turbine inlet temperature. The neural network based adaptive control, like PSC, will contain a model of the propulsion system which will be used to calculate optimal control commands on-line. Hopes are that it will be able to provide some additional benefits above and beyond those of PSC. The PSC algorithm is computationally intensive, it is valid only at near steady-state flight conditions, and it has no way to adapt or learn on-line. These issues are being addressed in the development of the optimal neural controller. Specialized neural network processing hardware is being developed to run the software, the algorithm will be valid at steady-state and transient conditions, and will take advantage of the on-line learning capability of neural networks. Future plans include testing the neural network software and hardware prototype against an aircraft engine simulation. In this paper, the proposed neural network software and hardware is described and preliminary neural network training results are presented.

Simon, Donald L.↗

DOE OSTI2025

Flexible Operation of Microgrids Through Operator-Configurable Microgrid Controllers

Microgrids are becoming critical assets in power distribution systems. This is partly due to the resiliency and reliability challenges faced by power distribution systems in the last decade and partly due to the increased integration of distributed energy resource assets, such as solar photovoltaic. This increased need for microgrids has created a multitude of needs for microgrid controllers. Most microgrid controllers in the past decade have been uniquely programmed or custom programmed to meet the needs of a specific microgrid. Currently, IEEE standards aim to integrate the needs and capabilities of microgrid controllers under a unified umbrella. But the standards do not recommend necessary or appropriate software development practices for microgrid controllers. In addition, the programmable nature and maintenance of controllers are also key characteristics that fall outside the coverage of the standards. In this paper, we present the best software practices that utility engineers and microgrid operators should consider in the microgrid software platform. This paper can be used as an information document for developing documentation of controller requirements and assessing microgrid controller requirements.

Banshee microgrid↗

NASA NTRS1999

An Evolvable Multi-Agent Approach to Space Operations Engineering

A complex system of spacecraft and ground tracking stations, as well as a constellation of satellites or spacecraft, has to be able to reliably withstand sudden environment changes, resource fluctuations, dynamic resource configuration, limited communication bandwidth, etc., while maintaining the consistency of the system as a whole. It is not known in advance when a change in the environment might occur or when a particular exchange will happen. A higher degree of sophistication for the communication mechanisms between different parts of the system is required. The actual behavior has to be determined while the system is performing and the course of action can be decided at the individual level. Under such circumstances, the solution will highly benefit from increased on-board and on the ground adaptability and autonomy. An evolvable architecture based on intelligent agents that communicate and cooperate with each other can offer advantages in this direction. This paper presents an architecture of an evolvable agent-based system (software and software/hardware hybrids) as well as some plans for further implementation.

Mandutianu, Sanda↗

DOE OSTI2025

NUTRON NESHAPs Dashboard

My project aims to enhance the Nuclear Material Tracking Application (NUTRON) software by integrating a tool for the National Emission Standards for Hazardous Air Pollutants (NESHAP) emissions calculations and presenting this data on a dashboard. Inefficiencies in the current NESHAP calculation process were addressed, which will result in more timely regulatory compliance efforts. Key improvements include revising the transfer request system, incorporating effective dose calculations, and developing a data visualization dashboard into NUTRON. The project involved creating a wireframe, preparing an Engineering Calculations and Analysis Report (ECAR), stakeholder meetings, and providing supplemental documentation. Key findings indicate that the proposed modifications will streamline the NESHAP calculation process, reduce human error, and provide REC personnel with accurate and timely data for material use determinations and dose estimations. Future work focuses on completing the NUTRON modifications and fully integrating the new features, ensuring a more efficient and reliable system for tracking and reporting nuclear material transfers.

