Brett Israelsen

Brett W. Israelsen, Nisar Ahmed

We summarize our efforts to date in developing a framework for generating succinct human-understandable competency self-assessments in terms of machine self confidence, i.e. a robot's self-trust in its functional abilities to accomplish assigned tasks. Whereas early work explored machine self-confidence in ad hoc ways for niche applications, our Factorized Machine Self-Confidence framework introduces and combines several aspects of probabilistic meta reasoning for algorithmic planning and decision-making under uncertainty to arrive at a novel set of generalizable self-confidence factors, which can support competency assessment for a wide variety of problems.

Brett W. Israelsen, Nisar R. Ahmed, Matthew Aitken et al.

How can intelligent machines assess their competency to complete a task? This question has come into focus for autonomous systems that algorithmically make decisions under uncertainty. We argue that machine self-confidence -- a form of meta-reasoning based on self-assessments of system knowledge about the state of the world, itself, and ability to reason about and execute tasks -- leads to many computable and useful competency indicators for such agents. This paper presents our body of work, so far, on this concept in the form of the Factorized Machine Self-confidence (FaMSeC) framework, which holistically considers several major factors driving competency in algorithmic decision-making: outcome assessment, solver quality, model quality, alignment quality, and past experience. In FaMSeC, self-confidence indicators are derived via 'problem-solving statistics' embedded in Markov decision process solvers and related approaches. These statistics come from evaluating probabilistic exceedance margins in relation to certain outcomes and associated competency standards specified by an evaluator. Once designed, and evaluated, the statistics can be easily incorporated into autonomous agents and serve as indicators of competency. We include detailed descriptions and examples for Markov decision process agents, and show how outcome assessment and solver quality factors can be found for a range of tasking contexts through novel use of meta-utility functions, behavior simulations, and surrogate prediction models. Numerical evaluations are performed to demonstrate that FaMSeC indicators perform as desired (references to human subject studies beyond the scope of this paper are provided).

Brett Israelsen, Soumalya Sarkar

Large Language Models have seen rapid progress in capability in recent years; this progress has been accelerating and their capabilities, measured by various benchmarks, are beginning to approach those of humans. There is a strong demand to use such models in a wide variety of applications but, due to unresolved vulnerabilities and limitations, great care needs to be used before applying them to intelligence and safety-critical applications. This paper reviews recent literature related to LLM assessment and vulnerabilities to synthesize the current research landscape and to help understand what advances are most critical to enable use of of these technologies in intelligence and safety-critical applications. The vulnerabilities are broken down into ten high-level categories and overlaid onto a high-level life cycle of an LLM. Some general categories of mitigations are reviewed.

Charles Peasley, Rachel Dianiska, Emily Oldham et al.

To reduce the need for business-related air travel and its associated energy consumption and carbon footprint, the U.S. Department of Energy's ARPA-E is supporting a research project called SCOTTIE - Systematic Communication Objectives and Telecommunications Technology Investigations and Evaluations. SCOTTIE tests virtual and augmented reality platforms in a functional comparison with face-to-face (FtF) interactions to derive travel replacement thresholds for common industrial training scenarios. The primary goal of Study 1 is to match the communication effectiveness and learning outcomes obtained from a FtF control using virtual reality (VR) training scenarios in which a local expert with physical equipment trains a remote apprentice without physical equipment immediately present. This application scenario is commonplace in industrial settings where access to expensive equipment and materials is limited and a number of apprentices must travel to a central location in order to undergo training. Supplying an empirically validated virtual training alternative constitutes a readily adoptable use-case for businesses looking to reduce time and monetary expenditures associated with travel. The technology used for three different virtual presence technologies was strategically selected for feasibility, relatively low cost, business relevance, and potential for impact through transition. The authors suggest that the results of this study might generalize to the challenge of virtual conferences.

Brett W Israelsen, Nisar R Ahmed, Eric Frew et al.

Algorithmic assurances from advanced autonomous systems assist human users in understanding, trusting, and using such systems appropriately. Designing these systems with the capacity of assessing their own capabilities is one approach to creating an algorithmic assurance. The idea of `machine self-confidence' is introduced for autonomous systems. Using a factorization based framework for self-confidence assessment, one component of self-confidence, called `solver-quality', is discussed in the context of Markov decision processes for autonomous systems. Markov decision processes underlie much of the theory of reinforcement learning, and are commonly used for planning and decision making under uncertainty in robotics and autonomous systems. A `solver quality' metric is formally defined in the context of decision making algorithms based on Markov decision processes. A method for assessing solver quality is then derived, drawing inspiration from empirical hardness models. Finally, numerical experiments for an unmanned autonomous vehicle navigation problem under different solver, parameter, and environment conditions indicate that the self-confidence metric exhibits the desired properties. Discussion of results, and avenues for future investigation are included.

