• 主题
高级搜索  >
历史搜索 清空历史
首页> 外文会议>Unmanned Systems Technology IX; Proceedings of SPIE-The International Society for Optical Engineering; vol.6561 >Toward safe navigation in urban environments
【24h】

Toward safe navigation in urban environments

机译：在城市环境中实现安全导航

获取原文
获取原文并翻译 | 示例
页面导航
  • 摘要
  • 著录项
  • 相似文献
  • 相关主题

摘要

This paper presents a complete system for autonomous navigation of a mobile robot in urban environments. An urban environment is defined as one having hard surface and comprising curbs, ramps, and obstacles. The robot is required to traverse flat ground surfaces and ramps, but avoid curbs and obstacles. The system employs a 2-D laser rangefinder for terrain mapping. In order to filter erroneous sensor data (mixed pixels and noises), an Extended Kalman Filter (EKF) is used to segment the laser range data into straight-line segments and isolated points. The isolated points are then compared with those points at their neighboring straight-line segments to detect discontinuity in received energy (called reflectivity value in this work). The points exhibiting discontinuity of reflectivity are identified as erroneous data and removed. A so-called "Polar Traversability Index" measure is proposed to evaluate terrain traversal property. A PTI dictates the level of difficulty for a robot to move along the corresponding direction. It enables the robot to traverse wheelchair ramps and avoid curbs when negotiating sidewalks in urban environment. The advantage of using PTI over the conventional traversability index is that the robot's yaw angle is taken into account when computing the terrain traversal property at the corresponding direction. This allows the robot to snake up a steep ramp that may be too steep for the robot to climb if the conventional traversibility index were used. The efficacies of the PTI and the entire system have been verified by simulation and experiments with a real robot.
机译：本文提出了一个完整的系统，用于在城市环境中对移动机器人进行自主导航。城市环境被定义为具有坚硬的表面并且包括路缘，坡道和障碍物的环境。要求机器人穿越平坦的地面和坡道，但要避免路缘和障碍物。该系统采用二维激光测距仪进行地形测绘。为了过滤错误的传感器数据（混合像素和噪声），使用扩展卡尔曼滤波器（EKF）将激光测距数据分割为直线段和孤立点。然后将孤立的点与其相邻直线段上的那些点进行比较，以检测接收到的能量的不连续性（在这项工作中称为反射率值）。表现出反射率不连续性的点被识别为错误数据并被移除。提出了一种所谓的“极地可穿越性指数”措施来评估地形的可穿越性。 PTI指示机器人沿相应方向移动的难度。当在城市环境中协商人行道时，它使机器人能够横穿轮椅坡道并避免路缘石。使用PTI优于常规的可遍历性指标的优点是，在计算相应方向的地形遍历属性时，应考虑机器人的偏航角。如果使用常规的可穿越性指标，这会使机器人爬上一个陡峭的坡道，对于机器人来说，这可能太陡峭了。 PTI和整个系统的效率已通过使用真实机器人进行的仿真和实验得到验证。

著录项

相似文献

  • 外文文献
  • 中文文献
  • 专利
获取原文

客服邮箱：kefu@zhangqiaokeyan.com

京公网安备：11010802029741号 ICP备案号：京ICP备15016152号-6 六维联合信息科技 (北京) 有限公司©版权所有

  • 客服微信

  • 服务号