Find your own way: Weakly-supervised segmentation of path proposals for urban autonomy

Abstract

We present a weakly-supervised approach to segmenting proposed drivable paths in images with the goal of autonomous driving in complex urban environments. Using recorded routes from a data collection vehicle, our proposed method generates vast quantities of labelled images containing proposed paths and obstacles without requiring manual annotation, which we then use to train a deep semantic segmentation network. With the trained network we can segment proposed paths and obstacles at run-time using a vehicle equipped with only a monocular camera without relying on explicit modelling of road or lane markings. We evaluate our method on the largescale KITTI and Oxford RobotCar datasets and demonstrate reliable path proposal and obstacle segmentation in a wide variety of environments under a range of lighting, weather and traffic conditions. We illustrate how the method can generalise to multiple path proposals at intersections and outline plans to incorporate the system into a framework for autonomous urban driving.

Safe Visual Navigation via Deep Learning and Novelty Detection

“…For instance, the DARPA LAGR program featured long-range terrain classification using a neural network, in an similar role to our collision prediction approach [13]. Barnes et al [3] and Oliveira et al [24] provide more recent examples of deep learning used to segment image pixels into drivable routes, which can then be used for planning. While we focus on supervised learning of collision probability, there are many other ways to map between images and actions, including end-to-end neural networks [6,19], affordance-based representations [7], reinforcement learning using either simulated or real images [23,31], and classification of paths from manually collected data [11].…”

Planning and Decision-Making for Autonomous Vehicles

“…The method works in a weakly supervised manner, since driving paths can be labeled automatically from past driving data. Similarly, a semantic segmentation network may be employed to generate path proposals in the camera image space (69 are labeled and projected into the image space in an automated fashion. During deployment, only a camera image is needed to classify path proposals and obstacles.…”

Off-Road Drivable Area Extraction Using 3D LiDAR Data

“…Recently, many deep learning methods have achieved impressive results on related tasks [22][23] [24][25] [26]. Compared to the traditional methods, deep networks can learn high-level semantic features directly from the data, which usually performs better than human-designed features.…”

“…To reduce the demand for human annotation, some studies have used a simulator to access endless data for training [25]. In addition, other studies have focused on weakly supervised [22] or semi-supervised methods [20], attempting to use auto-generated weak labels as substitution, which can be easily accessed.…”