This paper describes a new candidate method of computing autonomous "self confidence." We describe how to analyze a plan for possible but unexpected break down cases and how to adapt the plan to circumvent those conditions. We view the result plan as more stable than the original one. The ability of achieving such plan stability is the core of how we propose to compute a system’s self confidence in its decisions and plans. This paper summarizes this approach and presents a preliminary evaluation that shows our approach is promising.

We present an approach geared toward estimating task execution confidence for robotic bin-picking applications. This requires estimating execution confidence for all constituent subtasks including part recognition and pose estimation, singulation, transport, and fine positioning. This paper is focussed on computing associated confidence parameters for the part recognition and pose estimation subtask. In particular, our approach allows a robot to evaluate how good the part recognition and pose estimation is, based on a confidence-measure, and thereby determine whether to proceed with the task execution (part singulation) or to request help from a human in order to resolve the associated failure. The value of a mean-square distance metric at a local minimum where the part matching solution is found is used as a surrogate for the confidence parameter. Experiments with a Baxter robot are used illustrate our approach.

We present Saul, a new probabilistic programming language designed to address some of the shortcomings of programming languages that aim at advancing and simplifying the development of AI systems. Such languages need to interact with messy, naturally occurring data, to allow a programmer to specify what needs to be done at an appropriate level of abstraction rather than at the data level, to be developed on a solid theory that supports moving to and reasoning at this level of abstraction and, finally, to support flexible integration of these learning and inference models within an application program. Saul is an object-functional programming language written in Scala that facilitates these by (1) allowing a programmer to learn, name and manipulate named abstractions over relational data; (2) supporting seamless incorporation of trainable (probabilistic or discriminative) components into the program, and (3) providing a level of inference over trainable models to support composition and make decisions that respect domain and application constraints. Saul is developed over a declaratively defined relational data model, can use piecewise learned factor graphs with declaratively specified learning and inference objectives, and it supports inference over probabilistic models augmented with declarative knowledge-based constraints.We describe the key constructs of Saul and exemplify its use in developing applications that require relational feature engineering and structured output prediction.

This paper presents a model of exaggeration suitable for implementation on a robot. Exaggeration is an interest form of dishonesty in that it serves as a tradeoff between the different costs associated with lying and the reward received by having one’s lie accepted. Moreover, exaggeration offers the deceiver additional control in the form of much the exaggerated statement differs from the truth. We use a color guessing game to examine the different tradeoffs between these costs and rewards and their impact on exaggeration. Our results indicate some amount of exaggeration is the preferred option during most early interactions. Further, because the cost of lying increases linear with the number of lies, exaggeration decreases with additional interactions. We conclude by arguing why social robots must be capable of lying.

This study focuses on the question: "What are the computational formalisms at the heart of deceptive and counter-deceptive machines?" We formulate deception using a dynamic epistemic logic. Three different types of deception are considered: deception by lying, deception by bluffing and deception by truth-telling, depending on whether a speaker believes what he/she says or not. Next we consider various situations where an act of deceiving happens. Intentional deception is accompanied by a speaker's intent to deceive. Indirect deception happens when false information is carried over from person to person. Self-deception is an act of deceiving the self. We investigate formal properties of different sorts of deception.

In an earlier paper, I described in some detail how a system based on symbolic knowledge representation and reasoning could model and reason about an act of deception encountered in a children's story. This short position paper extends that earlier work, adding new analysis and discussion about the nature of deception, the desirability of building deceptive AI systems, and the computational mechanisms necessary for deceiving others and for recognizing their attempts to deceive us.

This brief paper explores the consequences of agnosticism with respect to whether a given human agent B is guilty of fraud. We find that if a human A is agnostic with respect to whether a human fraudster B is guilty of fraud, A, on the only formal definition of fraud that we are aware of, is her/himself provably not guilty of fraud. This means that a counter-fraud machine D based on an implemented version of this definition will classify A as innocent. Hence, if A by simply an act of will can bring it about that A is agnostic, A will evade D

In a symposium focused on deception and counter-deception in machines, one might be immediately drawn to a narrow conception of those phenomena which highlight the pernicious ways in which they might be used. On the broader notion of fibbing that we describe in our talk, the social function of being fast and loose with the truth takes center stage as a tool for accomplishing a wide variety of socially centered goals. We briefly review the FIDE framework, described in (Isaac & Bridewell 2014; Bridewell & Bello 2014), including the conceptual resources it requires and the variety of fib-related concepts it supports. FIDE delineates between the aforementioned concepts as ends, and the strategic means by which the fibber might achieve these ends. In doing so, we show that certain types of difficult to conceptualize behavior, most notably bullshitting (Frankfurt 2006) and responses to bullshitting, are instances of a kind of strategy for impression management that serves higher-order social goals.

Intelligent systems rely on pattern recognition and signature-based approaches for a wide range of sensors enhancing situational awareness. For example, autonomous systems depend on environmental sensors to perform their tasks and secure systems depend on anomaly detection methods. The availability of large amount of data requires the processing of data in a “streaming” fashion with online algorithms. Yet, just as online learning can enhance adaptability to a non-stationary environment, it introduces vulnerabilities that can be manipulated by adversaries to achieve their goals while evading detection. Although human intelligence might have evolved from social interactions, machine intelligence has evolved as a human intelligence artifact and been kept isolated to avoid ethical dilemmas. As our adversaries become sophisticated, it might be time to revisit this question and examine how we can combine online learning and reasoning leading to the science of deceptive and counter-deceptive machines.

This abstract describes the development of algorithms for personalized anxiety reduction feedback for use by a robot buddy interacting with a child about to receive intravenous therapy (an IV insertion). This three-phase study is currently being conducted; it consists of two data collections to determine domain-specific approaches, followed by the full study with personalized anxiety-reducing feedback. Participants receiving personalized feedback will be compared to participants with a non-personalized robot (to control for novelty) and a no robot condition (baseline control).