Plan Visualization and System Architecture in PDDL-based Planning

Question

I have built several domains and problems in PDDL and now I'm looking for a possibilty to visualize my domains, problems and solutions. My questions are as follows:

• Are there any tools for a rather simple graphical representation of plans (e.g. nodes and connections)?
• Are there tools that can display the current world state of my domain at any time (i.e. the value of all variables in my domain, after each step in my plan) in plain text?
• How do I integrate PDDL in the system architecture? If I want to use a 2D or 3D representation of my world (e.g. Gazebo) how can i "connect" Gazebo and PDDL?

Thanks!

Answer 1

Going over your questions one by one:

1. None made publicly available, but I am aware of several students of members of the Planning community working in tools like that. I'd suggest you to make the question on this mailing list: [email protected]

2. For that you'd need to modify one of the many existing planners and work it out yourself from their data structures or extend whatever debugging methods planners' authors have built into their systems. If you have the time and good C++ skills I'd suggest you to look into either Fast Downward (http://www.fast-downward.org/) or the less mature and simpler lwaptk (https://github.com/miquelramirez/lwaptk). If you are after some fast prototyping, and you are happy to compute the plans off-line, then I'd recommend you to look at Pyperplan (https://bitbucket.org/malte/pyperplan) a native Python planner which should quite easy to interface with pretty much anything (it just won't be very efficient when it comes to compute plans).

3. You'll have to work out yourself an interface between the model of your "Gazebo" world and the planning back-end, and the details depend on what a) what are you modeling in the "front-end" and b) what do you exactly want the planner to do for you. For an example of how to expose a relatively complex object model I'd suggest you to look at this little demo I put together a while back (https://github.com/miquelramirez/pr-as-planning-demo).