Douglas L. Vail

Learn More
Activity recognition is a key component for creating intelligent, multi-agent systems. Intrinsically, activity recognition is a temporal classification problem. In this paper, we compare two models for temporal classification: hidden Markov models (HMMs), which have long been applied to the activity recognition problem, and conditional random fields (CRFs).(More)
Communication among a group of robots should in principle improve the overall performance of the team of robots, as robots may share their world views and may negotiate task assignments. However, in practice, effectively handling in real-time multi-robot merge of information and coordination is a challenging task. In this paper, we present the approach that(More)
Role assignment and coordination are difficult issues for multi-robot systems, especially in highly dynamic tasks. Robot soccer is one such task and it provides a unique challenge for multi-robot research. In this paper, we contribute the approach that we successfully developed for CMPACK’02 , our team for the RoboCup-2002 Sony legged league. The(More)
Temporal classification, such as activity recognition, is a key component for creating intelligent robot systems. In the case of robots, classification algorithms must robustly incorporate complex, non-independent features extracted from streams of sensor data. Conditional random fields are discriminatively trained temporal models that can easily(More)
In multi-robot settings, activity recognition allows a robot to respond intelligently to the other robots in its environment. Conditional random fields are temporal models that are well suited for activity recognition because they can robustly incorporate rich, non-independent features computed from sensory data. In this work, we explore feature selection(More)
Since 1997, we have researched teams of soccer robots using the Sony AIBO robots as the robot platform (Veloso & Uther 1999; Veloso et al. 2000; Lenser, Bruce, & Veloso 2001a; 2001b; Uther et al. 2002). Our experience runs across several generations of these four-legged robots and we have met increasing success every year. In the fall of 2003, we created a(More)
In this paper, we present in detail our approach to constructing a world model in a multi-robot team. We introduce two separate world models, namely an individual world model that stores one robot’s state, and a shared world model that stores the state of the team. We present procedures to effectively merge information in these two world models in(More)