Search NASA⌕ Search

SEARCH · Search NASA

Results for “Autonomous Planning”

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.

At least 289 records · Page 16
All sourcesNASA NTRSDOE OSTI
NASA NTRS2022

Adapting a Trusted AI Framework to Space Mission Autonomy

As artificial intelligence (AI) is increasingly pro- posed for new and future capabilities in space missions, the question of how to trust AI-enabled space autonomy has been explored. Recently, a collaboration between The Aerospace Corporation (Aerospace) and NASA’s Jet Propulsion Labora- tory (JPL) investigated how Aerospace’s Trusted AI Frame- work could be applied to two JPL projects that planned on lev- eraging AI for critical autonomous tasks. This combined effort led to many insights in the practical implementation of trusted AI along with considerable updates to the Trusted AI Frame- work that tailored its topic threads to space exploration. This document cohesively summarizes the enhanced framework as tailored to space missions as well as estimation of the level of trust required as a function of mission criticality and key stakeholders. The goal of this work is to provide a set of best practices to inform autonomy researchers, flight engineers, mission and proposal reviewers, and instrument and mission principal investigators (PI’s) to drive AI-based autonomy that maximizes trust and lowers the barriers to mission adoption for both science and engineering applications.

Amini, Rashied↗
NASA NTRS1991

Priority scheme planning for the robust SSM/PMAD testbed

Whenever mixing priorities of manually controlled resources with those of autonomously controlled resources, the space station module power management and distribution (SSM/PMAD) environment requires cooperating expert system interaction between the planning function and the priority manager. The elements and interactions of the SSM/PMAD planning and priority management functions are presented. Their adherence to cooperating for common achievement are described. In the SSM/PMAD testbed these actions are guided by having a system planning function, KANT, which has insight to the executing system and its automated database. First, the user must be given access to all information which may have an effect on the desired outcome. Second, the fault manager element, FRAMES, must be informed as to the change so that correct diagnoses and operations take place if and when faults occur. Third, some element must engage as mediator for selection of resources and actions to be added or removed at the user's request. This is performed by the priority manager, LPLMS. Lastly, the scheduling mechanism, MAESTRO, must provide future schedules adhering to the user modified resource base.

Elges, Michael R.↗
NASA NTRS1999

Autonomous Formation Flying from the Ground to Flight

The cost of on-orbit operations remains a significant and increasingly visible concern in the support of satellite missions. Headway has been made in automating some ground operations; however, increased mission complexity and more precise orbital constraints have compelled continuing human involvement in mission design and maneuver planning operations. AI Solutions, Inc. in cooperation with the National Aeronautics and Space Administration's (NASA) Goddard Space Flight Center (GSFC) has tackled these more complex problems through the development of AutoCon(TM) as a tool for an automated solution. NASA is using AutoCon(TM) to automate the maneuver planning for the Earth Orbiter-1 (EO-1) mission. AutoCon(TM) was developed originally as a ground system tool. The EO-1 mission will be using a scaled version of AutoCon(TM) on-board the EO-1 satellite to command orbit adjustment maneuvers. The flight version of AutoCon(TM) plans maneuvers based on formation flying algorithms developed by GSFC, JPL, and other industry partners. In its fully autonomous mode, an AutoCon(TM) planned maneuver will be executed on-board the satellite without intervention from the ground. This paper describes how AutoCon(TM) automates maneuver planning for the formation flying constraints of the EO-1 mission. AutoCon(TM) was modified in a number of ways to automate the maneuver planning on-board the satellite. This paper describes how the interface and functionality of AutoCon(TM) were modified to support the on-board system. A significant component of this modification was the implementation of a data smoother, based on a Kalman filter, that ensures that the spacecraft states estimated by an on-board GPS receiver are as accurate as possible for maneuver planning. This paper also presents the methodology used to scale the AutoCon(TM) functionality to fit and execute on the flight hardware. This paper also presents the modes built into the system that allow the incremental phasing in of autonomy. New technologies for autonomous operations are usually received with significant, and probably appropriate, trepidation. A number of safeguards have been designed in both AutoCon(TM) and the interfacing systems to alleviate the potential of mission-impacting anomalies from the on-board autonomous system. This paper describes the error checking, input data integrity validation, and limits set on maneuvers in AutoCon(TM) and the on-board system.

