In this paper, we introduce a method for learning and adapting cooperative control strategies in real-time stochastic domains. Our framework is an instance of the intelligent cooperative control architecture (iCCA). The agent starts by following the "safe" plan calculated by the planning module and incrementally adapting the policy to maximize rewards. Actor-critic and consensus-based bundle algorithm (CBBA) were employed as the building blocks of the iCCA framework. We demonstrate the performance of our approach by simulating limited fuel unmanned aerial vehicles aiming for stochastic targets. The integrated framework boosted the optimality of the solution by 10 percent compared to running each of the modules individually.

Introducing robots as teammates in medical, space, and military domains raises interesting and challenging human factors issues that do not necessarily arise in multi-robot coordination. For example, we must consider how to design robots that integrate seamlessly with human group dynamics. An essential quality of a good human partner is her ability to robustly anticipate and adapt to other team members and the environment. Robots should preserve this ability and avoid constraining their human partners’ flexibility to act. This requires that the robot partner be capable of reasoning quickly online, and adapting to the humans’ actions in a temporally fluid way. This paper describes recent advances in dynamic plan execution, and argues that these advances provide a potentially powerful framework for explicitly modeling and efficiently reasoning on temporal information for human-robot interaction. We describe an executive named Chaski that enables a robot to coordinate with a human to execute a shared plan under different models of teamwork. We have applied Chaski to demonstrate teamwork using two Barrett Whole Arm Manipulators, and describe our ongoing work to demonstrate temporally fluid human-robot teaming using the Mobile-Dexterous-Social (MDS) robot.

There is a growing awareness and interest in the issues of accountability and transparency in the pursuit of digital privacy. In previous work, we asserted that systems needed to be “policy aware” and able to compute the likely compliance of any digital transaction with the associated privacy policies (law, rule, or contract). This paper focuses on one critical step in respecting privacy in a digital environment, that of understanding the context associated with each digital transaction. For any individual transaction, the pivotal fact may be context information about the data, the party seeking to use it, the specific action to be taken, or the associated rules. We believe that the granularity of semantic web representation is well suited to this challenge and we support this position in the paper.

Most social networks have implemented extensive and complex controls in order to battle the host of privacy concerns that initially plagued their online communities. These controls have taken the form of a-priori access control, which allow users to construct barriers preventing unwanted users from viewing their personal information. However, in cases in which the access restriction mechanisms are bypassed or when the access restrictions are met but the data is later misused, this system leaves users unprotected. Our framework, Respect My Privacy, proposes an alternative approach to the protection of privacy. Our strategy is similar to how legal and social rules work in our societies where the vast majority of these rules are not enforced perfectly or automatically, yet most of us follow the majority of the rules because social systems built up over thousands of years encourage us to do so and often make compliance easier than violation. Our project aims to support similar functionality in social networks. Instead of focusing on enforcing privacy policies through restricted access, we focus on helping users conform to existing policies by making them aware of the usage restrictions associated with the data. The framework has two main functions - generating privacy or usage control policies for social networks, and visualizing these policies while exploring social networks. We have implemented this functionality across three platforms: Facebook, OpenSocial and Tabulator, a Semantic Web browser. These applications enable users to specify privacy preferences for their data and then display this privacy-annotated data prominently enabling other users to easily recognize and conform to these preferences.

One of the most significant challenges in achieving digital privacy is incorporating privacy policy directly in computer systems. While rule systems have long existed, translating privacy laws, regulations, policies, and contracts into processor amenable forms is slow and difficult because the legal text is scattered, run-on, and unstructured, antithetical to the lean and logical forms of computer science. We are using and developing intermediate isomorphic forms as a Rosetta Stone-like tool to accelerate the translation process and in hopes of providing support to future domain-specific Natural Language Processing technology. This report describes our experience, thoughts about how to improve the form, and discoveries about the form and logic of the legal text that will affect the successful development of a rules tool to implement real-world complex privacy policies.