99 - GENERAL AND MISCELLANEOUS↗

NASA NTRS2001

Transient Reliability Analysis Capability Developed for CARES/Life

The CARES/Life software developed at the NASA Glenn Research Center provides a general-purpose design tool that predicts the probability of the failure of a ceramic component as a function of its time in service. This award-winning software has been widely used by U.S. industry to establish the reliability and life of a brittle material (e.g., ceramic, intermetallic, and graphite) structures in a wide variety of 21st century applications.Present capabilities of the NASA CARES/Life code include probabilistic life prediction of ceramic components subjected to fast fracture, slow crack growth (stress corrosion), and cyclic fatigue failure modes. Currently, this code can compute the time-dependent reliability of ceramic structures subjected to simple time-dependent loading. For example, in slow crack growth failure conditions CARES/Life can handle sustained and linearly increasing time-dependent loads, whereas in cyclic fatigue applications various types of repetitive constant-amplitude loads can be accounted for. However, in real applications applied loads are rarely that simple but vary with time in more complex ways such as engine startup, shutdown, and dynamic and vibrational loads. In addition, when a given component is subjected to transient environmental and or thermal conditions, the material properties also vary with time. A methodology has now been developed to allow the CARES/Life computer code to perform reliability analysis of ceramic components undergoing transient thermal and mechanical loading. This means that CARES/Life will be able to analyze finite element models of ceramic components that simulate dynamic engine operating conditions. The methodology developed is generalized to account for material property variation (on strength distribution and fatigue) as a function of temperature. This allows CARES/Life to analyze components undergoing rapid temperature change in other words, components undergoing thermal shock. In addition, the capability has been developed to perform reliability analysis for components that undergo proof testing involving transient loads. This methodology was developed for environmentally assisted crack growth (crack growth as a function of time and loading), but it will be extended to account for cyclic fatigue (crack growth as a function of load cycles) as well.

Nemeth, Noel N.↗

NASA NTRS1994

Experience report: Using formal methods for requirements analysis of critical spacecraft software

Formal specification and analysis of requirements continues to gain support as a method for producing more reliable software. However, the introduction of formal methods to a large software project is difficult, due in part to the unfamiliarity of the specification languages and the lack of graphics. This paper reports results of an investigation into the effectiveness of formal methods as an aid to the requirements analysis of critical, system-level fault-protection software on a spacecraft currently under development. Our experience indicates that formal specification and analysis can enhance the accuracy of the requirements and add assurance prior to design development in this domain. The work described here is part of a larger, NASA-funded research project whose purpose is to use formal-methods techniques to improve the quality of software in space applications. The demonstration project described here is part of the effort to evaluate experimentally the effectiveness of supplementing traditional engineering approaches to requirements specification with the more rigorous specification and analysis available with formal methods.

Lutz, Robyn R.↗

NASA NTRS2013

A Satellite Mortality Study to Support Space Systems Lifetime Prediction

Estimating the operational lifetime of satellites and spacecraft is a complex process. Operational lifetime can differ from mission design lifetime for a variety of reasons. Unexpected mortality can occur due to human errors in design and fabrication, to human errors in launch and operations, to random anomalies of hardware and software or even satellite function degradation or technology change, leading to unrealized economic or mission return. This study focuses on data collection of public information using, for the first time, a large, publically available dataset, and preliminary analysis of satellite lifetimes, both operational lifetime and design lifetime. The objective of this study is the illustration of the relationship of design life to actual lifetime for some representative classes of satellites and spacecraft. First, a Weibull and Exponential lifetime analysis comparison is performed on the ratio of mission operating lifetime to design life, accounting for terminated and ongoing missions. Next a Kaplan-Meier survivor function, standard practice for clinical trials analysis, is estimated from operating lifetime. Bootstrap resampling is used to provide uncertainty estimates of selected survival probabilities. This study highlights the need for more detailed databases and engineering reliability models of satellite lifetime that include satellite systems and subsystems, operations procedures and environmental characteristics to support the design of complex, multi-generation, long-lived space systems in Earth orbit.

