Robots that succeed in factories stumble to complete
the simplest daily task humans take for granted, for the change
of environment makes the task exceedingly difficult. Aiming to
teach robot perform daily manipulative tasks in a changing
environment using human demonstrations, we collected our own
data of manipulative motions. The dataset focuses on force,
torque, position and orientation of objects manipulated in daily
tasks. It includes more than 1,400 trials of 33 types of daily
motions and more than 1,500 trials of pouring alone, as well as
helper code. We present our dataset to facilitate the research on
task-oriented interactive manipulation.
We present a dataset of daily interactive manipulation. Specifically, we record daily performed fine motion in which an object is manipulated to interact with another object. We refer to the person who executes the motion as subject, the manipulated object as tool, and the interactive object as object. We focus on recording the motion of the tool. In some cases, we also record the motion of the object.
The dataset consists of two parts. The first part contains 1,483 trials that cover 32 types of motions. We choose fine motions that people commonly perform in daily life which involve interaction with a variety of objects. Different subsets of the motions are found in multiple different motion-related datasets. The motions we collect include those that are most frequently executed in cooking scenarios except that we do not include pick-and-place because it barely involve change of orientation.
The second part contains the pouring motion alone. We collect it to help with motion generalization to different environments. We chose pouring because 1) pouring is found to be the second frequently executed motion in cooking, right after pick-and-place and 2) we can vary the environment setup of the pouring motion easily by switching different materials, cups, and containers. The pouring data contains 1,596 trials of pouring 3 materials from 6 cups into 10 containers. We collect the two parts of the data using the same system.
The dataset provides position and orientation (PO) with 100% coverage, and force and torque (FT) with 96% coverage, and depth vision with 37% coverage. The less-than-perfect FT coverage is because of the introduction of FT collection system after the PO collection system. The less-than-perfect coverage of depth results from filming restrictions.
|m10: "Use Black Brush", 15 Trials|
|m11: "Spear Stuff Using Fork", 15 Trials|
|m13: " Fasten Screw ", 13 Trials|
|m14: " Loosen Screw ", 35 Trials|
NOTE: The entire "Collected Data" shown below is not available at this time. When the paper is published the rest of the data will be available. Thank you for your patience and support.