Task-Level Robot Learning

We are investigating how to program robots so that they learn from experience. Our goal is to develop principled methods of learning that can improve a robot's performance of a wide range of dynamic tasks. We have developed task-level learning that successfully improves a robot's performance of two complex tasks, ball-throwing and juggling. With task- level learning, a robot practices a task, monitors its own performance, and uses that experience to adjust its task-level commands. This learning method serves to complement other approaches, such as model calibration, for improving robot performance.

Generative Temporal Planning with Complex Processes

Autonomous vehicles are increasingly being used in mission-critical applications, and robust methods are needed for controlling these inherently unreliable and complex systems. This thesis advocates the use of model-based programming, which allows mission designers to program autonomous missions at the level of a coach or wing commander. To support such a system, this thesis presents the Spock generative planner. To generate plans, Spock must be able to piece together vehicle commands and team tactics that have a complex behavior represented by concurrent processes. This is in contrast to traditional planners, whose operators represent simple atomic or durative actions. Spock represents operators using the RMPL language, which describes behaviors using parallel and sequential compositions of state and activity episodes. RMPL is useful for controlling mobile autonomous missions because it allows mission designers to quickly encode expressive activity models using object-oriented design methods and an intuitive set of activity combinators. Spock also is significant in that it uniformly represents operators and plan-space processes in terms of Temporal Plan Networks, which support temporal flexibility for robust plan execution. Finally, Spock is implemented as a forward progression optimal planner that walks monotonically forward through plan processes, closing any open conditions and resolving any conflicts. This thesis describes the Spock algorithm in detail, along with example problems and test results.

Preliminary Observations on Program Instability

This white paper reports emerging findings at the end of Phase I of the Lean Aircraft Initiative in the Policy focus group area. Specifically, it provides details about research on program instability. Its objective is to discuss high-level findings detailing: 1) the relative contribution of different factors to a program’s overall instability; 2) the cost impact of program instability on acquisition programs; and 3) some strategies recommended by program managers for overcoming and/or mitigating the negative effects of program instability on their programs. Because this report comes as this research is underway, this is not meant to be a definitive document on the subject. Rather, is it anticipated that this research may potentially produce a number of reports on program instability-related topics. The government managers of military acquisition programs rated annual budget or production rate changes, changes in requirements, and technical difficulties as the three top contributors, respectively, to program instability. When asked to partition actual variance in their program’s planned cost and schedule to each of these factors, it was found that the combined effects of unplanned budget and requirement changes accounted for 5.2% annual cost growth and 20% total program schedule slip. At a rate of approximately 5% annual cost growth from these factors, it is easy to see that even conservative estimates of the cost benefits to be gained from acquisition reforms and process improvements can quickly be eclipsed by the added cost associated with program instability. Program management practices involving the integration of stakeholders from throughout the value chain into the decision making process were rated the most effective at avoiding program instability. The use of advanced information technologies was rated the most effective at mitigating the negative impact of program instability.

Preliminary Observations on Program Instability

This white paper reports emerging findings at the end of Phase I of the Lean Aircraft Initiative in the Policy focus group area. Specifically, it provides details about research on program instability. Its objective is to discuss high-level findings detailing: 1) the relative contribution of different factors to a program’s overall instability; 2) the cost impact of program instability on acquisition programs; and 3) some strategies recommended by program managers for overcoming and/or mitigating the negative effects of program instability on their programs. Because this report comes as this research is underway, this is not meant to be a definitive document on the subject. Rather, is it anticipated that this research may potentially produce a number of reports on program instability-related topics. The government managers of military acquisition programs rated annual budget or production rate changes, changes in requirements, and technical difficulties as the three top contributors, respectively, to program instability. When asked to partition actual variance in their program’s planned cost and schedule to each of these factors, it was found that the combined effects of unplanned budget and requirement changes accounted for 5.2% annual cost growth and 20% total program schedule slip. At a rate of approximately 5% annual cost growth from these factors, it is easy to see that even conservative estimates of the cost benefits to be gained from acquisition reforms and process improvements can quickly be eclipsed by the added cost associated with program instability. Program management practices involving the integration of stakeholders from throughout the value chain into the decision making process were rated the most effective at avoiding program instability. The use of advanced information technologies was rated the most effective at mitigating the negative impact of program instability.

