UT AUSTINVILLA 3D

https://github.com/LARG/utaustinvilla3d
包含：
Omnidirectional walk engine based on a double inverted pendulum model
基于双倒立摆的全方位步行引擎

A skill description language for specifying parameterized skills/behaviors
使用技能描述语言的具体参数来实现动作

Getup behaviors for all agent types
为各类型机器人封装动作

A couple basic skills or kicking one of which uses inverse kinematics
一对使用逆运动学来踢球的基础动作

Sample demo dribble and kick behaviors for scoring a goal
为进球演示运球和踢腿行为

World model and particle filter for localization
用于定位的世界模型和粒子滤波器

Kalman filter for tracking objects
用于跟踪目标的卡尔曼滤波器

All necessary parsing code for sending/receiving messages from/to the server
与服务器接受发送信息的所有重要解析代码

Code for drawing objects in the roboviz monitor
ROBOVIZ监视器（显示器）中绘制对象的代码

Communication system previously provided for use in drop-in player challenges
先前提供的通信系统可用于玩家在游戏中遇到的挑战

Example behaviors/tasks for optimizing a kick and forward walk
优化踢腿和向前走的行为/任务事例

Support for Gazebo RoboCup 3D simulation plugin (https://bitbucket.org/osrf/robocup3ds)
支持Gazebo RoboCup 3D 方针插件

Scripts and code for collecting game statistics
收集游戏统计信息的脚本和代码

不包含：
The team’s complete set of skills such as long kicks and goalie dives
本队的全套技术动作，如长踢和守门员扑球

Optimized parameters for behaviors such as the team’s fastest walks (slow and stable walk engine parameters are included, as well as optimized walk engine parameters for positioning/dribbling and approaching the ball to kick)
针对最快步行等行为的参数优化

High level strategy including formations and role assignment
高层战略包括编队和角色的分配

使用代码介绍
First be sure to start the simulation server running.
首先确定运行仿真服务器
Run full team:运行全队

./start.sh

Run penalty kick shooter:运行点球射手

./start_penalty_kicker.sh

Run penalty kick goalie:运行点球射门员

./start_penalty_goalie.sh

Run agent for Gazebo RoboCup 3D simulation plugin:运行Gazebo RoboCup 3D仿真器
./start_gazebo.sh

Video of default walking behavior in Gazebo: www.cs.utexas.edu/~AustinVilla/sim/3dsimulation/AustinVilla3DSimulationFiles/2016/videos/GazeboWalk.mp4

Kill team:清除全队

./kill.sh

List command line options:列出命令行选项

./agentspark --help