We explore the use of an interface to mark pairs of points on two images which are in "correspondence" with one another, as a way of collecting part annotations. The interface allows annotations of visual categories that are structurally diverse, such as chairs and buildings, where it is difficult to define a set of parts, or landmarks, that are consistent, namable or uniquely defined across all instances of the category. It allows flexibility in annotation - the landmarks can be instance specific, are not constrained by language, could be many to one, etc and requires little category specific instructions. We compare our approach to two popular methods of collecting part annotations, (1) drawing bounding boxes for a set of parts, and (2) annotating a set of landmarks, in terms of annotation setup overhead, cost, difficulty, applicability and utility, and identify scenarios where one method is better suited than the others. Preliminary experiments suggest that such annotations between a sparse set of pairs can be used to bootstrap many high level visual recognition tasks such as part discovery and semantic saliency.

Neurules are a type of neuro-symbolic rules integrating neurocomputing and production rules. Each neurule is represented as an adaline unit. Neurules exhibit characteristics such as modularity, naturalness and ability to perform interactive and integrated inferences. One way of producing a neurule base is through conversion of an existing symbolic rule base yielding an equivalent but more compact rule base. The conversion process merges symbolic rules having the same conclusion into one or more neurules. Due to the inability of the adaline unit to handle inseparability, more than one neurule for each conclusion may be produced. In this paper, we define criteria concerning the ability or inability to convert a rule set into a single neurule. Definition of criteria determining whether a set of symbolic rules can (or cannot) be converted into a single, equivalent but more compact rule is of general representational interest. With application of such criteria, the conversion process of symbolic rules into neurules becomes more time- and space-efficient by omitting useless trainings. Experimental results are promising.

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.

Smart Cities is a vision driven by the availability of governmental data that fosters many challenging applications. One of them is the management of inconsistent traffic regulations, i.e., the handling of inconsistent traffic signs and measures in urban areas such as wrong sign posting, or errors in data acquisition in traffic sign administration software. We investigate such inconsistent traffic scenarios and formally model traffic regulations. Based on this, we consider relevant reasoning tasks including consistency testing, diagnosis, and repair, and present an implementation of the these tasks using answer set programming. The results of this research may improve existing governmental software maintaining traffic regulations.

Many tasks for autonomous agents or robots are best de- scribed by a specification of the environment and a specifi- cation of the available actions the agent or robot can perform. Combining such a specification with the possibility to imper- atively program a robot or agent is what we call the action- based imperative programming. One of the most successful such approaches is Golog. In this paper, we draft a proposal for a new robot program- ming language YAGI, which is based on the action-based imperative programming paradigm. Our goal is to design a small, portable stand-alone YAGI interpreter. We combine the benefits of a principled domain specification with a clean, small and simple programming language, which does not ex- ploit any side-effects from the implementation language. We discuss general requirements of action-based programming languages and outline YAGI, our action-based language ap- proach which particularly aims at embeddability.

Human-robot interaction poses tight timing requirements on visual as well as natural language processing in order to allow for natural human-robot interaction. In particular, humans expect robots to incrementally resolve spoken references to visually perceivable objects as the referents are verbally described. In this paper, we present an integrated robotic architecture with novel incremental vision and natural language processing and demonstrate that incrementally refining attentional focus using linguistic constraints achieves significantly better performance of the vision system compared to non-incremental visual processing.

In aviation industry, free flight is a new concept which implies considering more freedom in the selection and modification of flight paths during flight time. The free flight concept allows pilots choose their own flight paths more efficient, and also plan for their flight with high performance. Although free flight has many advantages such as minimum delays and the reduction of the workload of the air traffic control centers, this concept causes many problems which one of the most important of them are conflicts between different aircrafts. Thus, Conflict Detection and Resolution (CD&R) is a major challenge in air traffic management. In this paper, we presented a model for CD&R between aircrafts in air traffic management using Graph Coloring Problem (GCP) method. In fact, we mapped the congestion area to a corresponding graph, and then addressed to find a reliable and optimal coloring for this graph using one of the new evolutionary algorithms known as Imperialist Competitive Algorithm (ICA) to solve the conflicts. Using ICA for solving GCP is a new method.

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.

With the proliferation of online labor markets and other social computing platforms, online experiments have become a low-cost and scalable way to empirically test hypotheses and mechanisms in both human computation and social science. Yet, despite the potential in designing more powerful and expressive online experiments using multiple subjects, researchers still face many technical and logistical difficulties. We see synchronous and longitudinal experiments involving real-time interaction between participants as a dual-use paradigm for both human computation and social science, and present TurkServer, a platform that facilitates these types of experiments on Amazon Mechanical Turk. Our work has the potential to make more fruitful online experiments accessible to researchers in many different fields.

To ensure quality results from unreliable crowdsourced workers, task designers often construct complex workflows and aggregate worker responses from redundant runs. Frequently, they create several alternative workflows to accomplish the task, and choose a single workflow to deploy (perhaps the one that achieves the best performance during early experiments). However, this seemingly natural design paradigm does not achieve the full potential of crowdsourcing. In particular, using a single workflow (even the best) to accomplish a task is suboptimal. We show that alternative workflows can compose synergistically to yield a much higher quality output. We formalize the insight with a novel probabilistic graphical model, design and implement AgentHunt, a POMDP-based controller that dynamically switches between these workflows to achieve higher returns on investment, and design offline and online methods for learning model parameters. Live experiments on Amazon Mechanical Turk demonstrate the superiority of AgentHunt for the practical task of generating NLP training data, yielding up to 50% error reduction and greater net utility compared to previous methods.