Predictive Control for Autonomous Driving With Uncertain, Multimodal Predictions
Not provided.
Automation & Control Systems↗
SEARCH · Search NASA
Results for “Autonomous Control”
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 4-D approach to visual control of autonomous systems
Development of a 4-D approach to dynamic machine vision is described. Core elements of this method are spatio-temporal models oriented towards objects and laws of perspective projection in a foward mode. Integration of multi-sensory measurement data was achieved through spatio-temporal models as invariants for object recognition. Situation assessment and long term predictions were allowed through maintenance of a symbolic 4-D image of processes involving objects. Behavioral capabilities were easily realized by state feedback and feed-foward control.
Dickmanns, Ernst D.↗
The MAP Autonomous Mission Control System
The Microwave Anisotropy Probe (MAP) mission is the second mission in NASA's Office of Space Science low-cost, Medium-class Explorers (MIDEX) program. The Explorers Program is designed to accomplish frequent, low cost, high quality space science investigations utilizing innovative, streamlined, efficient management, design and operations approaches. The MAP spacecraft will produce an accurate full-sky map of the cosmic microwave background temperature fluctuations with high sensitivity and angular resolution. The MAP spacecraft is planned for launch in early 2001, and will be staffed by only single-shift operations. During the rest of the time the spacecraft must be operated autonomously, with personnel available only on an on-call basis. Four (4) innovations will work cooperatively to enable a significant reduction in operations costs for the MAP spacecraft. First, the use of a common ground system for Spacecraft Integration and Test (I&T) as well as Operations. Second, the use of Finite State Modeling for intelligent autonomy. Third, the integration of a graphical planning engine to drive the autonomous systems without an intermediate manual step. And fourth, the ability for distributed operations via Web and pager access.
Breed, Juile↗
A Prototype System for Ground Control Space Telerobotics
A telerobotics system is described which provides supervised autonomous control capability for time-delayed ground-remote control applications. The system includes a local site operator interface for interactive task description and a remote site task execution system. Interactive stereo graphics overlay on video is provided at the local site to update the remote environmental model. The remote site system is capable of nominal task execution as well as monitoring and reflex action. Execution utilizes multiple control modules which execute based upon command parameterization.
robotics autonomous control telerobotics manipulat↗
A fault tolerant design for autonomous attitude control of the DSCS-III communication satellite
The first of a new series of satellites, which will provide the principal elements in the Defense Space Communications System (DSCS), was launched on Oct. 31, 1982. This satellite, DSCS-III, is part of a system which will consist of super-high frequency communications satellites in synchronous, equatorial orbits, continuously operating in four widely separate geographic regions. The DSCS-III is designed both to maintain critical communications in the presence of an electronic jamming threat and to survive nuclear radiation exposure. The results of the present investigation are to provide a basis for the design of a spacecraft tolerant of on-board failures, survivable against external threats, and capable of performing its mission autonomously for periods as long as six months.
Matijevic, J.↗
Limits to ground control in autonomous spacecraft
In this paper the autonomy concept used by ESA and NASA is critically evaluated. Moreover, a more proper ground control/spacecraft organizational structure is proposed on the basis of a new, more elaborated concept of autonomy. In an extended theoretical discussion its definitional properties and functionalities are established. The rather basic property of adaptivity leads to the categorization of behaviour into the modes of satisfaction and avoidance behaviour. However, the autonomy property with the most profound consequences is goal-robustness. The mechanism that implements goal-robustness tests newly generated goals and externally received goals on consistency with high-level goals. If goals appear not to be good instantiations or more acceptable replacements of existing goals, they are rejected. This means that ground control has to cooperate with the spacecraft instead of (intermittently) commanding it.
Wan, Alfred D. M.↗
Autonomous Detector Control and Fast Data Processing for sPHENIX and future EIC detectors
Explore the source record for details and available documents.
Atomic, Nuclear and Particle Physics↗
Autonomous Inverter Controls for Resilient and Secure Grid Operation: Vector Control Design for Grid Forming
The project addresses both fundamental and practical challenges of GFM/GFL inverter control for the power grids with high inverter based resources (IBRs) penetration. A data- driven modeling technique is applied to accurately model dynamics of PWM inverters, including electromagnetic-transient (EMT). Systematic and integrative designs of grid- forming (GFM) and grid-following (GFL) primary controls are developed to guarantee system performance under either normal or abnormal operating conditions without violating constraints. This modeling and control framework provides black-start capability in case of an outage without relying on rotating generators, and its secondary control is also shown to enhance resilience against cyber-physical attacks.
