Accelerated Robust Point Cloud Registration in Natural Environments through Positive and Unlabeled Learning Maxime Latulippe, Alexandre Drouin, Philippe Gigu` ere, and Franc ¸ois Laviolette Laval University, Quebec, Canada {maxime.latulippe.1, alexandre.drouin.8}@ulaval.ca, {philippe.giguere, francois.laviolette}@ift.ulaval.ca Abstract Localization of a mobile robot is crucial for au- tonomous navigation. Using laser scanners, this can be facilitated by the pairwise alignment of con- secutive scans. In this paper, we are interested in improving this scan alignment in challenging nat- ural environments. For this purpose, local descrip- tors are generally effective as they facilitate point matching. However, we show that in some natural environments, many of them are likely to be unreli- able, which affects the accuracy and robustness of the results. Therefore, we propose to filter the unre- liable descriptors as a prior step to alignment. Our approach uses a fast machine learning algorithm, trained on-the-fly under the positive and unlabeled learning paradigm without the need for human in- tervention. Our results show that the number of descriptors can be significantly reduced, while in- creasing the proportion of reliable ones, thus speed- ing up and improving the robustness of the scan alignment process. 1 Introduction To accomplish autonomous navigation in unknown environ- ments, a mobile robot must be able to localize itself. Proprio- ceptive sensors, such as odometry and inertial units, cannot be used alone to precisely keep track of the long-term robot pose, as they are subject to drift. Global localization systems like GPS can fulfill the task, but in some environments they may not be available. An alternative is to use a 3D laser scanner to exploit information from the surrounding environment in order to estimate the robot’s pose. Although being well handled in structured environments (corridors, buildings), this problem remains difficult in unstructured environments like wood or planetary terrains. To localize using laser scanners, consecutive scans (point clouds) taken with these sensors can be registered (i.e. aligned) in a pairwise manner to estimate the motion performed by the robot at each step. This motion, decomposed in a translation T and a rotation R, is often computed using the popular Iterative Closest Point (ICP) algorithm [Besl and McKay, 1992] or one of its variants [Rusinkiewicz and Levoy, 2001]. However, because ICP is subject to the problem of local minima, a prior coarse alignment of the point clouds increases the likelihood of converging towards the true solution. This coarse alignment can be performed using measure- ments from proprioceptive sensors, although they may not be reliable enough in some situations (e.g. on a slippery terrain for odometry). In such cases, the coarse alignment must be determined from the point clouds themselves. For this matter, one can compute local descriptors (set of values) depicting the geometry of each point’s vicinity in the scans and match the similar descriptors to establish correspondences between scans. Sample Consensus Initial Alignment (SAC-IA), pre- sented in [Rusu et al., 2009], is an adaptation of Random Sample Consensus (RANSAC) [Fischler and Bolles, 1981] to the point cloud registration problem and is based on this idea. Points are randomly picked in the source cloud and matched randomly within a list of the most potentially corresponding points (most similar descriptors) in the target cloud. For 3D point clouds, three correspondences are thus established and the geometrical transformation R and T that best aligns these corresponding points is computed. The process is repeated for N iterations and the transformation that yields the small- est alignment error on the clouds is kept. The accuracy of this coarse alignment therefore depends on the quality of the descriptors extracted, as more discriminative and robust de- scriptors should lead to more valid correspondences. On the other hand, with a descriptor set of poorer quality, the algo- rithm statistically requires a greater number of iterations to find an alignment with the same accuracy. In this paper, we address the coarse registration problem in natural unstructured environments, including those featuring dense vegetation. Section 3 explains the issues associated with descriptors in this type of environment. We aim at in- creasing the robustness of SAC-IA, as well as its computation efficiency, by filtering the unreliable descriptors beforehand. Our approach, based on positive and unlabeled learning, is described in Section 4. Section 5 details the experimentations and results, and section 7 concludes. 2 Related work Many types of descriptors have been proposed over the years. The interested reader can refer to [Tangelder and Veltkamp, 2008] for a survey. Some description methods extract key- points as a prior step. The well-known Scale-Invariant Feature Transform (SIFT) descriptor [Lowe, 2004] includes such key- Proceedings of the Twenty-Third International Joint Conference on Artificial Intelligence 2480