Chapman, Keith B.↗
NASA NTRS2007

Improved Path Planning Onboard the Mars Exploration Rovers

A revised version of the AutoNav (autonomous navigation with hazard avoidance) software running onboard each Mars Exploration Rover (MER) affords better obstacle avoidance than does the previous version. Both versions include GESTALT (Grid-based Estimation of Surface Traversability Applied to Local Terrain), a navigation program that generates local-terrain models from stereoscopic image pairs captured by onboard rover cameras; uses this information to evaluate candidate arcs that extend across the terrain from the current rover location; ranks the arcs with respect to hazard avoidance, minimization of steering time, and the direction towards the goal; and combines the rankings in a weighted vote to select an arc, along which the rover is then driven. GESTALT works well in navigating around small isolated obstacles, but tends to fail when the goal is on the other side of a large obstacle or multiple closely spaced small obstacles. When that occurs, the goal seeking votes and hazard avoidance votes conflict severely. The hazard avoidance votes will not allow the rover to drive through the unsafe area, and the waypoint votes will not allow enough deviation from the straight-line path for the rover to get around the hazard. The rover becomes stuck and is unable to reach the goal. The revised version of AutoNav utilizes a global path-planning program, Field D*, to evaluate the cost of traveling from the end of each GESTALT arc to the goal. In the voting process, Field D* arc votes supplant GESTALT goal-seeking arc votes. Hazard avoidance, steering bias, and Field D* votes are merged and the rover is driven a preset distance along the arc with the highest vote. Then new images are acquired and the process as described is repeated until the goal is reached. This new technology allows the rovers to autonomously navigate around much more complex obstacle arrangements than was previously possible. In addition, this improved autonomy enables longer traverses per Sol (a day on Mars), and can make planning drives easier for operators on Earth.

Stentz, Anthony↗
NASA NTRS2019

A Planning Pipeline for Large Multi-Agent Missions

In complex multi-agent applications, human operators are often tasked with planning and managing large heterogeneous teams of humans and autonomous vehicles. Although the use of these autonomous vehicles broadens the scope of meaningful applications, many of their systems remain unintuitive and difficult to master for human operators whose expertise lies in the application domain and not at the platform level. Current research focuses on the development of individual capabilities necessary to plan multi-agent missions of this scope, placing little emphasis on the integration of these components in to a full pipeline. The work presented in this paper presents a complete and user-agnostic planning pipeline for large multiagent missions known as the HOLII GRAILLE. The system takes a holistic approach to mission planning by integrating capabilities in human machine interaction, flight path generation, and validation and verification. Components – modules – of the pipeline are explored on an individual level, as well as their integration into a whole system. Lastly, implications for future mission planning are discussed.

Chandarana, Meghan↗
NASA NTRS2007

The Autonomous Precision Landing and Hazard Detection and Avoidance Technology (ALHAT)

As NASA plans to send humans back to the Moon and develop a lunar outpost, technologies must be developed to place humans and cargo safely, precisely, repeatedly, on the lunar surface with the capability to avoid surface hazards. Exploration Space Architecture Study requirements include the need for global lunar surface access with safe, precise landing without lighting constraints on terrain that may have landing hazards for human scale landing vehicles. Landing accuracies of perhaps 1,000 meters for sortie crew missions to 10 s of meters for Outpost class missions are required. The Autonomous precision Landing Hazard Avoidance Technology (ALHAT) project will develop the new and unique descent and landing Guidance, Navigation and Control (GNC) hardware and software technologies necessary for these capabilities. The ALHAT project will qualify a lunar descent and landing GNC system to a Technology Readiness Level (TRL) of 6 capable of supporting lunar crewed, cargo, and robotic missions. The (ALHAT) development project was chartered by NASA Headquarters in October 2006. The initial effort to write a project plan and define an ALHAT Team was followed by a fairly aggressive research and analysis effort to determine what technologies existed that could be developed and applied to the lunar landing problems indicated above. This paper describes the project development, research, analysis and concept evolution that has occurred since the assignment of the project. This includes the areas of systems engineering, GNC, sensors, sensor algorithms, simulations, fielding testing, laboratory testing, Hardware-In-The-Loop testing, system avionics and system certification concepts.

