Lab Course: Centralized Goal Reasoning for Logistics Robots

Monday, Jun 29, 2020

The Knowledge-Based Systems Group is, amongst others, doing research in task-level reasoning and agent controllers for mobile robots like in the RoboCup Logistics League (RCLL) as part of the Carologistics RoboCup Team.

Developing agents for such robotic tasks poses diverse problems to solve: acting rationally under hard real-time constraints, agent-to-agent communication, multi-robot cooperation, and task-level reasoning.

The scenario for the lab course will be the RoboCup Logistics League (RCLL). In this scenario, two competing groups of three robots each must complete dynamic production chains according to orders which are posted throughout the game period of 17 minutes. We have developed a simulation of the RCLL that allows to quickly run the game and test without long setup times of real robots.

The goal of this lab course is to model the RCLL scenario and integrate a task planning system using the CLIPS Executive (CX), a goal reasoning framework implemented in the programming language CLIPS. The CX is also used by the Carologistics RoboCup Team, which uses a distributed agent strategy. In contrast to the Carologistics' strategy, you will use a centralized agent, i.e., a single agent that controls all three robots centrally.

In this lab course you have the chance to

  • learn about robot software development
  • develop an intelligent control program
  • apply methods of AI to robotic scenarios

Videos

You can find videos showing and explaining the game at the Carologistics Youtube Channel. It specifically contains a playlist with videos of the RCLL Winter School 2015 that explain major components of the system.

Requirements

  • lecture “Artificial Intelligence” from our department (or objective evidence of equivalent knowledge)
  • lecture “Introduction to Knowledge Representation”
  • interest in logic-based programming
  • high motivation
  • Linux skills beneficial

Outline

The rough outline of the lab course’s schedule is as follows:

  • getting to know our software framework (Fawkes)
  • work in groups (2-4 students each)
  • concept + design
  • implementation
  • integration
  • evaluation

The date and time for the introductory meeting will be determined after the registration.