14 SOLAR ENERGY↗
Intelligent experiments through real-time AI: Fast Data Processing and Autonomous Detector Control for sPHENIX and future EIC detectors (Phase-I)
With an ever increasing demand for high precision data from modern detectors for discovery science and precision measurements, all major high energy nuclear and particle experiments, current and future, are facing the challenge on how to deal with the large volume of raw data generated from sophisticated state-of-the-art detectors in high rate collisions. These goals need to be balanced with available hardware and cost limits on DAQ (Data AcQuisition system) bandwidth and offline computing resources to capture, store and process the signal events. Two prototypical examples are the upcoming sPHENIX experiment, the DOE next generation heavy ion physics experiment at the Relativistic Heavy Ion Collider at BNL, and the future EIC experiments that are planned to be online circa 2030.
72 PHYSICS OF ELEMENTARY PARTICLES AND FIELDS↗
ARCH Technology Snapshot Autonomous Robot Control Hierarchy (ARCH): A universal software system that removes the need to rebuild robotic software for every new platform or task
Robots are increasingly used to perform repetitive, hazardous, and time-sensitive tasks, improving safety and operational efficiency. However, most robotic systems remain difficult to adapt because they are tightly tied to specific hardware and require extensive reprogramming for each new configuration.
42 ENGINEERING↗
Intelligent experiments through real-time AI: Fast Data Processing and Autonomous Detector Control for sPHENIX and future EIC detectors
This R&D project, initiated by the DOE Nuclear Physics AI-Machine Learning initiative in 2022, leverages AI to address data processing challenges in high-energy nuclear experiments (RHIC, LHC, and future EIC). Our focus is on developing a demonstrator for real-time processing of high-rate data streams from sPHENIX experiment tracking detectors. The limitations of a 15 kHz maximum trigger rate imposed by the calorimeters can be negated by intelligent use of streaming technology in the tracking system. The approach efficiently identifies low momentum rare heavy flavor events in high-rate p+p collisions (3MHz), using Graph Neural Network (GNN) and High Level Synthesis for Machine Learning (hls4ml). Success at sPHENIX promises immediate benefits, minimizing resources and accelerating the heavy-flavor measurements. The approach is transferable to other fields. For the EIC, we develop a DIS-electron tagger using Artificial Intelligence - Machine Learning (AI-ML) algorithms for real-time identification, showcasing the transformative potential of AI and FPGA technologies in high-energy nuclear and particle experiments real-time data processing pipelines.
46 INSTRUMENTATION RELATED TO NUCLEAR SCIENCE AND ↗
Performance improvement in remote manipulation with time delay by means of a learning system.
A teleoperating system is presented that involves shared control between a human operator and a general-purpose computer-based learning machine. This setup features a trainable control network termed the autonomous control subsystem (ACS) which is able to observe the operator's control actions, learn the task at hand, and take appropriate control actions. A working ACS system is described that has been put in operation for the purpose of exploring the uses of a remote intelligence of this type. The expansion of the present system into a multifunctional learning machine capable of a greater degree of autonomy is also discussed.
Freedy, A.↗
Control - Demands mushroom as station grows
The NASA space station, which is presently in the planning stage, is to be composed of both rigid and nonrigid modules, rotating elements, and flexible appendages subjected to environmental disturbances from the earth's atmospheric gravity gradient, and magnetic field, as well as solar radiation and self-generated disturbances. Control functions, which will originally include attitude control, docking and berthing control, and system monitoring and management, will with evolving mission objectives come to encompass such control functions as articulation control, autonomous navigation, space traffic control, and large space structure control. Attention is given to the advancements in modular, distributed, and adaptive control methods, as well as system identification and hardware fault tolerance techniques, which will be required.