Concurrent Aggregates (CA): An Object-Oriented Language for Fine-Grained Message-Passing Machines

Fine-grained parallel machines have the potential for very high speed computation. To program massively-concurrent MIMD machines, programmers need tools for managing complexity. These tools should not restrict program concurrency. Concurrent Aggregates (CA) provides multiple-access data abstraction tools, Aggregates, which can be used to implement abstractions with virtually unlimited potential for concurrency. Such tools allow programmers to modularize programs without reducing concurrency. I describe the design, motivation, implementation and evaluation of Concurrent Aggregates. CA has been used to construct a number of application programs. Multi-access data abstractions are found to be useful in constructing highly concurrent programs.

Building Grounded Abstractions for Artificial Intelligence Programming

Most Artificial Intelligence (AI) work can be characterized as either ``high-level'' (e.g., logical, symbolic) or ``low-level'' (e.g., connectionist networks, behavior-based robotics). Each approach suffers from particular drawbacks. High-level AI uses abstractions that often have no relation to the way real, biological brains work. Low-level AI, on the other hand, tends to lack the powerful abstractions that are needed to express complex structures and relationships. I have tried to combine the best features of both approaches, by building a set of programming abstractions defined in terms of simple, biologically plausible components. At the ``ground level'', I define a primitive, perceptron-like computational unit. I then show how more abstract computational units may be implemented in terms of the primitive units, and show the utility of the abstract units in sample networks. The new units make it possible to build networks using concepts such as long-term memories, short-term memories, and frames. As a demonstration of these abstractions, I have implemented a simulator for ``creatures'' controlled by a network of abstract units. The creatures exist in a simple 2D world, and exhibit behaviors such as catching mobile prey and sorting colored blocks into matching boxes. This program demonstrates that it is possible to build systems that can interact effectively with a dynamic physical environment, yet use symbolic representations to control aspects of their behavior.

On the Convergence of Stochastic Iterative Dynamic Programming Algorithms

Recent developments in the area of reinforcement learning have yielded a number of new algorithms for the prediction and control of Markovian environments. These algorithms, including the TD(lambda) algorithm of Sutton (1988) and the Q-learning algorithm of Watkins (1989), can be motivated heuristically as approximations to dynamic programming (DP). In this paper we provide a rigorous proof of convergence of these DP-based learning algorithms by relating them to the powerful techniques of stochastic approximation theory via a new convergence theorem. The theorem establishes a general class of convergent algorithms to which both TD(lambda) and Q-learning belong.

AFL-1: A Programming Language for Massively Concurrent Computers

Computational models are arising is which programs are constructed by specifying large networks of very simple computational devices. Although such models can potentially make use of a massive amount of concurrency, their usefulness as a programming model for the design of complex systems will ultimately be decided by the ease in which such networks can be programmed (constructed). This thesis outlines a language for specifying computational networks. The language (AFL-1) consists of a set of primitives, ad a mechanism to group these elements into higher level structures. An implementation of this language runs on the Thinking Machines Corporation, Connection machine. Two significant examples were programmed in the language, an expert system (CIS), and a planning system (AFPLAN). These systems are explained and analyzed in terms of how they compare with similar systems written in conventional languages.

Reasoning about Temporal Context using Ontology and Abductive Constraint Logic Programming

The underlying assumptions for interpreting the meaning of data often change over time, which further complicates the problem of semantic heterogeneities among autonomous data sources. As an extension to the COntext INterchange (COIN) framework, this paper introduces the notion of temporal context as a formalization of the problem. We represent temporal context as a multi-valued method in F-Logic; however, only one value is valid at any point in time, the determination of which is constrained by temporal relations. This representation is then mapped to an abductive constraint logic programming framework with temporal relations being treated as constraints. A mediation engine that implements the framework automatically detects and reconciles semantic differences at different times. We articulate that this extended COIN framework is suitable for reasoning on the Semantic Web.

