Results 1  10
of
14
Global solutions for nonlinear systems using qualitative reasoning
 Proc. 11th International Workshop on Qualitative Reasoning, 3140. Cortona: Istituto di Analisi Numerica C.N.R
, 1997
"... This paper explores how qualitative information can be used to improve the performance of global optimization procedures. Specically, we have constructed a nonlinear parameter estimation reasoner (nper) for nding parameter values that match an ordinary dierential equation (ode) model to observed dat ..."
Abstract

Cited by 18 (10 self)
 Add to MetaCart
(Show Context)
This paper explores how qualitative information can be used to improve the performance of global optimization procedures. Specically, we have constructed a nonlinear parameter estimation reasoner (nper) for nding parameter values that match an ordinary dierential equation (ode) model to observed data. Qualitative reasoning (qr) is used within the nper, for instance, to intelligently choose starting values for the unknown parameters and to empirically determine when the system appears to be chaotic. This enables odrpack, the nonlinear leastsquares solver that lies at the heart of this nper, to avoid terminating at local extrema in the regression landscape. odrpack is uniquely suited to this task because of its eÆciency and stability. The nper's robustness is demonstrated via a Monte Carlo analysis of simulated examples drawn from across the domain of dynamics, including systems that are nonlinear, chaotic, and noisy. It is shown to locate solutions for noisy, incomplete realworld sensor data from radiocontrolled cars used in the University of British Columbia's soccerplaying robot project. The parameter estimation scheme described in this paper is a component of pret, an implemented computer program that uses a variety of articial intelligence techniques to automate system identication  the process of inferring an internal ode model from
Maps for Verbs
, 1998
"... This paper describes a representation of the meanings of verbs based on the dynamics of interactions between two agents or objects. The representation treats interactions as having three phases, before, during and after contact. Maps for these phases are constructed. Trajectories through these maps ..."
Abstract

Cited by 10 (9 self)
 Add to MetaCart
This paper describes a representation of the meanings of verbs based on the dynamics of interactions between two agents or objects. The representation treats interactions as having three phases, before, during and after contact. Maps for these phases are constructed. Trajectories through these maps correspond to different types of interactions and are denoted by different verbs. We summarize the results of experiments on learning and reasoning with maps.
Opportunistic Modeling
 In IJCAI97 Workshop on Engineering Problems for Qualitative Reasoning
, 1997
"... System identification  the process of inferring an internal model from external observations of a system  is a routine and difficult problem faced by engineers in a variety of domains. Typically, in the hierarchy from moreabstract to lessabstract models, the model of choice is the one that i ..."
Abstract

Cited by 8 (4 self)
 Add to MetaCart
System identification  the process of inferring an internal model from external observations of a system  is a routine and difficult problem faced by engineers in a variety of domains. Typically, in the hierarchy from moreabstract to lessabstract models, the model of choice is the one that is just detailed enough to account for the properties and perspectives that are of interest for the task at hand. The main goal of the work described here was to design and implement a knowledge representation framework that allows a computer program to reason about physical systems and candidate models  ordinary differential equations (ODEs), specifically  in such a way as to find the right model at the right abstraction level as quickly as possible. A key observation about the modeling process is the following. Not only is the resulting model the least complex of all possible ones, but also the reasoning during model construction takes place at the highest possible level at any time. ...
Multimodal Reasoning for Automatic Model Construction
 In Proceedings of AAAI98
, 1998
"... This paper describes a program called Pret that automates system identication, the process of nding a dynamical model of a blackbox system. Pret performs both structural identication and parameter estimation by integrating several reasoning modes: qualitative reasoning, qualitative simulation, ..."
Abstract

Cited by 7 (4 self)
 Add to MetaCart
(Show Context)
This paper describes a program called Pret that automates system identication, the process of nding a dynamical model of a blackbox system. Pret performs both structural identication and parameter estimation by integrating several reasoning modes: qualitative reasoning, qualitative simulation, numerical simulation, geometric reasoning, constraint reasoning, resolution, reasoning with abstraction levels, declarative metalevel control, and a simple form of truth maintenance. Unlike other modeling programs that map structural or functional descriptions to model fragments, Pret combines hypotheses about the mathematics involved into candidate models that are intelligently tested against observations about the target system. We give two examples of system identication tasks that this automated modeling tool has successfully performed. The rst, a simple linear system, was chosen because it facilitates a brief and clear presentation of Pret's features and reasoning t...
Reasoning about inputoutput modeling of dynamical systems
 In Proceedings of the Third International Symposium on Intelligent Data Analysis (IDA99
, 1999
"... Abstract. The goal of inputoutput modeling is to apply a test input to a system, analyze the results, and learn something useful from the causeeffect pair. Any automated modeling tool that takes this approach must be able to reason effectively about sensors and actuators and their interactions with ..."
Abstract

