Self‐supervised learning to visually detect terrain surfaces for autonomous robots operating in forested terrain

Abstract

Autonomous robotic navigation in forested environments is difficult because of the highly variable appearance and geometric properties of the terrain. In most navigation systems, researchers assume a priori knowledge of the terrain appearance properties, geometric properties, or both. In forest environments, vegetation such as trees, shrubs, and bushes has appearance and geometric properties that vary with change of seasons, vegetation age, and vegetation species. In addition, in forested environments the terrain surface is often rough, sloped, and/or covered with a surface layer of grass, vegetation, or snow. The complexity of the forest environment presents difficult challenges for autonomous navigation systems. In this paper, a self-supervised sensing approach is introduced that attempts to robustly identify a drivable terrain surface for robots operating in forested terrain. The sensing system employs both LIDAR and vision sensor data. There are three main stages in the system: feature learning, feature training, and terrain prediction. In the feature learning stage, 3D range points from LIDAR are analyzed to obtain an estimate of the ground surface location. In the feature training stage, the ground surface estimate is used to train a visual classifier to discriminate between ground and nonground regions of the image. In the prediction stage, the ground surface location can be estimated at high frequency solely from vision sensor data. C 2012 Wiley Periodicals, Inc.

Computationally Inexpensive Appearance Based Terrain Learning in Unknown Environments

“…The LAGR platform was equipped with stereo-vision, proximity-sensors, inertial measurement unit, and infrared rangefinders. The nature of forested terrain and dense foliage led to the development of techniques for in-motion terrain learning ( [23]). The technique employs three stages : feature learning, feature training, and terrain prediction.…”

An Efficient Calibration Approach for Arbitrary Equipped 3-D LiDAR Based on an Orthogonal Normal Vector Pair

“…Recently, LiDARs are widely applied in UGV for autonomous navigation [1], object detection, localization [2], posture estimation [3] etc.. In these applications, LiDARs usually should be calibrated to vehicle coordinate, and the performance of LiDARs largely depends on their calibration.…”

Traversability analysis using terrain mapping and online-trained Terrain type classifier

“…The road estimation allowed the algorithm to identify which pixels were misclassified, and therefore, use them as examples to feed back the classifier. Another related paper of Zhou et al [5] adopts a road probabilistic distribution model, which assigns a weight to each pixel in order to give it an importance for the next retraining cycle; pixels located in the center of the estimated road will receive higher values than those on the borders.…”