Safe and reliable autonomous navigation in unstructured environments remains a challenge for field robots. In particular, operating on vegetated terrain is problematic, because simple purely geometric traversability analysis methods typically classify dense foliage as nontraversable. As traversing through vegetated terrain is often possible and even preferable in some cases (e.g., to avoid executing longer paths), more complex multimodal traversability analysis methods are necessary. In this article, we propose a three-dimensional (3D) traversability mapping algorithm for outdoor environments, able to classify sparsely vegetated areas as traversable, without compromising accuracy on other terrain types. The proposed normal distributions transform traversability mapping (NDT-TM) representation exploits 3D LIDAR sensor data to incrementally expand normal distributions transform occupancy (NDT-OM) maps. In addition to geometrical information, we propose to augment the NDT-OM representation with statistical data of the permeability and reflectivity of each cell. Using these additional features, we train a support-vector machine classifier to discriminate between traversable and nondrivable areas of the NDT-TM maps. We evaluate classifier performance on a set of challenging outdoor environments and note improvements over previous purely geometrical traversability analysis approaches.
Matching and merging overlapping point clouds is a common procedure in many applications, including mobile robotics, three-dimensional mapping, and object visualization. However, fully automatic point-cloud matching, without manual verification, is still not possible because no matching algorithms exist today that can provide any certain methods for detecting misaligned point clouds. In this article, we make a comparative evaluation of geometric consistency methods for classifying aligned and nonaligned point-cloud pairs. We also propose a method that combines the results of the evaluated methods to further improve the classification of the point clouds. We compare a range of methods on two data sets from different environments related to mobile robotics and mapping. The results show that methods based on a Normal Distributions Transform representation of the point clouds perform best under the circumstances presented herein.
This paper presents the development, testing and validation of SWEEPER, a robot for harvesting sweet pepper fruit in greenhouses. The robotic system includes a six degrees of freedom industrial arm equipped with a specially designed end effector, RGB-D camera, high-end computer with graphics processing unit, programmable logic controllers, other electronic equipment, and a small container to store harvested fruit. All is mounted on a cart that autonomously drives on pipe rails and concrete floor in the end-user environment. The overall operation of the harvesting robot is described along with details of the algorithms for fruit detection and localization, grasp pose estimation, and motion control. The main contributions of this paper are the integrated system design and its validation and extensive field testing in a commercial greenhouse for different varieties and growing conditions. A total of 262 fruits were involved in a 4-week long testing period. The average cycle time to harvest a fruit was 24 s. Logistics took approximately 50% of this time (7.8 s for discharge of fruit and 4.7 s for platform movements). Laboratory experiments have proven that the cycle time can be reduced to 15 s by running the robot manipulator at a higher speed. The harvest success rates were 61% for the best fit crop conditions and 18% in current crop conditions. This reveals the importance of finding the best fit crop conditions and crop varieties for successful robotic harvesting. The SWEEPER robot is the first sweet pepper harvesting robot to demonstrate this kind of performance in a commercial greenhouse.
Registration of point cloud data containing both depth and color information is critical for a variety of applications, including in-field robotic plant manipulation, crop growth modeling, and autonomous navigation. However, current state-of-the-art registration methods often fail in challenging agricultural field conditions due to factors such as occlusions, plant density, and variable illumination. To address these issues, we propose the NDT-6D registration method, which is a color-based variation of the Normal Distribution Transform (NDT) registration approach for point clouds. Our method computes correspondences between pointclouds using both geometric and color information and minimizes the distance between these correspondences using only the three-dimensional (3D) geometric dimensions. We evaluate the method using the GRAPES3D data set collected with a commercial-grade RGB-D sensor mounted on a mobile platform in a vineyard. Results show that registration methods that only rely on depth information fail to provide quality registration for the tested data set. The proposed color-based variation outperforms state-of-the-art methods with a root mean square error (RMSE) of 1.1-1.6 cm for NDT-6D compared with 1.1-2.3 cm for other color-information-based methods and 1.2-13.7 cm for noncolor-information-based methods. The proposed method is shown to be robust against noises using the TUM RGBD data set by artificially adding noise present in an outdoor scenario. The relative pose error (RPE) increased similar to 14% for our method compared to an increase of similar to 75% for the best-performing registration method. The obtained average accuracy suggests that the NDT-6D registration methods can be used for in-field precision agriculture applications, for example, crop detection, size-based maturity estimation, and growth modeling.
