A New Method for Classifying Scenes for Simultaneous Localization and Mapping Using the Boundary Object Function Descriptor on RGB-D Points.

Scene classification in autonomous navigation is a highly complex task due to variations, such as light conditions and dynamic objects, in the inspected scenes; it is also a challenge for small-factor computers to run modern and highly demanding algorithms. In this contribution, we introduce a novel method for classifying scenes in simultaneous localization and mapping (SLAM) using the boundary object function (BOF) descriptor on RGB-D points. Our method aims to reduce complexity with almost no performance cost. All the BOF-based descriptors from each object in a scene are combined to define the scene class. Instead of traditional image classification methods such as ORB or SIFT, we use the BOF descriptor to classify scenes. Through an RGB-D camera, we capture points and adjust them onto layers than are perpendicular to the camera plane. From each plane, we extract the boundaries of objects such as furniture, ceilings, walls, or doors. The extracted features compose a bag of visual words classified by a support vector machine. The proposed method achieves almost the same accuracy in scene classification as a SIFT-based algorithm and is 2.38× faster. The experimental results demonstrate the effectiveness of the proposed method in terms of accuracy and robustness for the 7-Scenes and SUNRGBD datasets.

Graph Search-Based Exploration Method Using a Frontier-Graph Structure for Mobile Robots.

This paper describes a graph search-based exploration method. Segmented frontier nodes and their relative transformations constitute a frontier-graph structure. Frontier detection and segmentation are performed using local grid maps of adjacent nodes. The proposed frontier-graph structure can systematically manage local information according to the exploration state and overcome the problem caused by updating a single global grid map. The robot selects the next target using breadth-first search (BFS) exploration of the frontier-graph. The BFS exploration is improved to generate an efficient loop-closing sequence between adjacent nodes. We verify that our BFS-based exploration method can gradually extend the frontier-graph structure and efficiently map the entire environment, regardless of the starting position.

A Revisiting Method Using a Covariance Traveling Salesman Problem Algorithm for Landmark-Based Simultaneous Localization and Mapping.

This paper presents an efficient revisiting algorithm for landmark-based simultaneous localization and mapping (SLAM). To reduce SLAM uncertainty in terms of a robot's pose and landmark positions, the method autonomously evaluates valuable landmarks for the data associations in the SLAM algorithm and selects positions to revisit by considering both landmark visibility and sensor measurement uncertainty. The optimal path among the selected positions is obtained by applying the traveling salesman problem (TSP) algorithm. To plan a path that reduces overall uncertainty, the cost matrix associated with the change in covariance between all selected positions of all pairs is applied for the TSP algorithm. From simulations, it is verified that the proposed method efficiently reduces and maintains SLAM uncertainty at the low level compared to the backtracking method.

Indirect Correspondence-Based Robust Extrinsic Calibration of LiDAR and Camera.

LiDAR and cameras have been broadly utilized in computer vision and autonomous vehicle applications. However, in order to convert data between the local coordinate systems, we must estimate the rigid body transformation between the sensors. In this paper, we propose a robust extrinsic calibration algorithm that can be implemented easily and has small calibration error. The extrinsic calibration parameters are estimated by minimizing the distance between corresponding features projected onto the image plane. The features are edge and centerline features on a v-shaped calibration target. The proposed algorithm contributes two ways to improve the calibration accuracy. First, we use different weights to distance between a point and a line feature according to the correspondence accuracy of the features. Second, we apply a penalizing function to exclude the influence of outliers in the calibration datasets. Additionally, based on our robust calibration approach for a single LiDAR-camera pair, we introduce a joint calibration that estimates the extrinsic parameters of multiple sensors at once by minimizing one objective function with loop closing constraints. We conduct several experiments to evaluate the performance of our extrinsic calibration algorithm. The experimental results show that our calibration method has better performance than the other approaches.