Reasoning about Temporal Context using Ontology and Abductive Constraint Logic Programming

The underlying assumptions for interpreting the meaning of data often change over time, which further complicates the problem of semantic heterogeneities among autonomous data sources. As an extension to the COntext INterchange (COIN) framework, this paper introduces the notion of temporal context as a formalization of the problem. We represent temporal context as a multi-valued method in F-Logic; however, only one value is valid at any point in time, the determination of which is constrained by temporal relations. This representation is then mapped to an abductive constraint logic programming framework with temporal relations being treated as constraints. A mediation engine that implements the framework automatically detects and reconciles semantic differences at different times. We articulate that this extended COIN framework is suitable for reasoning on the Semantic Web.

Reasoning about Temporal Context using Ontology and Abductive Constraint Logic Programming

The underlying assumptions for interpreting the meaning of data often change over time, which further complicates the problem of semantic heterogeneities among autonomous data sources. As an extension to the COntext INterchange (COIN) framework, this paper introduces the notion of temporal context as a formalization of the problem. We represent temporal context as a multi-valued method in F-Logic; however, only one value is valid at any point in time, the determination of which is constrained by temporal relations. This representation is then mapped to an abductive constraint logic programming framework with temporal relations being treated as constraints. A mediation engine that implements the framework automatically detects and reconciles semantic differences at different times. We articulate that this extended COIN framework is suitable for reasoning on the Semantic Web.

Reasoning about Temporal Context using Ontology and Abductive Constraint Logic Programming

The underlying assumptions for interpreting the meaning of data often change over time, which further complicates the problem of semantic heterogeneities among autonomous data sources. As an extension to the COntext INterchange (COIN) framework, this paper introduces the notion of temporal context as a formalization of the problem. We represent temporal context as a multi-valued method in F-Logic; however, only one value is valid at any point in time, the determination of which is constrained by temporal relations. This representation is then mapped to an abductive constraint logic programming framework with temporal relations being treated as constraints. A mediation engine that implements the framework automatically detects and reconciles semantic differences at different times. We articulate that this extended COIN framework is suitable for reasoning on the Semantic Web.

Preconditioning and iterative solution of symmetric indefinite linear systems arising from interior point methods for linear programming

We study the preconditioning of symmetric indefinite linear systems of equations that arise in interior point solution of linear optimization problems. The preconditioning method that we study exploits the block structure of the augmented matrix to design a similar block structure preconditioner to improve the spectral properties of the resulting preconditioned matrix so as to improve the convergence rate of the iterative solution of the system. We also propose a two-phase algorithm that takes advantage of the spectral properties of the transformed matrix to solve for the Newton directions in the interior-point method. Numerical experiments have been performed on some LP test problems in the NETLIB suite to demonstrate the potential of the preconditioning method discussed.

Behavioral Measures and their Correlation with IPM Iteration Counts on Semi-Definite Programming Problems

We study four measures of problem instance behavior that might account for the observed differences in interior-point method (IPM) iterations when these methods are used to solve semidefinite programming (SDP) problem instances: (i) an aggregate geometry measure related to the primal and dual feasible regions (aspect ratios) and norms of the optimal solutions, (ii) the (Renegar-) condition measure C(d) of the data instance, (iii) a measure of the near-absence of strict complementarity of the optimal solution, and (iv) the level of degeneracy of the optimal solution. We compute these measures for the SDPLIB suite problem instances and measure the correlation between these measures and IPM iteration counts (solved using the software SDPT3) when the measures have finite values. Our conclusions are roughly as follows: the aggregate geometry measure is highly correlated with IPM iterations (CORR = 0.896), and is a very good predictor of IPM iterations, particularly for problem instances with solutions of small norm and aspect ratio. The condition measure C(d) is also correlated with IPM iterations, but less so than the aggregate geometry measure (CORR = 0.630). The near-absence of strict complementarity is weakly correlated with IPM iterations (CORR = 0.423). The level of degeneracy of the optimal solution is essentially uncorrelated with IPM iterations.