A Simulated Environment for Traversability Estimation Experiments in Field Robotics Applications

被引:1
|
作者
Sevastopoulos, Christos [1 ]
Konstantopoulos, Stasinos [2 ]
机构
[1] Univ Texas Arlington, Arlington, TX 76019 USA
[2] NSCR Demokritos, Athens, Greece
基金
欧盟地平线“2020”;
关键词
Robot perception; machine learning; outdoors robotics applications;
D O I
10.1145/3453892.3462214
中图分类号
TP3 [计算技术、计算机技术];
学科分类号
0812 ;
摘要
We present an environment for simulated experiments in field robotics, and especially in experiments on estimating the traversability of foliage and other objects that appear as obstacles but that can be overcome by the robot without circumventing them. The simulated environment is developed in the Unity real-time development platform, integrated with the ROS middleware. In the preliminary experiments presented here, we demonstrate that our environment is able to simulate the sensory input needed in order to train supervised traversability estimation models.
引用
收藏
页码:256 / 257
页数:2
相关论文
共 50 条