Search Results for "robotics"

...This project demonstrates applications in multi-agent and multi-UAV cooperative path planning, making it useful for research and educational purposes in the field of intelligent optimization and robotics.

...With Coach, it is possible to model an agent by combining various building blocks, and training the agent on multiple environments. The available environments allow testing the agent in different fields such as robotics, autonomous driving, games and more. It exposes a set of easy-to-use APIs for experimenting with new RL algorithms and allows simple integration of new environments to solve. Coach collects statistics from the training process and supports advanced visualization techniques for debugging the agent being trained. Coach supports many state-of-the-art reinforcement learning algorithms, which are separated into three main classes - value optimization, policy optimization, and imitation learning. ...

PyVision is a object-oriented Computer Vision Toolkit for researchers that contains vision and machine learning algorithms and algorithm analysis and easily interfaces with scipy/numpy, PIL, opencv and other computer and machine learning libraries.

This project comprises two main parts: 1. The classic "Rodney" as described in David L. Heisermann's book "How to build your own self-programming robot", with the original Intel 8085 code. In all likelihood, this is for reference only. I don't expect many people are going to build it 2. An updated version, running on more modern hardware, but remaining true to the algorithms published in his book. The end result will be at least three sets of code, for the Alpha, Beta and Gamma...

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.

Joshua chess robot: a stepper motor robot interfaced with a photosensible board to play chess with an embedded artificial intelligence, a game database or and internet player. Software, robot photos, tech papers, schematics and cabling included. Enjo

The Mars Rover Simulator project is based on the evolutionary robotics paradigm where an artificial agent acquires its skills through the process of artificial evolution. This simulator can be useful to evolve neural network controllers for the rover

PHPXref is a developers tool, written in Perl, that will cross reference and extract inline documentation from a collection of PHP scripts. It generates simple HTML output suitable for browsing offline.

Todbot is an AI addon to the gamestool virtual machine. The aim is to create an evolving neural network topology that should be capable of creating the optimal topology and network weighting to solve any problem given it.

Gearbox provides a collection of usable peer-reviewed robotics-related libraries. Gearbox is not an integration framework. Rather, it provides a set of implementations, without insisting on a standard API, for use by any number of existing frameworks.

An implementation of Bruhn et al.'s fast variational optical flow algorithm using the OpenCV image processing library. The code calculates dense flow fields with a user-specified level of precision.

A cross-platform library that computes fast and accurate SIFT image features. libsiftfast provides Octave/Matlab scripts, a command line interface, and a python interface (siftfastpy). Optimized with SIMD instructions and OpenMP .

It's a simpler clone of RoboCode. It's a game which simulates tanks war. The focus is artificial intelligence AI, evolutive algorithms and neural networks. It's implemented in Java.

CILib is a framework for developing Computational Intelligence software in swarm intelligence, evolutionary computing, neural networks, artificial immune systems, fuzzy logic and robotics.

The library currently consists of an implementation of collision detection of static/moving ellipsoids that exploits frame-coherence using separating planes. Please visit http://www.cs.hku.hk/GraphicsGroup/cd.html for paper references.

An easy to extend, highly graphical, easy to use 2D robot simulator specialized for path planning algorithms. Can be used in testing various robotic algorithms, and already used for comparison of path planning algorithms like RRT, RRTConnect, PRM, RboT..

The Free Connectionist Q-learning Java Framework is an library for developing learning systems. Keywords: qlearning, artificial intelligence, alife, neural nets, neural networks, machine learning, reinforcement learning unsupervised learning agents lejos

The below is a list of all files released for the Crossbow's MNAV100CA with SPB400. This framework may provide a complete solution for AHRS, Navigation, WiFi Comm, and Data Logging, for various robotic applications.

‘intelliworm’ is a prototype simulation of a Intelligent Species of a common earth worm,which inherits human like decision making capabilities through Neural Network intelligence representation,all developed by integrating .NET with Lisp and Yacc.

A simulation environment for 2D robots to interact and perform tasks in. Meant to be educational and demonstrate emergent behaviors. No download necessary! See demos on project website!

Plantra-Trajectory Planning is a software to rebuild surfaces from cloud points, featuring shaded 3D visualization and path planning for robotics paths. It uses Voronoi diagram, Cyrus-Beck clipping, Delaunay triangulation and B-Splines.

Depending on a SICK lasescan and a created environment landscape a routing function will be implemented to give a robot a few waypoint to drive from a start point to a choosen destination.

This project aims to develop a colour-based vision processing system for use in RoboCup. We are using a CCD camera for input to an FPGA. The system locates coloured objects and outputs detected corners.

CoPP is an object-oriented framework for developing algorithms for robot path planning. One of of the design goals is to make it easy to make comparisons between various path planning algorithms.