PackIt: A Virtual Environment for Geometric Planning
This provides a new benchmark for researchers in robotics and AI to test geometric planning abilities, though it is incremental as it builds on existing interactive environment frameworks.
The authors tackled the lack of environments for evaluating geometric planning by introducing PackIt, a virtual environment where agents must pack objects into a limited space, and they created challenging tasks using an evolutionary algorithm while testing various baselines.
The ability to jointly understand the geometry of objects and plan actions for manipulating them is crucial for intelligent agents. We refer to this ability as geometric planning. Recently, many interactive environments have been proposed to evaluate intelligent agents on various skills, however, none of them cater to the needs of geometric planning. We present PackIt, a virtual environment to evaluate and potentially learn the ability to do geometric planning, where an agent needs to take a sequence of actions to pack a set of objects into a box with limited space. We also construct a set of challenging packing tasks using an evolutionary algorithm. Further, we study various baselines for the task that include model-free learning-based and heuristic-based methods, as well as search-based optimization methods that assume access to the model of the environment. Code and data are available at https://github.com/princeton-vl/PackIt.