Agent design Development

Overview

Autonomous Agent Design is the high level decision making program to control which functionality should our robot choose under different circumstances. However, a powerful decision making agent requires as much critical information as possible. This information is gained by each functional-layer node (such as those projects in Computer Vision). In addition, our agent can only be tested in VCATS. Therefore, this area of projects will not be available before a stable version of VCATS is available. 

Platform

Real Robot

  • Only got 2 robots, can play with 1 vs 1.
  • A 5m * 8m field with walls and buff system is unavailable under current circumstance, 
rplidar_a3

Simulation

  • Can run simple match with mimic shooting system with Gazebo simulator.
  • VCATS using Unity 3D with capacity for a full referee system is ideal (still under development).
simulation cover pic

Code base

  • OS: Linux Ubuntu 18.04
  • Tools: ROS
  • Programming language: C++

FSM

  • The basic version of an autonomous agent is a finite state machine.
  • To be continued…

Decision Tree

  • To be continued…

Planning

  • To be continued…

Reinforcement Learning

  • To be continued…

If interested, what's next?

If you are interested to choose one of the above projects are your capstone project, please click this link. Otherwise, please read the following points:

  1. Most of these project is recommended to develop and explore as a Team since the scale for each topic is pretty big. Please fill in the form that we sent by email after induction section, so that it would be easy for us to manage different teams with different projects.
  2. All projects related with Agent Design are expected to be development in a Ubuntu OS (ideally 18.04) with ROS installed, there are some instruction for install ROS available on this link.
  3. Please contact Guang (ghu1@student.unimelb.edu.au) by email if you have any question about Agent Design Projects.