Epp, Chirold D.↗
NASA NTRSDate not supplied

Starling Swarm Mission – Technology Objectives, Status and Future Applications

NASA’s Starling mission is advancing the readiness of technologies for cooperative groups of space craft referred to as swarms. The Starling swarm of four 6U spacecraft launched in July 2023, and is completing its tests in Low Earth Orbit (LEO) of four key technologies that will enable future swarm missions: onboard maneuver planning and execution to adjust the swarm formation; establishing and maintaining an adhoc network in space; relative and absolute orbit determination using optical sensors; autonomous collaboration between spacecraft for establishing and conducting a science observation plan. A mission extension is also being prepared to demonstrate a space traffic management architecture to address the large and rapidly growing number of space craft in LEO. In this presentation, the objectives of the Starling mission and its extension will be reviewed along with the latest status and mission outcomes. The presentation will also look at the revolutionary potential for swarms in future science and exploration missions and the impact to operations.

SpaceOps Starling Swarm Distributed Spacecraft Net↗
NASA NTRS2004

A Software Architecture for Semiautonomous Robot Control

A software architecture has been developed to increase the safety and effectiveness with which tasks are performed by robots that are capable of functioning autonomously but sometimes are operated under control by humans. The control system of such a robot designed according to a prior software architecture has no way of taking account of how the environment has changed or what parts of a task were performed during an interval of control by a human, so that errors can occur (and, hence, safety and effectiveness jeopardized) when the human relinquishes control. The present architecture incorporates the control, task-planning, and sensor-based-monitoring features of typical prior autonomous-robot software architectures, plus features for updating information on the environment and planning of tasks during control by a human operator in order to enable the robot to track the actions taken by the operator and to be ready to resume autonomous operation with minimal error. The present architecture also provides a user interface that presents, to the operator, a variety of information on the internal state of the robot and the status of the task.

Kortenkamp, David↗
NASA NTRS2018

Serious Gaming for Building a Basis of Certification via Trust and Trustworthiness of Autonomous Systems

Autonomous systems governed by a variety of adaptive and nondeterministic algorithms are being planned for inclusion into safety-critical environments, such as unmanned aircraft and space systems in both civilian and military applications. However, until autonomous systems are proven and perceived to be capable and resilient in the face of unanticipated conditions, humans will be reluctant or unable to delegate authority, remaining in control aided by machine-based information and decision support. Proving capability, or trustworthiness, is a necessary component of certification. Perceived capability is a component of trust. Trustworthiness is an attribute of a cyber-physical system that requires context-driven metrics to prove and certify. Trust is an attribute of the agents participating in the system and is gained over time and multiple interactions through trustworthy behavior and transparency. Historically, artificial intelligence and machine learning systems provide answers without explanation - without a rationale or insight into the machine “thinking”. In order to function as trusted teammates, machines must be able to explain their decisions and actions. This transparency is a product of both content and communication. NASA’s Autonomy Teaming & TRAjectories for Complex Trusted Operational Reliability (ATTRACTOR) project seeks to build a basis for certification of autonomous systems via establishing metrics for trustworthiness and trust in multi-agent team interactions, using AI (Artificial Intelligence) explainability and persistent modeling and simulation, in the context of mission planning and execution, with analyzable trajectories. Inspired by Massively Multiplayer Online Role Playing Games (MMORPG) and Serious Gaming, the proposed ATTRACTOR modeling and simulation environment is similar to online gaming environments in which player (aka agent) participants interact with each other, affect their environment, and expect the simulation to persist and change regardless of any individual agent’s active participation. This persistent simulation environment will accommodate individual agents, groups of self-organizing agents, and large-scale infrastructure behavior. The effects of the emerging adaptation and coevolution can be observed and measured to building a basis of measurable trustworthiness and trust, toward certification of safety-critical autonomous systems.

