Knowledge Representation and Reasoning for Fault Identification in a Space Robot Arm (original) (raw)
Related papers
Diagnosis as a variable assignment problem: a case study in a space robot fault diagnosis
INTERNATIONAL JOINT CONFERENCE ON ARTIFICIAL INTELLIGENCE, 1999
In the present paper we introduce the notion of Variable Assignment Problem (VAP) as an abstract framework for characterizing diagnosis. Components of the system to be diagnosed are put in correspondence with variables, behavioral modes of the components are the values of the variables and a diagnosis is a variable assignment which explains the observations of the diagnostic problem, by considering the constraints put by the domain theory. In order to have a concise representation of diagnoses and to reduce the search ...
This paper introduces a software prototype called ARPHA for on-board diagnosis, prognosis and recovery. The goal is to allow the design of an innovative on-board FDIR (Fault Detection, Identification and Recovery) process for autonomous systems, able to deal with uncertain system/environment interactions, uncertain dynamic system evolution, partial observability and detection of recovery policies taking into account imminent failures. We propose to base the inference engine of ARPHA on Dynamic Probabilistic Graphical Models suitable to reason about system evolution with control actions, over a finite time horizon. The model needed by ARPHA is derived from standard dependability modeling, exploiting an extension of the Dynamic Fault Tree language, called EDFT. We finally discuss the software architecture of ARPHA, where on-board FDIR is implemented and we provide some preliminary results on simulation scenarios for Mars rover activities
is paper introduces a software prototype called ARPA for on-board diagnosis, prognosis and recovery. e goal is to allow the design of an innovative on-board R (ault etection, dentification and Recovery) process for autonomous systems, able to deal with uncertain system/environment interactions, uncertain dynamic system evolution, partial observability and detection of recovery policies taking into account imminent failures. We propose to base the inference engine of ARPA on ynamic Probabilistic Graphical Models suitable to reason about system evolution with control actions, over a finite time horizon. e model needed by ARPA is derived from standard dependability modeling, exploiting an extension of the ynamic ault Tree language, called T. We finally discuss the software architecture of ARPA, where on-board R is implemented and we provide some preliminary results on simulation scenarios for Mars rover activities. Acta utura (0) / -0 . odetta-Raiteri at al.
Real-time reasoning: the monitoring and control of spacecraft systems
Sixth Conference on Artificial Intelligence for Applications, 1990
This paper describes research concerned with automating the monitoring and control of spacecraft systems. In particular, the paper examines the application of SRI'S Procedural Reasoning System (PRS) to the handling of malfunctions in the Reaction Control System (RCS) of NASA's space shuttle. Unlike traditional monitoring and control systems, PRS is able to reason about and perform complex tasks in a very flexible and robust manner, somewhat in the manner of a human assistant. Using various RCS malfunctions as examples (including sensor faults, leaking components, multiple alarms, and regulator and jet failures), it is shown how PRS manages to combine both goal-directed reasoning and the ability to react rapidly to unanticipated changes in its environment. In conclusion, some important issues in the design of PRS are reviewed and future enhancements are indicated.
A System for Fault Management for NASA's Deep Space Habitat
NASA's exploration program envisions the utilization of a Deep Space Habitat (DSH) for human exploration of the space environment in the vicinity of Mars and/or asteroids. Communication latencies with ground control of as long as 20+ minutes make it imperative that DSH operations be highly autonomous, as any telemetry-based detection of a systems problem on Earth could well occur too late to assist the crew with the problem. A DSH-based development program has been initiated to develop and test the automation technologies necessary to support highly autonomous DSH operations. One such technology is a fault management tool to support performance monitoring of vehicle systems operations and to assist with real-time decision making in connection with operational anomalies and failures. Toward that end, we are developing Advanced Caution and Warning System (ACAWS), a tool that combines dynamic and interactive graphical representations of spacecraft systems, systems modeling, automated diagnostic analysis and root cause identification, system and mission impact assessment, and mitigation procedure identification to help spacecraft operators (both flight controllers and crew) understand and respond to anomalies more effectively. In this paper, we describe four major architecture elements of ACAWS: Anomaly Detection, Fault Isolation, System Effects Analysis, and Graphic User Interface (GUI), and how these elements work in concert with each other and with other tools to provide fault management support to both the controllers and crew. We then describe recent evaluations and tests of ACAWS on the DSH testbed. The results of these tests support the feasibility and strength of our approach to failure management automation and enhanced operational autonomy.
Risks evaluation and Failures Diagnosis for Autonomous tasks execution in Space
2001
We present a control system for autonomous manipulators based on a theory of actions integrated with a theory of perception and failures. The theory of actions, perception and failures is defined in the Situation Calculus, a logical language that allows the representation of dynamic domains. We assume that an au- tonomous agent is provided with a set of possible goals.
Design of the Remote Agent experiment for spacecraft autonomy
1998
This paper describes the Remote Agent flight experiment for spacecraft commanding and control. In the Remote Agent approach, the operational rules and constraints are encoded in the flight software. The software may be considered to be an autonomous “remote agent” of the spacecraft operators in the sense that the operators rely on the agent to achieve particular goals. The experiment will be executed during the flight of NASA's Deep Space One technology validation mission. During the experiment, the spacecraft will not be given the usual detailed sequence of commands to execute. Instead, the spacecraft will be given a list of goals to achieve during the experiment. In flight, the Remote Agent flight software will generate a plan to accomplish the goals and then execute the plan in a robust manner while keeping track of how well the plan is being accomplished. During plan execution, the Remote Agent stays on the lookout for any hardware faults that might require recovery actions or replanning. In addition to describing the design of the remote agent, this paper discusses technology-insertion challenges and the approach used in the Remote Agent approach to address these challenges. The experiment integrates several spacecraft autonomy technologies developed at NASA Ames and the Jet Propulsion Laboratory: on-board planning, a robust multi threaded executive, and model-based failure diagnosis and recovery
ADVOCATE II: ADVanced On-Board Diagnosis and Control of Autonomous Systems II
Lecture Notes in Computer Science, 2003
A way to improve the reliability and to reduce costs in autonomous robots is to add intelligence to on-board diagnosis and control systems to avoid expensive hardware redundancy and inopportune mission abortion. According to this, the main goal of the ADVOCATE II project is to adapt legacy piloting software around a generic SOAP (Simple Object Access Protocol) architecture on which intelligent modules could be plugged. Artificial Intelligent (AI) modules using Belief Bayesian Networks (BBN), Neuro-Symbolic Systems (NSS), and Fuzzy Logic (FL) are coordinated to help the operator or piloting system manage fault detection, risk assessment, and recovery plans. In this paper, the specification of the ADVOCATE II system is presented.