GONet: A Semi-Supervised Deep Learning Approach For Traversability Estimation

By Noriaki Hirose, Amir Sadeghian, Marynel Vázquez, Patrick Goebel, Silvio Savarese. 2018

89 citations recorded by the source corpus.

We present semi-supervised deep learning approaches for traversability estimation from fisheye images. Our method, GONet, and the proposed extensions leverage Generative Adversarial Networks (GANs) to effectively predict whether the area seen in the input image(s) is safe for a robot to traverse. These methods are trained with many positive images of traversable places, but just a small set of negative images depicting blocked and unsafe areas. This makes the proposed methods practical. Positive examples can be collected easily by simply operating a robot through traversable spaces, while obtaining negative examples is time consuming, costly, and potentially dangerous. Through extensive experiments and several demonstrations, we show that the proposed traversability estimation approaches are robust and can generalize to unseen scenarios. Further, we demonstrate that our methods are memory efficient and fast, allowing for real-time operation on a mobile robot with single or stereo fisheye cameras. As part of our contributions, we open-source two new datasets for traversability estimation. These datasets are composed of approximately 24h of videos from more than 25 indoor environments. Our methods outperform baseline approaches for traversability estimation on these new datasets.

Subfields: Aerospace Engineering, Computer Vision and Pattern Recognition

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Aerospace Engineering

In Computer Vision and Pattern Recognition

Citations in the corpus

BADGR: An Autonomous Self-Supervised Learning-Based Navigation System (2020, methodology): “However, these methods typically depend on existing SLAM approaches [4, 5, 23, 9, 24] or humans [6, 7] in order to provide the semantic labels, which consequently means these approaches either inherit the limitations of geometric approaches or are not autonomously self-improving.”
Gibson Env: Real-World Perception for Embodied Agents (2018, background): “A large portion of them are nonlearning based [50, 27, 49], while recent methods have attempted learning visuomotor policies end-to-end [100, 54] taking advantage of imitation learning [69], reinforcement learning [74, 41, 73, 41, 5, 6], acting by prediction [28] or self-supervision [38, 63, 28, 62,”
BridgeData V2: A Dataset for Robot Learning at Scale (2023, background): “There are also several large datasets for robotic navigation [36, 37, 38], some covering multiple widely available mobile robot platforms [39].”
Deep Visual MPC-Policy Learning for Navigation (2019, methodology): “Hirose et al. [33] presented GONet, a deep neural network-based method that estimates the traversable probability from an RGB image.”
Where Should I Walk? Predicting Terrain Properties From Images Via Self-Supervised Learning (2019, methodology): “For semantic-aware navigation, additional and richer sensor streams like grayscale [4], RGB [5], [8]–[11], NIR [5], [12] and thermal cameras [13] as well as RADAR [14] have been used.”