Allen, B. Danette↗
NASA NTRS2001

Model Checking the Remote Agent Planner

This work tackles the problem of using Model Checking for the purpose of verifying the HSTS (Scheduling Testbed System) planning system. HSTS is the planner and scheduler of the remote agent autonomous control system deployed in Deep Space One (DS1). Model Checking allows for the verification of domain models as well as planning entries. We have chosen the real-time model checker UPPAAL for this work. We start by motivating our work in the introduction. Then we give a brief description of HSTS and UPPAAL. After that, we give a sketch for the mapping of HSTS models into UPPAAL and we present samples of plan model properties one may want to verify.

Khatib, Lina↗
NASA NTRS1995

STS-64 Space Shuttle mission report

The STS-64 Space Shuttle Program Mission Report summarizes the Payload activities as well as the Orbiter, External Tank (ET), Solid Rocket Booster (SRB), Redesigned Solid Rocket Motor (RSRM), and the Space Shuttle main engine (SSME) systems performance during the sixty-fourth flight of the Space Shuttle Program and the nineteenth flight of the Orbiter vehicle Discovery (OV-103). In addition to the Orbiter, the flight vehicle consisted of an ET that was designated ET-66; three SSMEs that were designated as serial numbers 2031, 2109, and 2029 in positions 1, 2, and 3, respectively; and two SRB's that were designated Bl-068. The RSRM's that were installed in each SRB were designated as 360L041 A for the left SRB, and 360L041 B for the right SRB. The primary objective of this flight was to successfully perform the planned operations of the Lidar In-Space Technology Experiment (LITE), and to deploy the Shuttle Pointed Autonomous Research Tool for Astronomy (SPARTAN) -201 payload. The secondary objectives were to perform the planned activities of the Robot Operated Materials Processing System (ROMPS), the Shuttle Amateur Radio Experiment - 2 (SAREX-2), the Solid Surface Combustion Experiment (SSCE), the Biological Research in Canisters (BRIC) experiment, the Radiation Monitoring Equipment-3 (RME-3) payload, the Military Application of Ship Tracks (MAST) experiment, and the Air Force Maui Optical Site Calibration Test (AMOS) payload.

Fricke, Robert W., Jr.↗
NASA NTRS1991

The SERENDIP 2 SETI project: Current status

Over the past 30 years, interest in extraterrestrial intelligence has progressed from philosophical discussion to rigorous scientific endeavors attempting to make contact. Since it is impossible to assess the probability of success and the amount of telescope time needed for detection, Search for Extraterrestrial Intelligence (SETI) Projects are plagued with the problem of attaining the large amounts of time needed on the world's precious few large radio telescopes. To circumvent this problem, the Search for Extraterrestrial Radio Emissions from Nearby Developed Intelligent Populations (SERENDIP) instrument operates autonomously in a piggyback mode utilizing whatever observing plan is chosen by the primary observer. In this way, large quantities of high-quality data can be collected in a cost-effective and unobtrusive manner. During normal operations, SERENDIP logs statistically significant events for further offline analysis. Due to the large number of terrestrial and near-space transmitters on earth, a major element of the SERENDIP project involves identifying and rejecting spurious signals from these sources. Another major element of the SERENDIP Project (as well as most other SETI efforts) is detecting extraterrestrial intelligence (ETI) signals. Events selected as candidate ETI signals are studied further in a targeted search program which utilizes between 24 to 48 hours of dedicated telescope time each year.

Bowyer, C. S.↗
NASA NTRS2003

Actions, Observations, and Decision-Making: Biologically Inspired Strategies for Autonomous Aerial Vehicles

This paper details the development and demonstration of an autonomous aerial vehicle embodying search and find mission planning and execution srrategies inspired by foraging behaviors found in biology. It begins by describing key characteristics required by an aeria! explorer to support science and planetary exploration goals, and illustrates these through a hypothetical mission profile. It next outlines a conceptual bio- inspired search and find autonomy architecture that implements observations, decisions, and actions through an "ecology" of producer, consumer, and decomposer agents. Moving from concepts to development activities, it then presents the results of mission representative UAV aerial surveys at a Mars analog site. It next describes hardware and software enhancements made to a commercial small fixed-wing UAV system, which inc!nde a ncw dpvelopnent architecture that also provides hardware in the loop simulation capability. After presenting the results of simulated and actual flights of bioinspired flight algorithms, it concludes with a discussion of future development to include an expansion of system capabilities and field science support.

