Search Results for "artificial intelligence algorithm" - Page 2

Scorpius Robocup soccer simulation team. we will release our binaries, base code, trainers and useful documents here.

Tools and libraries for cross platform developement of intelligent agents.

EVO is a simulation platform for co-evolving the morphology and the behavior of 3D artificial agents in a complex environment. This project directly follows the original work of Karl Sims. It puts together complex creatures, a GA & Open Dynamics Engine.

Travis contains several algorithms for computer vision in robotics. There are tracking, motion detection and reactive navigation functions.

Apollo3D is a team in RoboCup soccer simulation 3D league. The target is to build a nice team with wonderful skills and good cooperation among players.

Highly modularized Reinforcement Learning library for real/simulation robots to learn behaviors. Our ultimate goal is to develop an artificial intelligence (AI) program with which the robots can learn to behave as their users wish.

The Fish4knowledge project investigated: information abstraction and storage methods for analyzing undersea video data (from 10E+15 pixels to 10E+12 units of information), machine and human vocabularies for detecting & describing fish, flexible process architectures to process the data and scientific queries and effective specialised user query interfaces. A combination of computer vision, database storage, workflow and human computer interaction methods were used to achieve this. The...

Customizable software to smoothly fit non-linear, high-dimensional data. SDK in C with C++ wrappers, plus demo applications (all under LGPL). Versions under Windows and Linux already operational. Further progress depends on your imagination!

Critterding is a "Petri dish" universe in 3D that demonstrates evolving artificial life. Critters start out with completely random brains and bodies, but will automatically start evolving into something with much better survival skills.

Urmia University 2D Soccer Server Simulation base

NOTE: This project was moved to: https://github.com/eetorres The BPANNA is a flexible Back propagation neural network, which include the Conjugate Gradient and the Levenberg-Marquardt. You can change the number of inputs, number of layers, number of neurons per layer and outputs. It included an structure editor.

This library contains among other things a set of graphical widgets for video output, performance evaluation and augmented reality. The library also provides classes for several data types usually required by computer vision and image processing applications such as vectors, matrices, quaternions and images. Thanks to a large number of wrapper functions these objects can be used with highly efficient functionality from third party libraries such as OpenCV, GNU Scientific Library,...

The TUM personal robotics package is a collection of libraries that aims to offer methods for personal robotic assistants to operate successfully in indoor environments.

OpenRDK (OPENsource Robot Development Kit) is a modular software framework that can be used by developers in their research in robotics and artificial intelligence. This project has been moved to https://github.com/madmage/openrdk

iSpike is a spiking neural interface between the iCub humanoid robot and a spiking neural simulator such as NeMo.The system aims to provide an interface for the iCub that provides as biologically realistic spike trains from its senses as possible.

Fast flexible simulator of spiking neural networks. Easy to use graphical user interface with comprehensive monitoring facilities. Integrates with the NeMo CUDA simulator and the iSpike interface for the iCub robot.

The Whole-Body Control framework jointly developed at Stanford University and The University of Texas at Austin provides advanced control for fixed base manipulators and is currently running on the the Meka A2 Arm and the Dreamer/Meka Humanoid robot. The code repository is hosted on Github, please go to https://github.com/poftwaresatent/stanford_wbc

It's an object-oriented library written in C++ for creating arbitrary kind of neural networks. The user can use the classes provided to create neural network with arbitrary topology and mixed type of neurons. It's very easy add custom neurons.

A software toolkit that implements the CoSy Architecture Schema for developing integrated intelligent robotic systems. The toolkit focuses on supporting on a space of information-processing architectures based on shared working memories.

The ETHNOS environment is composed of: 1) ETHNOS-6, a dedicated distributed real-time operating system (developed as an extension to Linux), from which the overall environment takes its name, supporting different high level representation, communication, and execution requirements, 2) a dedicated network protocol designed for both the single robot and the multi-robot environment, specifically designed for noisy wireless communication, 3) an object oriented Application Programming...

Software Infrastructure for Stanford's Autonomous Vehicles

A C++ implementation of Dynamic Field Theory (DFT), Amari kind of space-time continuous fields representing activation of populations in neural cortex. Source code for the GUI is available through SVN.

The sunflower library provides programming abstractions developed at the Autonomous Systems Lab http://www.asl.ethz.ch/. It contains a complete path planning and obstacle avoidance system, common mobile robotics tasks abstractions, and a 2D simulator.

An optimized C++ library for working with Dynamic Field Theory.

This is the RoboCup Mixed Reality Project: a standard research and educational platform integrating cutting edge and low cost watch technology into a miniature multi-robot system which mixes reality and simulation.