Fox, George↗

NASA NTRS2003

Improved Testing Capability and Adaptability Through the Use of Wireless Sensors

From the first Saturn V rocket booster (S-II-T) testing in 1966 and the routine Space Shuttle Main Engine (SSME) testing beginning in 1975, to more recent test programs such as the X-33 Aerospike Engine, the Integrated Powerhead Development (IPD) program, and the Hybrid Sounding Rocket (HYSR), Stennis Space Center (SSC) continues to be a premier location for conducting large-scale testing. Central to each test program is the capability for sensor systems to deliver reliable measurements and high quality data, while also providing a means to monitor the test stand area to the highest degree of safety and sustainability. Sensor wiring is routed along piping and through cable trenches, making its way from the engine test area, through the test stand area and to the signal conditioning building before final transfer to the test control center. When sensor requirements lie outside the reach of the routine sensor cable routing, the use of wireless sensor networks becomes particularly attractive due to their versatility and ease of installation. As part of an on-going effort to enhance the testing capabilities of Stennis Space Center, the Test Technology and Development group has found numerous applications for its sensor-adaptable wireless sensor suite. While not intended for critical engine measurements or control loops, in-house hardware and software development of the sensor suite can provide improved testing capability for a range of applications including the safety monitoring of propellant storage barrels and as an experimental test-bed for embedded health monitoring paradigms.

Solano, Wanda M.↗

NASA NTRS2006

Emerging technologies for V&V of ISHM software for space exploration

Systems1,2 required to exhibit high operational reliability often rely on some form of fault protection to recognize and respond to faults, preventing faults' escalation to catastrophic failures. Integrated System Health Management (ISHM) extends the functionality of fault protection to both scale to more complex systems (and systems of systems), and to maintain capability rather than just avert catastrophe. Forms of ISHM have been utilized to good effect in the maintenance phase of systems' total lifecycles (often referred to as 'condition-based mainte-nance'), but less so in a 'fault protection' role during actual operations. One of the impediments to such use lies in the challenges of verification, validation and certification of ISHM systems themselves. This paper makes the case that state-of-the-practice V&V and certification techniques will not suffice for emerging forms of ISHM systems; however, a number of maturing software engineering assurance technologies show particular promise for addressing these ISHM V&V challenges.

fault detection, isolation, and recovery↗

NASA NTRS2011

Licklider Transmission Protocol Implementation

This software is an implementation of the Licklider Transmission Protocol (LTP), a communications protocol intended to support the Bundle Protocol in Delay-Tolerant Network (DTN) operations. LTP is designed to provide retransmission-based reliability over links characterized by extremely long message round-trip times and/or frequent interruptions in connectivity. Communication in interplanetary space is the most prominent example of this sort of environment, and LTP is principally aimed at supporting long-haul reliable transmission over deep-space RF links. Like any reliable transport service employing ARQ (Automatic Repeat re-Quests), LTP is stateful. In order to assure the reception of a block of data it has sent, LTP must retain for possible retransmission all portions of that block which might not have been received yet. In order to do so, it must keep track of which portions of the block are known to have been received so far, and which are not, together with any additional information needed for purposes of retransmitting part, or all, of the block. Long round-trip times mean substantial delay between the transmission of a block of data and the reception of an acknowledgement from the block s destination, signaling arrival of the block. If LTP postponed transmission of additional blocks of data until it received acknowledgement of the arrival of all prior blocks, valuable opportunities to use what little deep space transmission bandwidth is available would be forever lost. For this reason, LTP is based in part on a notion of massive state retention. Any number of requested transmission conversations (sessions) may be concurrently in flight at various displacements along the link between two LTP engines, and the LTP engines must necessarily retain transmission status and retransmission resources for all of them. Moreover, if any of the data of a given block are lost en route, it will be necessary to retain the state of that transmission during an additional round trip while the lost data are retransmitted; even multiple retransmission cycles may be necessary. LTP's possible multiplicity of sessions per association makes it necessary for each segment of application data to include an additional demultiplexing token: a session ID that uniquely identifies the session in which the segment was issued and, implicitly, the block of data being conveyed by this session. This software comprises a prototype implementation developed by Johns Hopkins University APL in cooperation with JPL, together with adaptations that improve the robustness, correctness, and operability of that implementation.

