Robotic Learning the Sequence of Packing Irregular Objects from Human Demonstrations

TL;DR

This paper presents a method for teaching robots to pack irregular objects by learning from human demonstrations, resulting in sequences that are more human-like and outperform human performance in packing tasks.

Contribution

The authors introduce a VR-based data collection platform and a Markov chain model to predict packing sequences, advancing robotic bin packing with irregular objects.

Findings

Model outperforms human performance in sequence prediction.

Generated sequences are more human-like than actual human sequences.

VR platform and dataset are publicly available for further research.

Abstract

We tackle the challenge of robotic bin packing with irregular objects, such as groceries. Given the diverse physical attributes of these objects and the complex constraints governing their placement and manipulation, employing preprogrammed strategies becomes unfeasible. Our approach is to learn directly from expert demonstrations in order to extract implicit task knowledge and strategies to ensure safe object positioning, efficient use of space, and the generation of human-like behaviors that enhance human-robot trust. We rely on human demonstrations to learn a Markov chain for predicting the object packing sequence for a given set of items and then compare it with human performance. Our experimental results show that the model outperforms human performance by generating sequence predictions that humans classify as human-like more frequently than human-generated sequences. The human demonstrations were collected using our proposed VR platform, BoxED, which is a box packaging environment for simulating real-world objects and scenarios for fast and streamlined data collection with the purpose of teaching robots. We collected data from 43 participants packing a total of 263 boxes with supermarket-like objects, yielding 4644 object manipulations. Our VR platform can be easily adapted to new scenarios and objects, and is publicly available, alongside our dataset, at https://github.com/andrejfsantos4/BoxED.