PackIt: A Virtual Environment for Geometric Planning

ICML 2020  ·  Ankit Goyal, Jia Deng ·

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.

PDF Abstract ICML 2020 PDF

Datasets


Introduced in the Paper:

PackIt

Used in the Paper:

ShapeNet OpenAI Gym AI2-THOR HoME CHALET

Results from the Paper


Task Dataset Model Metric Name Metric Value Global Rank Result Benchmark
Robot Task Planning PackIt PackNN Average Reward 64.9 # 1
Robot Task Planning PackIt Heuristic Largest First-Aligned-Random Average Reward 49.4 # 3
Robot Task Planning PackIt Heuristic Largest First-Aligned-BLBF Average Reward 59.2 # 2
Robot Task Planning PackIt Heuristic Random-Aligned-BLBF Average Reward 41.9 # 4

Methods


No methods listed for this paper. Add relevant methods here