Burleigh, Scott C.↗

NASA NTRS2018

A Prognostic Launch Vehicle Probability of Failure Assessment Methodology for Conceptual Systems Predicated on Human Causal Factors

Create an improved method to calculate reliability of a conceptual launch vehicle system prior to fabrication by using historic data of actual root causes of failures. While failures have unique "proximate causes", there are typically a finite amount of common "root causes". Heretofore launch vehicle reliability evaluation typically hardware-centric statistical analyses, while most root causes of failures are been shown to be human-centric. A method based on human-centric root causes can be used to quantify reliability assessments and focus proposed actions to mitigate problems. Existing methods have been optimistic in their projections of launch vehicle reliability compared to actuals. Hypothesis: reliability of a conceptual launch vehicle can be more accurately evaluated based on a rational, probabilistic approach using past failure assessment teams' findings predicated on human-centric causes."Human Reliability Analysis Methods Selection Guidance for NASA"Chandler F.T., et al., NASA HQ/OSMA study group, July 2006. Outside HRA experts from academia, other federal labs, and the private sector. 50 system reliability methods considered, fourteen selected for further study, four finally selected as best suited for human spaceflight. Probabilistic Risk Analysis (PRA) + Human Reliability Analysis (HRA) enabled incorporating effects and probabilities of human errors. While four down-selected methods deemed appropriate for failure assessment, it did not appear that these methods could be concisely applied to perform major system-wide assessment of probability of failure of a conceptual design without becoming unwieldy."Engineering a Safer World", Detailed, comprehensive study external to NASA Leveson N. G., MIT, 2011.Systems-Theoretic Accident Model and Processes (STAMP). All-encompassing accident model based on systems theory analyzed accidents after they occurred and created approaches to prevent occurrence in developing systems not focused on failure prevention per se, but rather reducing hazards by influencing human behavior through use of constraints, hierarchical control structures, and process models to improve system safetySystem Theoretic Process Analysis (STPA) addresses predictive part of problem (a "hazard analysis"). Includes all causal factors identified in STAMP: "...design errors, software flaws, component interaction accidents, cognitively complex human decision-making errors, and social organizational and management factors contributing to accidents" can guide design process rather than require it to exist before-hand did not appear capable of concise application for system-wide assessment of probability of failure of a conceptual design without becoming unwieldy.

Williams, Craig H.↗

NASA NTRSDate not supplied

Enabling a Voice Management System for Space Applications

The sustainable missions beyond Low Earth Orbit (LEO) envisioned for NASA’s Artemis program will require autonomous capabilities. Moreover, Artemis mission crews will need a means to efficiently interact with a spacecraft’s autonomous systems. This interaction can be facilitated by voice and speech communications because voice-based controls enable users to interact hands- and eyes-free, allowing the user to better focus on critical tasks. The goal of our project was to explore the knowledge and technology needed to successfully design effective Voice User Interfaces (VUIs) for autonomous systems utilizing Human Centered Design (HCD) principles. The focus of the human factors’ aspect of engineering, pays close attention to psychological and physiological principles in the development of autonomous crew operation systems. A main objective was to understand how a crew member, through voice interaction, could efficiently and intuitively communicate with a notional autonomous vehicle system manager. This project was a part of the NASA Moon to Mars eXploration Systems and Habitation (M2M X-Hab) 2020 Academic Innovation Challenge. The work from the BLiSS Team, at the University of Michigan, resulted in the design of a system persona, Diego, to which an astronaut may quickly build trust with autonomous systems, to alleviate known stressors on mental health expected during long duration space missions. Optimal software to facilitate integration of the system persona into a reference Lunar orbiting Gateway station was defined. Additionally, a Speech to Text (STT) system and a Graphical User Interface (GUI) that could be implemented in future missions was developed on an Internet of Things (IOT) platform. The Voice User Interface (VUI) design for the M2M X-Hab 2020 project leveraged previous technology developed by the BLiSS team to incorporate a voice-based interface into NASA’s Platform for Autonomous Systems (NPAS) software. This required technologies to convert voice to text, conduct semantic interpretations, and convert responses from the autonomous system to text and to speech; additionally, the spacecraft background noise environment was assessed, a noise mitigation technique was developed, and a relatable personality for the autonomous system was developed in order to facilitate human-like conversations. The success of our effort was largely due to the diversity of the team that included expertise in Space Systems Engineering, Human Computer Interaction, Aerospace Engineering, Computer Science, Biomedical Engineering, and Applied Physics. The diverse perspectives fostered elaborate discussions, resulting in the conception of three main subsystems: (1) User-System, (2) NPAS-System, and (3) Environment-System. The VUI was unique and had to be efficient and intuitive. For this project, 5 subteams were formed, each with a separate objective, Voice Design team, Background Noise Mitigation team, Software Integration team and Graphical User Interface team. The BLiSS team crafted a personality for the VUI to enable human-like conversation and drive user adoption and trust. User surveys were completed and used to help determine the required VUI system personality traits by capturing perspectives and expectations of prospective “Artemis Generation Astronauts”. To further simulate human-like conversations, the system had to be able to quickly interpret user speech and be able to integrate with NASA’s NPAS platform for quick and reliable information transfer. The outcomes of our research were: (1) a working prototype user interface, that is compatible with NASA’s NPAS platform; (2) software that demonstrates the ability of the VUI system to interpret user requests and respond appropriately; (3) the capability to implement fully expanded conversations between user and system using intuitive communication in four request categories; and (4) software and hardware recommendations that optimize the system’s ability to operate in a noisy environment. Our research has laid the foundation for the development of VUI’s for autonomy, and provides a baseline for future VUI developments.