Szirmay, S. Z.↗
Space Station Photovoltaic power modules
Silicon cell Photovoltaic (PV) power modules are key components of the Space Station Electrical Power System (EPS) scheduled to begin deployment in 1994. Four PV power modules, providing 75 KWe of user ac power, form the cornerstone of the EPS; which is comprised of Photovoltaic (PV) power modules, Solar Dynamic (SD) power modules, and the Power Management and Distribution (PMAD) system. The PV modules are located on rotating outboard sections of the Space Station (SS) structure and each module incorporates its own nickel-hydrogen energy storage batteries, its own thermal control system, and some autonomous control features. The PV modules are a cost-effective and technologically mature approach for providing reliable SS electrical power and are a solid base for EPS growth, which is expected to reach 300 KWe by the end of the Space Station's 30-year design lifetime.
Tatro, Charles A.↗
Automatic learning rate adjustment for self-supervising autonomous robot control
Described is an application in which an Artificial Neural Network (ANN) controls the positioning of a robot arm with five degrees of freedom by using visual feedback provided by two cameras. This application and the specific ANN model, local liner maps, are based on the work of Ritter, Martinetz, and Schulten. We extended their approach by generating a filtered, average positioning error from the continuous camera feedback and by coupling the learning rate to this error. When the network learns to position the arm, the positioning error decreases and so does the learning rate until the system stabilizes at a minimum error and learning rate. This abolishes the need for a predetermined cooling schedule. The automatic cooling procedure results in a closed loop control with no distinction between a learning phase and a production phase. If the positioning error suddenly starts to increase due to an internal failure such as a broken joint, or an environmental change such as a camera moving, the learning rate increases accordingly. Thus, learning is automatically activated and the network adapts to the new condition after which the error decreases again and learning is 'shut off'. The automatic cooling is therefore a prerequisite for the autonomy and the fault tolerance of the system.
Arras, Michael K.↗
Adaptive artificial neural network for autonomous robot control
The topics are presented in viewgraph form and include: neural network controller for robot arm positioning with visual feedback; initial training of the arm; automatic recovery from cumulative fault scenarios; and error reduction by iterative fine movements.
Michael K Arras↗
Autonomous Reconfigurable Control Allocation (ARCA) for Reusable Launch Vehicles
The role of control allocation (CA) in modern aerospace vehicles is to compute a command vector delta(sub c) is a member of IR(sup n(sub a)) that corresponding to commanded or desired body-frame torques (moments) tou(sub c) = [L M N](sup T) to the vehicle, compensating for and/or responding to inaccuracies in off-line nominal control allocation calculations, actuator failures and/or degradations (reduced effectiveness), or actuator limitations (rate/position saturation). The command vector delta(sub c) may govern the behavior of, e.g., acrosurfaces, reaction thrusters, engine gimbals and/or thrust vectoring. Typically, the individual moments generated in response to each of the n(sub a) commands does not lie strictly in the roll, pitch, or yaw axes, and so a common practice is to group or gang actuators so that a one-to-one mapping from torque commands tau(sub c) actuator commands delta(sub c) may be achieved in an off-line computed CA function.
Hodel, A. S.↗
A Fundamental Mathematical Model of a Microbial Predenitrification System
Space flight beyond Low Earth Orbit requires sophisticated systems to support all aspects of the mission (life support, real-time communications, etc.). A common concern that cuts across all these systems is the selection of information technology (IT) methodology, software and hardware architectures to provide robust monitoring, diagnosis, and control support. Another dimension of the problem space is that different systems must be integrated seamlessly so that communication speed and data handling appear as a continuum (un-interrupted). One such team investigating this problem is the Advanced Integration Matrix (AIM) team whose role is to define the critical requirements expected of software and hardware to support an integrated approach to the command and control of Advanced Life Support (ALS) for future long-duration human space missions, including permanent human presence on the Moon and Mars. A goal of the AIM team is to set the foundation for testing criteria that will assist in specifying tasks, control schemes and test scenarios to validate and verify systems capabilities. This project is to contribute to the goals of the AIM team by assisting with controls planning for ALS. Control for ALS is an enormous problem it involves air revitalization, water recovery, food production, solids processing and crew. In more general terms, these systems can be characterized as involving both continuous and discrete processes, dynamic interactions among the sub-systems, nonlinear behavior due to the complex operations, and a large number of multivariable interactions due to the dimension of the state space. It is imperative that a baseline approach from which to measure performance is established especially when the expectation for the control system is complete autonomous control.
Hoo, Karlene A.↗