pthimon's prediction [10 articles]

Abstract

Tracking the movements of a target based on limited observations plays a role in many interesting applications. Existing probabilistic tracking techniques have shown considerable success but the majority assume simplistic motion models suitable for short-term, local motion prediction. Agent movements are often governed by more sophisticated mechanisms such as a goal-directed path-planning algorithm. In such contexts we must go beyond estimating a target's current location to consider its future path and ultimate goal. ...

Abstract

When a robot plans its actions within an environment containing multiple robots, it is often necessary to take into account the actions and movements of the other robots to either avoid, counter, or cooperate with them, depending on the scenario. Our predictive system is based on the biologically-inspired, simulationtheoretic approach that uses internal generative models in single-robot applications. Here, we move beyond the single-robot case to illustrate how these generative models can predict the movements of the opponent’s robots, when applied ...

Abstract

High-level online methods become more and more attractive with the increasing abilities of players and teams in the simulation league. As in real soccer, the recognition and prediction of strategies (e.g. opponent’s formation), tactics (e.g. wing play, offside traps), and situations (e.g. passing behavior) is important. In 2001, we proposed an approach where spatio-temporal relations between objects are described and interpreted in order to detect some of the above mentioned situations. In this paper we propose an extension of this approach ...

Abstract

One of the current topics of research in robotics is activity planning. Most works in this field are related to artificial intelligence (AI) techniques. The main feature of robot planning systems is that they are focused on the particular robot problem or are intended to solve a particular aspect of the planning problem. For this last case, motion planning or task planning are solved in an independent way. This paper covers robot activity planning and re-planning, from the high-level activity description ...

Abstract

Jeff Hawkins, the high-tech success story behind PalmPilots and the Redwood Neuroscience Institute, does a lot of thinking about thinking. In <I>On Intelligence</I> Hawkins juxtaposes his two loves--computers and brains--to examine the real future of artificial intelligence. In doing so, he unites two fields of study that have been moving uneasily toward one another for at least two decades. Most people think that computers are getting smarter, and that maybe someday, they'll be as smart as we humans are. But Hawkins ...