Name
Abstract | ||
|---|---|---|
One of the most important characteristics of intelligent activity is the ability to change behaviour according to many forms of feedback. Through learning an agent can interact with its environment to improve its performance over time. However, most of the techniques known that involves learning are time expensive, i.e., once the agent is supposed to learn over time by experimentation, the task has to be executed many times. Hence, high fidelity simulators can save a lot of time. In this context, this paper describes the framework designed to allow a team of real RoboNova-Ihumanoids robots to be simulated under USARSimenvironment. Details about the complete process of modeling and programming the robot are given, as well as the learning methodology proposed to improve robot's performance. Due to the use of a high fidelity model, the learning algorithms can be widely explored in simulation before adapted to real robots. |
Year | DOI | Venue |
|---|---|---|
2007 | 10.1007/978-3-540-68847-1_34 | RoboCup 2009 |
Keywords | Field | DocType |
complete process,important characteristic,high fidelity simulator,high fidelity model,intelligent activity,real robonova-ihumanoids robot,humanoid simulated robots,real robot,humanoid robot | Robot learning,High fidelity,Computer vision,Computer science,Simulation,Legged robot,Artificial intelligence,Robot,Error-driven learning,Static mesh,Robotics,Robot programming | Conference |
Volume | ISSN | Citations |
5001 | 0302-9743 | 1 |
PageRank | References | Authors |
0.38 | 3 | 4 |
Name | Order | Citations | PageRank |
|---|---|---|---|
| Esther Luna Colombini | 1 | 5 | 5.34 |
| alexandre unesp da silva simoes | 2 | 1 | 0.38 |
| antonio cesar germano unesp martins | 3 | 1 | 0.38 |
| Jackson Paul Matsuura | 4 | 8 | 1.56 |