Overview / Usage

This research introduces Roblocks, a user-friendly system for learning AI planning concepts using mobile manipulator robots. It uses a visual programming interface based on block-structured programming to make AI planning concepts easier to grasp. Users get the robot to accomplish any desired tasks by dynamically populating puzzle shaped blocks encoding the robot's possible actions, allowing them to carry out tasks like navigation, planning, and manipulation by connecting blocks instead of writing code. Roblocks uses a two-stage approach, where in the first stage users are made to re-arrange a jumbled sequence of actions of a plan in the correct order so that a given goal could be achieved. In the second stage, they get to select actions of their choice but only those actions pertaining to the current state are made available to them, thereby pruning down the vast number of possible actions and suggesting only the truly feasible and relevant actions. Both of these stages have a simulation where the user plan is executed. Moreover, if the user plan is invalid or fails to achieve the given goal condition then an explanation is provided for the failure.

Methodology / Approach

Roblocks is a visual programming interface that lets users control a robot by connecting puzzle shaped blocks instead of typing code. The interface provides actions as blocks which the robot can perform. The interface is implemented in a web browser, enabling users to start programming the robot without having to set up a development environment. The user-plan is executed on a simulation or robot if it is found to be valid or else an explanation is provided showing the cause of the failure. If the user plan fails in achieving the given goal condition then it will show all the missing facts from the goal condition on the GUI. And, if the plan fails because of a wrong action then it will show which proposition in the precondition of the failed action could not be met along with the entire trace of all the previous actions within the plan that affected the value of this proposition

Technologies Used

Java, Python, OpenRAVE, PDDL, Html5, JQuery, AJAX

Other links

• Youtube
• Website

• Github (https://github.com/chiravdave)

• Linkedin