We propose a new approach to appearance-based loop detection for mobile robots, usingthree-dimensional (3D) laser scans. Loop detection is an important problem in the simultaneouslocalization and mapping (SLAM) domain, and, because it can be seen as theproblem of recognizing previously visited places, it is an example of the data associationproblem. Without a flat-floor assumption, two-dimensional laser-based approaches arebound to fail in many cases. Two of the problems with 3D approaches that we address inthis paper are how to handle the greatly increased amount of data and how to efficientlyobtain invariance to 3D rotations.We present a compact representation of 3D point cloudsthat is still discriminative enough to detect loop closures without false positives (i.e.,detecting loop closure where there is none). A low false-positive rate is very important becausewrong data association could have disastrous consequences in a SLAM algorithm.Our approach uses only the appearance of 3D point clouds to detect loops and requires nopose information. We exploit the normal distributions transform surface representationto create feature histograms based on surface orientation and smoothness. The surfaceshape histograms compress the input data by two to three orders of magnitude. Becauseof the high compression rate, the histograms can be matched efficiently to compare theappearance of two scans. Rotation invariance is achieved by aligning scans with respectto dominant surface orientations. We also propose to use expectation maximization to fit a gamma mixture model to the output similarity measures in order to automatically determinethe threshold that separates scans at loop closures from nonoverlapping ones.Wediscuss the problem of determining ground truth in the context of loop detection and thedifficulties in comparing the results of the few available methods based on range information.Furthermore, we present quantitative performance evaluations using three realworlddata sets, one of which is highly self-similar, showing that the proposed methodachieves high recall rates (percentage of correctly identified loop closures) at low falsepositiverates in environments with different characteristics.
Scan registration is an essential sub-task when building maps based on range finder data from mobile robots. The problem is to deduce how the robot has moved between consecutive scans, based on the shape of overlapping portions of the scans. This paper presents a new algorithm for registration of 3D data. The algorithm is a generalisation and improvement of the normal distributions transform (NDT) for 2D data developed by Biber and Straßer, which allows for accurate registration using a memory-efficient representation of the scan surface. A detailed quantitative and qualitative comparison of the new algorithm with the 3D version of the popular ICP (iterative closest point) algorithm is presented. Results with actual mine data, some of which were collected with a new prototype 3D laser scanner, show that the presented algorithm is faster and slightly more reliable than the standard ICP algorithm for 3D registration, while using a more memory-efficient scan surface representation.
An increasing number of robots for outdoor applications rely on complex three-dimensional (3D) environmental models. In many cases, 3D maps are used for vital tasks, such as path planning and collision detection in challenging semistructured environments. Thus, acquiring accurate three-dimensional maps is an important research topic of high priority for autonomously navigating robots. This article proposes an evaluation method that is designed to compare the consistency with which different representations model the environment. In particular, the article examines several popular (probabilistic) spatial representations that are capable of predicting the occupancy of any point in space, given prior 3D range measurements. This work proposes to reformulate the obtained environmental models as probabilistic binary classifiers, thus allowing for the use of standard evaluation and comparison procedures. To avoid introducing localization errors, this article concentrates on evaluating models constructed from measurements acquired at fixed sensor poses. Using a cross-validation approach, the consistency of different representations, i.e., the likelihood of correctly predicting unseen measurements in the sensor field of view, can be evaluated. Simulated and real-world data sets are used to benchmark the precision of four spatial models—occupancy grid, triangle mesh, and two variations of the three-dimensional normal distributions transform (3D-NDT)—over various environments and sensor noise levels. Overall, the consistency of representation of the 3D-NDT is found to be the highest among the tested models, with a similar performance over varying input data.