Ground-Challenge
收藏资源简介:
Ground-Challenge是一个专为地面机器人设计的SLAM数据集,由腾讯机器人X实验室创建。该数据集包含36个轨迹,覆盖了多种极端情况,如剧烈运动、严重遮挡、光照变化等。数据集通过配备多种传感器的地面机器人收集,包括RGB-D相机、惯性测量单元、轮式编码器和3D激光雷达。数据集旨在挑战现有的尖端SLAM系统,推动多传感器融合SLAM算法的发展,特别是在处理传感器故障和特定运动模式方面。
Ground-Challenge is a SLAM dataset specifically designed for ground robots, created by Tencent Robotics X Lab. This dataset contains 36 trajectories covering various extreme scenarios such as aggressive motion, severe occlusion, illumination changes and more. It is collected via ground robots equipped with multiple sensors, including RGB-D cameras, inertial measurement units (IMUs), wheel encoders and 3D LiDARs. The dataset aims to challenge state-of-the-art SLAM systems and promote the development of multi-sensor fusion SLAM algorithms, particularly in handling sensor failures and specific motion patterns.




