Robotic Pick-and-Place of Novel Objects in Clutter with Multi-Affordance Grasping and Cross-Domain Image Matching

TL;DR

This paper introduces a robotic pick-and-place system capable of handling both known and novel objects in cluttered environments without task-specific training, using affordance prediction and cross-domain image matching.

Contribution

It presents a novel system combining category-agnostic affordance grasping with cross-domain image recognition for novel objects, eliminating the need for additional training data.

Findings

High success rates in cluttered environments

Accurate recognition of known and novel objects

Achieved 1st place in Amazon Robotics Challenge 2017

Abstract

This paper presents a robotic pick-and-place system that is capable of grasping and recognizing both known and novel objects in cluttered environments. The key new feature of the system is that it handles a wide range of object categories without needing any task-specific training data for novel objects. To achieve this, it first uses a category-agnostic affordance prediction algorithm to select and execute among four different grasping primitive behaviors. It then recognizes picked objects with a cross-domain image classification framework that matches observed images to product images. Since product images are readily available for a wide range of objects (e.g., from the web), the system works out-of-the-box for novel objects without requiring any additional training data. Exhaustive experimental results demonstrate that our multi-affordance grasping achieves high success rates for a wide variety of objects in clutter, and our recognition algorithm achieves high accuracy for both known and novel grasped objects. The approach was part of the MIT-Princeton Team system that took 1st place in the stowing task at the 2017 Amazon Robotics Challenge. All code, datasets, and pre-trained models are available online at http://arc.cs.princeton.edu