To Go or Not To Go? A Near Unsupervised Learning Approach For Robot Navigation
This addresses a safety-critical navigation problem for robots in dynamic environments, offering an incremental improvement by reducing data collection risks.
The paper tackles the problem of enabling robots to classify traversable spaces using visual data, proposing unsupervised and near-unsupervised GAN-based methods that reduce the need for negative training examples, and verifies effectiveness on a test dataset in an unseen environment while demonstrating utility for path planning via 'GoNoGo' costmaps.
It is important for robots to be able to decide whether they can go through a space or not, as they navigate through a dynamic environment. This capability can help them avoid injury or serious damage, e.g., as a result of running into people and obstacles, getting stuck, or falling off an edge. To this end, we propose an unsupervised and a near-unsupervised method based on Generative Adversarial Networks (GAN) to classify scenarios as traversable or not based on visual data. Our method is inspired by the recent success of data-driven approaches on computer vision problems and anomaly detection, and reduces the need for vast amounts of negative examples at training time. Collecting negative data indicating that a robot should not go through a space is typically hard and dangerous because of collisions, whereas collecting positive data can be automated and done safely based on the robot's own traveling experience. We verify the generality and effectiveness of the proposed approach on a test dataset collected in a previously unseen environment with a mobile robot. Furthermore, we show that our method can be used to build costmaps (we call as "GoNoGo" costmaps) for robot path planning using visual data only.