Contextual knowledge is essential in answering questions given specific observations. While recent approaches to building commonsense knowledge basesvia text mining and/or crowdsourcing are successful,contextual knowledge is largely missing. To addressthis gap, this paper presents SocialExplain, a novel approach to acquiring contextual commonsense knowledge from explanations of social content. The acquisition process is broken into two cognitively simple tasks:to identify contextual clues from the given social content, and to explain the content with the clues. An experiment was conducted to show that multiple piecesof contextual commonsense knowledge can be identi-fied from a small number of tweets. Online users verified that 92.45% of the acquired sentences are good,and 95.92% are new sentences compared with existingcrowd-sourced commonsense knowledge bases.

We report results from a human computation study that tests the extent to which output agreement games are better than traditional methods in terms of increasing quality of labels and motivation of voluntary workers on a task with a gold standard. We built an output agreement game that let workers recruited from Amazon's Mechanical Turks label the semantic textual similarity of 20 sentence pairs. To compare and test the effects of the major components of the game, we created interfaces that had different combinations of a gaming environment (G), social interaction (S), and feedback (F). Our results show that the main reason that an output agreement game can collect more high-quality labels is the gaming environment (scoring system, leaderboard, etc). On the other hand, a worker is much more motivated to voluntarily do the task if he or she can do it with another worker (i.e., with social interaction). Our analysis provides human computation researchers important insight on understanding how and why the method of Game with a Purpose (GWAP) can generate high-quality outcomes and motivate more voluntary workers.

This paper outlines a study that investigates spatial language for use in human-robot communication. The scenario studied is a home setting in which the elderly resident has misplaced an object, such as eyeglasses, and the robot will help the resident find the object. We present results from phase I of the study in which we investigate spatial language generated to a human addressee or a robot addressee in a virtual environment and highlight differences between younger and older adults. Drawn from these results, a discussion is included of needed robot capabilities, such as an approach that addresses varying perspectives used and recognition of furniture items for use as spatial references.

We discuss preliminary work focusing on the problem of combining social interaction with task-based action in a dynamic, multiagent bartending domain, using an embodied robot. We show how the users' spoken input is interpreted, discuss how social states are inferred from the parsed speech together with low-level information from the vision system, and present a planning approach that models task, dialogue, and social actions in a simple bartending scenario. This approach allows us to build interesting plans, which have been evaluated in a real-world study, using a general purpose, off-the-shelf planner, as an alternative to more mainstream methods of interaction management.

Linguistic communication relies on non-linguistic context toconvey meaning. That context might include, for instance, recent orlong-term experience, semantic knowledge of the world, or objects and events in the immediate environment. In this paper, we describe embodied agents instantiated in Soar cognitive architecture that use context derived from their linguistic, perceptual, procedural and semantic knowledge for comprehending imperative sentences.

We address the problem of training an artificial agent to follow verbal commands using a set of instructions paired with demonstration traces of appropriate behavior. From this data, a mapping from instructions to tasks is learned, enabling the agent to carry out new instructions in novel environments. Our system consists of three components: semantic parsing (SP), inverse reinforcement learning (IRL), and task abstraction (TA). SP parses sentences into logical form representations, but when learning begins, the domain/task specific meanings of these representations are unknown. IRL takes demonstration traces and determines the likely reward functions that gave rise to these traces, defined over a set of provided features. TA combines results from SP and IRL over a set of training instances to create abstract goal definitions of tasks. TA also provides SP domain specific meanings for its logical forms and provides IRL the set of task-relevant features.

While highly constrained language can be used for robot control, robots that can operate as fully autonomous subordinate agents communicating via rich language remain an open challenge. Toward this end, we developed an autonomous system that supports natural, continuous interaction with the operator through language before, during, and after mission execution. The operator communicates instructions to the system through natural language and is given feedback on how each instruction was understood as the system constructs a logical representation of its orders. While the plan is executed, the operator is updated on relevant progress via language and images and can change the robot's orders. Unlike many other integrated systems of this type, the language interface is built using robust, general purpose parsing and semantics systems that do not rely on domain-specific grammars. This system demonstrates a new level of continuous natural language interaction and a novel approach to using general-purpose language and planning components instead of hand-building for the domain. Language-enabled autonomous systems of this type represent important progress toward the goal of integrating robots as effective members of human teams.

A cognitive robot should construct a plan to attain its goals. While it executes the actions in its plan, it may face several failures due to both internal and external issues. We present a taxonomy to classify these failures that may be encountered during the execution of cognitive tasks. The taxonomy presents a wide range of failure types. To recover from most of these failures presented in this taxonomy, we propose a Robust Planning Framework for cognitive robots. Our framework combines planning, reasoning and learning procedures into each other for robust execution of cognitive tasks. Failures can be detected and handled by reasoning and replanning, respectively. The framework also facilitates learning new hypotheses incrementally based on experience. It can successfully detect and recover from temporary failures on a selected set of actions executed by a Pioneer3DX robot. It has been shown that our preliminary results for hypothesis learning in failure scenarios are promising.

In the area of reasoning about actions, one of the key computational problems is the projection problem: to find whether a given logical formula is true after performing a sequence of actions. This problem is undecidable in the general situation calculus; however, it is decidable in some fragments. We consider a fragment P of the situation calculus and Reiter’s basic action theories (BAT) such that the projection problem can be reduced to the satisfiability problem in an expressive description logic ALCO(U) that includes nominals (O), the universal role (U), and constructs from the well-known logic ALC. It turns out that our fragment P is more expressive than previously explored description logic based fragments of the situation calculus. We explore some of the logical properties of our theories. In particular, we show that the projection problem can be solved using regression in the case where BATs include a general “static” TBox, i.e., an ontology that has no occurrences of fluents. Thus, we propose seamless integration of traditional ontologies with reasoning about actions. We also show that the projection problem can be solved using progression if all actions have only local effects on the fluents, i.e., in P, if one starts with an incomplete initial theory that can be transformed into an ALCO(U) concept, then its progression resulting from the execution of a ground action can still be expressed in the same language. Moreover, we show that for a broad class of incomplete initial theories progression can be computed efficiently.

Much of the existing work on plan recognition assumes that actions of other agents can be observed directly. In continuous temporal domains such as traffic scenarios this assumption is typically not warranted. Instead, one is only able to observe facts about the world such as vehicle positions at different points in time, from which the agents' intentions need to be inferred. In this paper we show how this problem can be addressed in the situation calculus and a new variant of the action programming language Golog, which includes features such as continuous time and change, stochastic actions, nondeterminism, and concurrency. In our approach we match observations against a set of candidate plans in the form of Golog programs. We turn the observations into actions which are then executed concurrently with the given programs. Using decision-theoretic optimization techniques those programs are preferred which bring about the observations at the appropriate times. Besides defining this new variant of Golog we also discuss an implementation and experimental results using driving maneuvers as an example.