Voice user interface↗

DOE OSTI2025

Medium Voltage Testbed for Comparing Advanced Power Line Sensors vs. Transformers with Electrical Grid Events

Electrical utilities have relied upon potential transformers (PTs) and current transformers (CTs) for very accurate metering and to provide reliable signals for protective relays. These devices measure phase voltages and currents and are commissioned by electrical engineers. PTs/CTs can detect and react to various electrical anomalies that could adversely affect electrical grid operations. Less expensive alternative sensing technologies offer the possibility of wider deployment, particularly in grids that employ distributed energy resources. In this work, the performance of an advanced medium-voltage sensor is compared with that of a reference PT and a CT and experimentally evaluated for different power grid scenarios on an advanced outdoor power line sensor testbed at the U.S. Department of Energy’s Oak Ridge National Laboratory. The sensor is based on a capacitive divider for voltage monitoring and a Rogowski coil with an integrator for current monitoring. This study simulated a power grid model based on a utility circuit at the Riverside EPB of Chattanooga. The simulation circuit was created with MATLAB/Simulink software and was integrated into an RT-LAB project to run with the OP4510 real-time simulator at the OPLST. During the tests, the real-time simulations were run for 40 s, and the signal to record the test event with the power meter was set at 30 s for the event-trigger circuit. The advanced outdoor power line sensor testbed has a real-time simulator that is used to generate transient scenarios (e.g., electrical faults, capacitor bank operation, and service restoration), while the analog signals are recorded by the same high-resolution power meter. The behaviors of analog signals, harmonic components, total harmonic distortion, and crest factors are assessed for this power line sensor and compared with those of the reference PT/CT because of the absence of testing standards for advanced outdoor power line sensors. The results showed that this OPLS technology responded identically to the PT and CT under all conditions.

Piesciorovsky, Emilio [ORNL]↗

NASA NTRS2006

Modern Design of Resonant Edge-Slot Array Antennas

Resonant edge-slot (slotted-waveguide) array antennas can now be designed very accurately following a modern computational approach like that followed for some other microwave components. This modern approach makes it possible to design superior antennas at lower cost than was previously possible. Heretofore, the physical and engineering knowledge of resonant edge-slot array antennas had remained immature since they were introduced during World War II. This is because despite their mechanical simplicity, high reliability, and potential for operation with high efficiency, the electromagnetic behavior of resonant edge-slot antennas is very complex. Because engineering design formulas and curves for such antennas are not available in the open literature, designers have been forced to implement iterative processes of fabricating and testing multiple prototypes to derive design databases, each unique for a specific combination of operating frequency and set of waveguide tube dimensions. The expensive, time-consuming nature of these processes has inhibited the use of resonant edge-slot antennas. The present modern approach reduces costs by making it unnecessary to build and test multiple prototypes. As an additional benefit, this approach affords a capability to design an array of slots having different dimensions to taper the antenna illumination to reduce the amplitudes of unwanted side lobes. The heart of the modern approach is the use of the latest commercially available microwave-design software, which implements finite-element models of electromagnetic fields in and around waveguides, antenna elements, and similar components. Instead of building and testing prototypes, one builds a database and constructs design curves from the results of computational simulations for sets of design parameters. The figure shows a resonant edge-slot antenna designed following this approach. Intended for use as part of a radiometer operating at a frequency of 10.7 GHz, this antenna was fabricated from dimensions defined exclusively by results of computational simulations. The final design was found to be well optimized and to yield performance exceeding that initially required.

