Teppei Saitoh

Online road surface analysis using laser remission value in urban environments

This paper describes the novel road surface analysis using reflectivity of a laser scanner in structured outdoor environments. The proposed approach makes estimation of road surface conditions robust by using information of remission value as reflectivity of a laser that much less depends on brightness of color or ambient lighting than passive camera. Our method can be applied to various structured outdoor environments by online estimating distributions of the remission value from the road surface. This article shows that the method is successfully verified with accuracy of approximately 99% at both (i) the testing course of the 2009 Real World Robot Challenge which is known as “Tsukuba Challenge” and (ii) our university campus.

Online road segmentation for urban complex environments

In this paper, we propose a novel approach to stable near and long range perception for various complex outdoor environments. Our techniques cope robustly with near-range road estimation using a laser scanner and long-range terrain classification using a color camera. Near-range road surface conditions are estimated by using information of remission value as reflectivity of a laser. We apply graph cut algorithm to grid map in order to estimate road region robustly also in complex environments where fallen leaves exist sparsely. Moreover, we propose superpixel-based terrain classification method which can give a good performance compared with pixel-based classification. Experimental results have shown that demonstrate a marked increase in long-range classification and near-range road estimation accuracy over standard methods.

Near-to-Far Self-Supervised Road Estimation for Complicated Environments

Abstract In this paper, we propose a novel approach to stable near and long range perception for various complex outdoor environments. Our techniques cope robustly with near-range road estimation using a laser scanner and long-range terrain classification using a color camera. Near-range road surface conditions are estimated by using information of remission value as reflectivity of a laser. We apply graph cut algorithm to grid map in order to estimate road region robustly also in complex environments where fallen leaves exist sparsely. Moreover, we propose superpixel-based terrain classification method which can give a good performance compared with pixel-based classification. Our approach has real-time processing. Experimental results have shown that demonstrate a marked increase in long-range classification and near-range road estimation accuracy over standard methods.

Effective strategy for autonomous navigation without prior knowledge in FastSLAM

This paper describes the efficient strategy for planning for autonomous mobile robot navigation using the information which is the resulting probabilistic distribution of position and map acquired by solving the SLAM. In order to estimate good robots position and map, we used a highly efficient variant of the grid based version of the FastSLAM algorithm. D* Lite algorithm for global path planning, which has the effective replanning at the partial cost field changed, was employed. Because the acquired map in the SLAM is also grid based which indicates the probabilistic existence of the obstacles in each grid, and SLAMs uncertain grid map is utilized to compute the cost field for path planning. In this research, it was proven that the mobile robot could carry out autonomous navigation in the outdoor field without prior information. This paper presented that the mobile robot reached the predefined goal with estimating good position and map simultaneously.

Vision-Based Probabilistic Map Estimation with an Inclined Surface Grid for Rough Terrain Rover Navigation

This paper describes a novel map representation called Inclined Surface Grid (ISG) maps that provides the ability of modeling traversability of an environment. In order to accomplish safer navigation autonomously with a planetary rover by avoiding hazardous areas, appropriate traversability of the terrain has to be evaluated. In the ISG maps, the patch on each grid stores not only traversability but more detailed information — height, slopes (roll and pitch angle) and roughness. The ISG maps have higher degree-of-freedom knowledge about the surface compared with two-dimensional grid or elevation maps and have very good performance to analyze traversability. In order to assure the reliability of surface estimation in far range areas where the point cloud density decreases, an expanding sampling area approach is introduced to homogenize the point density in a grid by increasing the sampling points. Moreover, probabilistically updating using a stereo vision-specified error model is introduced to estimate the information of each patch. Thus, probabilistic updating allows the ISG maps to yield few failed patches. In the experiment, the resulting geometrical information of our ISG maps converged into an accurate geometry of terrain more than the simple overwriting approach. It is shown that our approach can also create the appropriate traversability map in rough terrain.

Simultaneous Adaptive Path planning system for the real world application

In this paper, we propose a path planning system named SAP (Simultaneous Adaptive Path planning) which can make a plan adapt to kinematic and dynamic constraints, and dynamically changing environment simultaneously. SAP has three key issues: condition layers, a dynamic space, and a search tree. Each condition layer involves a factor which influences running of the robot such as coefficient of friction and elevation of the field. Dynamic space is an area in velocity domain where the robot could reach in the next time step. The limitation (means outer shape) of the dynamic space is defined as a function of all conditions and a robot model, velocities that can be achieved within a short time interval. Search tree that consider the dynamic space expands like tree to search a path from start to goal. By these mechanisms, SAP can generate a path that robot can achieve in real environment.