Cited by 3 (1 self)
 Add to MetaCart
(Show Context)
Abstract. The goal of inputoutput modeling is to apply a test input to a system, analyze the results, and learn something useful from the causeeffect pair. Any automated modeling tool that takes this approach must be able to reason effectively about sensors and actuators and their interactions with the target system. Distilling qualitative information from sensor data is fairly easy, but a variety of difficult controltheoretic issues — controllability, reachability, and utility — arise during the planning and execution of experiments. This paper describes some representations and reasoning tactics, collectively termed qualitative bifurcation analysis, that make it possible to automate this task. 1 InputOutput Modeling System identification (SID) is the process of inferring an internal ordinary differential equation (ODE) model from external observations of a system. The computer program pret[5] automates the SID process, using a combination of artificial intelligence and system identification techniques to construct ODE models of lumpedparameter continuoustime nonlinear dynamic systems. As dimodeling specification ODE model domain math PRET data excitation sensors actuators target system Fig. 1. pret uses sensors and actuators to interact with target systems in an inputoutput approach to dynamical system modeling. agrammed in Fig. 1, pret uses domain knowledge to combine model fragments into ODEs, then employs actuators and sensors to learn more about the target system, and finally tests the ODEs against the actuator/sensor data using a body of mathematical knowledge encoded in firstorder logic[20].
Dynamic Maps as Representations of Verbs
, 1998
"... This paper describes a representation of the meanings of verbs based on the dynamics of interactions between two agents or objects. The representation treats interactions as having three phases, before, during and after contact. Maps for these phases are constructed. Trajectories through these maps ..."
Abstract

Cited by 2 (2 self)
 Add to MetaCart
This paper describes a representation of the meanings of verbs based on the dynamics of interactions between two agents or objects. The representation treats interactions as having three phases, before, during and after contact. Maps for these phases are constructed. Trajectories through these maps correspond to different types of interactions and are denoted by different verbs. We summarize the results of experiments on learning and reasoning with maps.
Putting Declarative Meta Control to Work
, 1998
"... We present a logic programming system that accomplishes three important goals: equivalence of declarative and operational semantics, declarative specification of control information, and smoothness of interaction with nonlogic based programs. The language of the system is that of Generalized Horn C ..."
Abstract

Cited by 2 (1 self)
 Add to MetaCart
(Show Context)
We present a logic programming system that accomplishes three important goals: equivalence of declarative and operational semantics, declarative specification of control information, and smoothness of interaction with nonlogic based programs. The language of the system is that of Generalized Horn Clause Intuitionistic Logic with negation as inconsistency. Meta level predicates are used to specify control information declaratively, compensating for the absence of procedural constructs that usually facilitate formulation of e# cient programs. Knowledge that has been derived in the course of the current inference process can at any time be passed to nonlogicbased program modules. Traditional SLD inference engines maintain only the linear path to the current state in the SLD search tree: formulae that have been proved on this path are implicitly represented in a stack of recursive calls to the inference engine, and formulae that have been proved on previous, unsuccessful paths are lost...
Global Solutions for Nonlinear Systems Using Qualitative Reasoning*
"... This paper explores how qualitative information can be used to improve the performance of global optimization procedures. Specifically, we have constructed a nonlinear parameter estimation reasoner (NPER) for finding parameter values that match an ordinary differential equation (ODE) model to observ ..."
Abstract
 Add to MetaCart
(Show Context)
This paper explores how qualitative information can be used to improve the performance of global optimization procedures. Specifically, we have constructed a nonlinear parameter estimation reasoner (NPER) for finding parameter values that match an ordinary differential equation (ODE) model to observed data. Qualitative reasoning (QR) is used within the NPER, for instance, to intelligently choose starting values for the unknown parameters and to empirically determine when the system appears to be chaotic. This enables odrpack, the nonlinear leastsquares solver that lies at the heart of this NPER, to avoid terminating at local extrema in the regression landscape. odrpack is uniquely suited to this task because of its efficiency and stability. The NPER's robustness is demonstrated via a Monte Carlo analysis ofsimulated examples drawn from across the domain of dynamics, including systems that are nonlinear, chaotic, and noisy. It is shown to locate solutions for noisy, incomplete realworld sensor datafrom radiocontrolled carsused in the University of British Columbia's soccerplaying robot project. The parameter estimation scheme described in this paper is a component of pret, an implemented computer program that uses a variety of artificial intelligence techniques to automate system identificationthe process ofinferring an internal ODE model from external ob
Global Solutions for Nonlinear Systems Using Qualitative Reasoning
"... 1 external observations of a system a routine and difficult problem faced by engineers from various disciplines. ..."
Abstract
 Add to MetaCart
(Show Context)
1 external observations of a system a routine and difficult problem faced by engineers from various disciplines.
Hybrid PhasePortrait Analysis in Automated System Identification
, 1999
"... We present a new representation for hybrid phaseportrait analysis, called the qualitative state/parameter space, wherein a physical system's dynamics are classified into discrete regions of qualitatively identical behavior. This classification is performed using automated phaseportrait analys ..."
Abstract
 Add to MetaCart
(Show Context)
We present a new representation for hybrid phaseportrait analysis, called the qualitative state/parameter space, wherein a physical system's dynamics are classified into discrete regions of qualitatively identical behavior. This classification is performed using automated phaseportrait analysis techniques and an abstraction scheme from the dynamical systems literature called cell dynamics. This hybrid representation is useful for inputoutput modeling of dynamical systems; among other things, it is a very natural way to reason about multiple sets of observations over a given system. Issues about the transitions between these discrete regions are analogous to many of the issues found in the hybrid systems literature. Our representation is an essential element of the inputoutput modeling component of the pret automated system identification program.