Pisanich, Greg↗
NASA NTRS2009

NASA Global Hawk: A New Tool for Earth Science Research

This slide presentation reviews the Global Hawk, a unmanned aerial vehicle (UAV) that NASA plans to use for Earth Sciences research. The Global Hawk is the world's first fully autonomous high-altitude, long-endurance aircraft, and is capable of conducting long duration missions. Plans are being made for the use of the aircraft on missions in the Arctic, Pacific and Western Atlantic Oceans. There are slides showing the Global Hawk Operations Center (GHOC), Flight Control and Air Traffic Control Communications Architecture, and Payload Integration and Accommodations on the Global Hawk. The first science campaign, planned for a study of the Pacific Ocean, is reviewed.

Hall, Phill↗
NASA NTRS2003

Revolutionary Deep Space Science Missions Enabled by Onboard Autonomy

Breakthrough autonomy technologies enable a new range of spire missions that acquire vast amounts of data and return only the most scientifically important data to Earth. These missions would monitor science phenomena in great detail (either with frequent observations or at extremely high spatial resolution) and onboard analyze the data to detect specific science events of interest. These missions would monitor volcanic eruptions, formation and movement of aeolian features. and atmospheric phenomena. The autonomous spacecraft would respond to science events by planning its future operations to revisit or perform complementary observations. In this paradigm, the spacecraft represents the scientists agent enabling optimization of the downlink data volume resource. This paper describes preliminary efforts to define and design such missions.

autonomy↗
NASA NTRS2017

Preliminary Results from a Model-Driven Architecture Methodology for Development of an Event-Driven Space Communications Service Concept

NASA's next generation space communications network will involve dynamic and autonomous services analogous to services provided by current terrestrial wireless networks. This architecture concept, known as the Space Mobile Network (SMN), is enabled by several technologies now in development. A pillar of the SMN architecture is the establishment and utilization of a continuous bidirectional control plane space link channel and a new User Initiated Service (UIS) protocol to enable more dynamic and autonomous mission operations concepts, reduced user space communications planning burden, and more efficient and effective provider network resource utilization. This paper provides preliminary results from the application of model driven architecture methodology to develop UIS. Such an approach is necessary to ensure systematic investigation of several open questions concerning the efficiency, robustness, interoperability, scalability and security of the control plane space link and UIS protocol.

Roberts, Christopher J.↗
NASA NTRSDate not supplied

Aircraft Classification Using Radar from Small Unmanned Aerial Systems for Scalable Traffic Management Emergency Response Operations

This work investigates two machine learning techniques: Support Vector Machine (SVM) and Autoencoders (AE)with SVM layer for classification of radar trajectories as General Aviation (GA), fixed-wing small Unmanned Aerial System (sUAS), or not-an-aircraft using radar data recorded from sUAS. Onboard identification of intruder aircraft type is useful for planning avoidance maneuvers and is necessary to provide autonomous systems to meet or exceed the avoidance capability of a human pilot. Aircraft classification can identify intruder aircraft that are not part of the team and may be violating a Temporary Flight Restriction. Aircraft classification is needed in monitoring an airspace where multiple aircraft are teaming on a shared task. Scalable Traffic Management for Emergency Response Operations (STEReO) is a NASA project aimed at improving disaster response by enabling large scale aircraft operations through the teaming of manned aircraft with sUAS to maximize emergency response resources. To this end, this work uses trajectories and radar derived features to classify aircraft from a multirotor sUAS. The AE + SVM generated the strongest classification overall accuracy of 93.5% using the first 4 seconds of radar track data for tracks that activated the avoidance system. Subsampling the available track data increased the available training data with the maximum aircraft recall of 0.94 achieved using the SVM with 1 second track data.

Chester V. Dolph↗