Sciweavers

160 search results - page 10 / 32
» Dynamics and control in component-based agent models
Sort
View
AAAI
2008
13 years 10 months ago
An Efficient Motion Planning Algorithm for Stochastic Dynamic Systems with Constraints on Probability of Failure
When controlling dynamic systems, such as mobile robots in uncertain environments, there is a trade off between risk and reward. For example, a race car can turn a corner faster b...
Masahiro Ono, Brian C. Williams
ECAL
2007
Springer
14 years 1 months ago
Measuring Entropy in Embodied Neural Agents with Homeostasic Units: A Link Between Complexity and Cybernetics
Abstract. We present a model of a recurrent neural network with homeostasic units, embodied in a minimalist articulated agent with a single link and joint. The configuration of th...
Jorge Simão
AAAI
2008
13 years 10 months ago
Perpetual Learning for Non-Cooperative Multiple Agents
This paper examines, by argument, the dynamics of sequences of behavioural choices made, when non-cooperative restricted-memory agents learn in partially observable stochastic gam...
Luke Dickens
ECAL
2005
Springer
14 years 1 months ago
Is an Embodied System Ever Purely Reactive?
This paper explores the performance of a simple model agent using a reactive controller in situations where, from an external perspective, a solution that relies on internal states...
Eduardo Izquierdo-Torres, Ezequiel A. Di Paolo
AAAI
2008
13 years 10 months ago
Adaptive Control for Autonomous Underwater Vehicles
We describe a novel integration of Planning with Probabilistic State Estimation and Execution resulting in a unified representational and computational framework based on declarat...
Conor McGann, Frederic Py, Kanna Rajan, John Ryan,...