Robot handle grasping failure data

Short summary

Accompanying dataset for our paper

A. Mitrevski, P. G. Plöger, and G. Lakemeyer, "Robot Action Diagnosis and Experience Correction by Falsifying Parameterised Execution Models," in Proceedings of the IEEE International Conference on Robotics and Automation (ICRA), 2021.

Contents

The dataset includes a single zip archive, containing data from the experiment described in the paper (conducted with a Toyota HSR). The zip archive contains three subdirectories:

• handle_grasping_failure_database: A dump of a MongoDB database containing data from the handle grasping experiment, including ground-truth grasping failure annotations
• pre_arm_motion_images: Images collected from the robot's hand camera before moving the robot's hand towards the handle
• pregrasp_images: Images collected from the robot's hand camera just before closing the gripper for grasping

The image names include the time stamp at which the images were taken; this allows matching each image with the execution data in the database.

Database usage

After unzipping the archive, the database can be restored with the command

mongorestore handle_grasping_failure_database

This will create a MongoDB database with the name drawer_handle_grasping_failures.

Code for processing the data and failure analysis can be found in our GitHub repository.