Recent research identifies stochastic dominance as critical for understanding the relationship between network structure and diffusion. This paper introduces the concept of stochastic dominance, explains the theory linking stochastic dominance and diffusion, and applies this theory to a number of diffusion studies in the literature. The paper illustrates how the theory connects observations from different disciplines, and details when and how those observations can be generalized to broader classes of networks.

An essential quality of a good partner is her responsiveness to other team members. Recent work in dynamic plan execution exhibits elements of this quality through the ability to adapt to the temporal uncertainties of others agents and the environment. However, a good teammate also has the ability to adapt on-the-fly through task assignment. We generalize the framework of dynamic execution to perform plan execution with dynamic task assignment as well as scheduling. This paper introduces Chaski, a multi-agent executive for scheduling temporal plans with online task assignment. Chaski enables an agent to dynamically update its plan in response to disturbances in task assignment and the schedule of other agents. The agent then uses the updated plan to choose, schedule and execute actions that are guaranteed to be temporally consistent and logically valid within the multi-agent plan. Chaski is made efficient through an incremental algorithm that compactly encodes all scheduling policies for all possible task assignments. We apply Chaski to perform multi-manipulator coordination using two Barrett Arms within the authors' hardware testbed. We empirically demonstrate up to one order of magnitude improvements in execution latency and solution compactness compared to prior art.

The dispatcher uses the dispatchable form to quickly make dynamic scheduling decisions. As autonomous systems become more capable and common, However, developing flexible executives for plans with they will need to reason about complex tasks and robustly choices, has been more difficult. Kim, Williams, and execute plans in uncertain environments. In previous work, Abramson present an executive called Kirk, which uses a Williams et al. introduced the Reactive Model-Based Programming deliberative planning step to change the execution sequence Language (RMPL), which is designed to allow online (2001). Although their results show improvement engineers to simply and intuitively express the desired behavior over prior planning systems, the latency is still too high for of the system (2003). Then the agent's executive determines tightly coupled systems, for example robots working with the correct sequence of actions to accomplish this humans or walking robots with fast dynamics. Recently, behavior, relieving the programmer of explicitly coding that Shah and Williams extended the compiler and dispatcher logic. RMPL programs often involve temporal constraints model to Temporal Constraint Satisfaction Problems (TCwhich the executives must reason over. SPs), a type of temporal problems with choice, by compactly Kim, Williams, and Abramson previously developed recording the possible set of solutions and efficiently Temporal Plan Networks (TPNs) as a temporal constraint reasoning over the possible options (2008).

The Association for the Advancement of Artificial Intelligence was pleased to present the 2008 Fall Symposium Series, held Friday through Sunday, November 7-9, at the Westin Arlington Gateway in Arlington, Virginia. The titles of the seven symposia were (1) Adaptive Agents in Cultural Contexts, (2) AI in Eldercare: New Solutions to Old Problems, (3) Automated Scientific Discovery, (4) Biologically Inspired Cognitive Architectures, (5) Education Informatics: Steps toward the International Internet Classroom, (6) Multimedia Information Extraction, and (7) Naturally Inspired AI.

These underpinnings in genetics and fields are vast, variegated, informed by memetics, studying phenomena such disparate theoretical and technical disciplines, as coalition formation in an artificial and interrelated. Other applications provided an updated perspective ethical concerns related to the use of included case-based retrieval of to a previous symposium held in fall eldercare technology to ensure that narratives culturally relevant to a 2005 on the same topic. Some models focused One major theme of the symposium The symposium ended with a more directly on adaptation, from machine-learning was to investigate the use of sensor brainstorming session on possible solutions and game-theoretic networks in the home environment to for two real-life scenarios for perspectives, but discussions suggested provide safety, to monitor activities of ailing elders and their caregivers. The ways in which those adaptations daily living, to assess physical and cognitive exercise was helpful in grounding the might vary from one cultural context function, and to identify participants in the lives of older adults to another. Work was also should address real needs.