I propose that the notion of cognitive state be broadened from the current predicate-symbolic, Language-of-Thought framework to a multi-modal one, where perception and kinesthetic modalities participate in thinking. In contrast to the roles assigned to perception and motor activities as modules external to central cognition in the currently dominant theories in AI and Cognitive Science, in the proposed approach, central cognition incorporates parts of the perceptual machinery. I motivate and describe the proposal schematically, and describe the implementation of a bimodal version in which a diagrammatic representation component is added to the cognitive state. The proposal explains our rich multimodal internal experience, and can be a key step in the realization of embodied agents. The proposed multimodal cognitive state can significantly enhance the agent's problem solving. Note: Memory, as well as the information retrieved from memory and from perception, represented in a predicate-symbolic form.
Planning in real-time offers several benefits over the more typical techniques of implementing Non-Player Character (NPC) behavior with scripts or finite state machines. NPCs that plan their actions dynamically are better equipped to handle unexpected situations. The modular nature of the goals and actions that make up the plan facilitates reuse, sharing, and maintenance of behavioral building blocks. These benefits, however, come at the cost of CPU cycles. In order to simultaneously plan for several NPCs in real-time, while continuing to share the processor with the physics, animation, and rendering systems, careful consideration must taken with the supporting architecture. The architecture must support distributed processing and caching of costly calculations. These considerations have impacts that stretch beyond the architecture of the planner, and affect the agent architecture as a whole. This paper describes lessons learned while implementing real-time planning for NPCs for F.E.A.R., a AAA first person shooter shipping for PC in 2005.
A group of researchers from Facebook has recently proposed a set of 20 question-answering tasks (Facebook's bAbl dataset) as a challenge for the natural language understanding ability of an intelligent agent. These tasks are designed to measure various skills of an agent, such as: fact based question-answering, simple induction, the ability to find paths, co-reference resolution and many more. Their goal is to aid in the development of systems that can learn to solve such tasks and to allow a proper evaluation of such systems. They show existing systems cannot fully solve many of those toy tasks. In this work, we present a system that excels at all the tasks except one. The proposed model of the agent uses the Answer Set Programming (ASP) language as the primary knowledge representation and reasoning language along with the standard statistical Natural Language Processing (NLP) models. Given a training dataset containing a set of narrations, questions and their answers, the agent jointly uses a translation system, an Inductive Logic Programming algorithm and Statistical NLP methods to learn the knowledge needed to answer similar questions. Our results demonstrate that the introduction of a reasoning module significantly improves the performance of an intelligent agent.
The IJCAI-09 Workshop on Learning Structural Knowledge from Observations (STRUCK-09) took place as part of the International Joint Conference on Artificial Intelligence (IJCAI-09) on July 12 in Pasadena, California. The workshop program included paper presentations, discussion sessions about those papers, group discussions about two selected topics, and a joint discussion. As a result, many cognitive architectures use structural models to represent relations between knowledge of different complexity. Structural modeling has led to a number of representation and reasoning formalisms including frames, schemas, abstractions, hierarchical task networks (HTNs), and goal graphs among others. These formalisms have in common the use of certain kinds of constructs (for example, objects, goals, skills, and tasks) that represent knowledge of varying degrees of complexity and that are connected through structural relations.
Northrop Research and Technology Center, One Research Park, Pales Wdes Peninsula, CA 90274 It, is interesting t,o note that there is no agreed upon definition of artificial intrlligence. Because government agencies ask for it, software shops claim to provide it, popular magazines and newspapers publish articles about, it, dreamers base their fant,asies on it, and pragmatists criticize and denounce it. Such a stat,c of affairs has persisted since Newell, Simon, and Shaw wrote thcif first. Not knowing exactly what we ale talking about, or expecting is typical of a new field; for example, witness the chaos that centcrcd around program verification of security rclated aspects of systems a few years ago The details are too glim to recount, in mixed company. However, artificial intelligence has been around for nearly 30 years, so one might wonder why our wheels are st,ill spinning.