Gosselin, R. B.↗

NASA NTRS2021

Combined Cycle Engine Large-Scale Inlet for Mode Transition Studies: System Identification Rack Software Design

This report describes the development of the system identification (SysID) rack custom application code. This code is used to automate the system identification experimental processes for the National Aeronautics and Space Administration (NASA) Combined Cycle Engine Large-Scale Inlet for Mode Transition Experiments testbed. This series of experiments took place in the NASA Glenn Research Center (GRC) 10 foot by 10 foot (10x10) Supersonic Wind Tunnel (SWT) test facility. The SysID code was developed to apply command signals to testbed actuators, receive actuator feedback signals, and acquire sensor data which is used to identify the dynamics of the experimental processes. This code development and the process identification experiments were conducted during Phase-2 testing at various operating points. These points were predefined from data collected during the Phase-1 testbed characterization experiments. The developed SysID code was executed on a NASA designed and built real-time data acquisition (DAQ) and controls (SysID) rack. This report focuses on the development of the SysID rack real-time DAQ and control hardware and the custom application code used to automate the system identification process. The implementation of this reliable and efficient data acquisition and controls development tool is demonstrated by presenting an example of experimental data collected to be used for system identification.

R Thomas↗

NASA NTRSDate not supplied

Towards Autonomous Lunar Resource Excavation via Reinforcement Learning

To continue on a sustainable and flexible path, NASA needs to address the challenge of collecting and moving large amounts of regolith at the destination. NASA’s Regolith Advanced Surface Systems Operations Robot (RASSOR) is principally designed to mine and deliver regolith for In-Situ Resource Utilization (ISRU) processing. RASSOR’s design enables it to efficiently collect and deposit regolith, return collected material for processing, and myriad related ISRU activities. To reliably perform these operations on the lunar surface, RASSOR software and sensory systems need to be robust and maximize the information extracted from a reduced sensor payload. Herein, we present preliminary findings from the Intelligent Capabilities Enhanced RASSOR project. We created reduced-order simulation environments to develop autonomous trenching controllers via reinforcement learning and prototype state estimation architectures. The goal of reinforcement learning is for an agent to learn a policy (task strategy) through interactions with an environment. When the agent performs an action, a change occurs in environment state and a numerical reward is received which informs the agent whether the action performed was good or not. Since reinforcement learning algorithms learn through trial-and-error, a simulation is a desirable first environment for development and learning. We developed two simulations, the first is a 2D excavation simulation developed to facilitate parameter selection, and a 3D simulation developed using a game physics engine, to simulate simplified soil interactions and increase the fidelity of the dynamic models of the robotic agents. The development of this 3D simulation has enabled the training of additional sensing capabilities and research both at the granular mechanics and operations levels. We experimented with various virtual sensor payloads to identify a combination that enabled efficient excavation operation and learning. Our reward function is based on how much material is excavated per step. A penalty is also received for leaving the dig site and to smooth the acceleration of the drum arms. We implemented pseudo time-of-flight sensors to report distance from each drum to ground and the height above ground which was found to be more efficient than existing solutions. Our findings suggest that reinforcement learning for autonomous operations has learned viable trenching strategies within 3000 training episodes in our simplified 2D environment and helped identify desirable sensing capabilities, arrangements, and considerations such as the positioning of time-of-flight sensors. Future work includes expanding our simulation to more complex environments and scenarios, and transfer learning from simulation to RASSOR 2.0 hardware for deployment in the Regolith Test Bin at NASA's Kennedy Space Center.

rassor↗