Brett W Israelsen

As technology become more advanced, those who design, use and are otherwise affected by it want to know that it will perform correctly, and understand why it does what it does, and how to use it appropriately. In essence they want to be able to trust the systems that are being designed. In this survey we present assurances that are the method by which users can understand how to trust this technology. Trust between humans and autonomy is reviewed, and the implications for the design of assurances are highlighted. A survey of research that has been performed with respect to assurances is presented, and several key ideas are extracted in order to refine the definition of assurances. Several directions for future research are identified and discussed.

Brett W. Israelsen, Nisar Ahmed, Kenneth Center et al.

This work studies how an AI-controlled dog-fighting agent with tunable decision-making parameters can learn to optimize performance against an intelligent adversary, as measured by a stochastic objective function evaluated on simulated combat engagements. Gaussian process Bayesian optimization (GPBO) techniques are developed to automatically learn global Gaussian Process (GP) surrogate models, which provide statistical performance predictions in both explored and unexplored areas of the parameter space. This allows a learning engine to sample full-combat simulations at parameter values that are most likely to optimize performance and also provide highly informative data points for improving future predictions. However, standard GPBO methods do not provide a reliable surrogate model for the highly volatile objective functions found in aerial combat, and thus do not reliably identify global maxima. These issues are addressed by novel Repeat Sampling (RS) and Hybrid Repeat/Multi-point Sampling (HRMS) techniques. Simulation studies show that HRMS improves the accuracy of GP surrogate models, allowing AI decision-makers to more accurately predict performance and efficiently tune parameters.

Brett W. Israelsen, Nisar Ahmed, Kenneth Center et al.

A key requirement for the current generation of artificial decision-makers is that they should adapt well to changes in unexpected situations. This paper addresses the situation in which an AI for aerial dog fighting, with tunable parameters that govern its behavior, must optimize behavior with respect to an objective function that is evaluated and learned through simulations. Bayesian optimization with a Gaussian Process surrogate is used as the method for investigating the objective function. One key benefit is that during optimization, the Gaussian Process learns a global estimate of the true objective function, with predicted outcomes and a statistical measure of confidence in areas that haven't been investigated yet. Having a model of the objective function is important for being able to understand possible outcomes in the decision space; for example this is crucial for training and providing feedback to human pilots. However, standard Bayesian optimization does not perform consistently or provide an accurate Gaussian Process surrogate function for highly volatile objective functions. We treat these problems by introducing a novel sampling technique called Hybrid Repeat/Multi-point Sampling. This technique gives the AI ability to learn optimum behaviors in a highly uncertain environment. More importantly, it not only improves the reliability of the optimization, but also creates a better model of the entire objective surface. With this improved model the agent is equipped to more accurately/efficiently predict performance in unexplored scenarios.

Brett Israelsen, Nisar Ahmed

A key drawback of the current generation of artificial decision-makers is that they do not adapt well to changes in unexpected situations. This paper addresses the situation in which an AI for aerial dog fighting, with tunable parameters that govern its behavior, will optimize behavior with respect to an objective function that must be evaluated and learned through simulations. Once this objective function has been modeled, the agent can then choose its desired behavior in different situations. Bayesian optimization with a Gaussian Process surrogate is used as the method for investigating the objective function. One key benefit is that during optimization the Gaussian Process learns a global estimate of the true objective function, with predicted outcomes and a statistical measure of confidence in areas that haven't been investigated yet. However, standard Bayesian optimization does not perform consistently or provide an accurate Gaussian Process surrogate function for highly volatile objective functions. We treat these problems by introducing a novel sampling technique called Hybrid Repeat/Multi-point Sampling. This technique gives the AI ability to learn optimum behaviors in a highly uncertain environment. More importantly, it not only improves the reliability of the optimization, but also creates a better model of the entire objective surface. With this improved model the agent is equipped to better adapt behaviors.

Brett W. Israelsen, Dale A. Smith

The Volterra series can be used to model a large subset of nonlinear, dynamic systems. A major drawback is the number of coefficients required model such systems. In order to reduce the number of required coefficients, Laguerre polynomials are used to estimate the Volterra kernels. Existing literature proposes algorithms for a fixed number of Volterra kernels, and Laguerre series. This paper presents a novel algorithm for generalized calculation of the finite order Volterra-Laguerre (VL) series for a MIMO system. An example addresses the utility of the algorithm in practical application.