pith. sign in

arxiv: 1710.04280 · v1 · pith:LHUNO5YUnew · submitted 2017-10-11 · 💻 cs.RO

GeneSIS-RT: Generating Synthetic Images for training Secondary Real-world Tasks

classification 💻 cs.RO
keywords datagenesis-rtimagestasksreal-worldtraininggeneratingsynthetic
0
0 comments X
read the original abstract

We propose a novel approach for generating high-quality, synthetic data for domain-specific learning tasks, for which training data may not be readily available. We leverage recent progress in image-to-image translation to bridge the gap between simulated and real images, allowing us to generate realistic training data for real-world tasks using only unlabeled real-world images and a simulation. GeneSIS-RT ameliorates the burden of having to collect labeled real-world images and is a promising candidate for generating high-quality, domain-specific, synthetic data. To show the effectiveness of using GeneSIS-RT to create training data, we study two tasks: semantic segmentation and reactive obstacle avoidance. We demonstrate that learning algorithms trained using data generated by GeneSIS-RT make high-accuracy predictions and outperform systems trained on raw simulated data alone, and as well or better than those trained on real data. Finally, we use our data to train a quadcopter to fly 60 meters at speeds up to 3.4 m/s through a cluttered environment, demonstrating that our GeneSIS-RT images can be used to learn to perform mission-critical tasks.

This paper has not been read by Pith yet.

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.