Segway DRIVE Benchmark
收藏资源简介:
Segway DRIVE Benchmark是由九号机器人有限公司创建的一个新颖且具有挑战性的数据集,旨在支持视觉地点识别和同步定位与地图构建(SLAM)研究。该数据集由一群九号配送机器人在执行任务时收集,这些机器人装备有全局快门鱼眼相机、消费级IMU、两个低成本轮编码器和一个可拆卸的高精度激光雷达。数据集涵盖了一年的时间,特点是平面运动、场景中的移动行人以及环境和照明的变化。这些因素为SLAM算法带来了严峻的挑战。此外,数据集还提出了几种评估度量,用于评估度量地点识别算法。该数据集适用于评估SLAM和地点识别方法,特别是在解决实际世界自主导航任务中的应用问题。
Segway DRIVE Benchmark is a novel and challenging dataset created by Ninebot Robotics Co., Ltd., aimed at supporting research on visual place recognition and simultaneous localization and mapping (SLAM). This dataset was collected by a fleet of Ninebot delivery robots during their operational tasks. These robots are equipped with global-shutter fisheye cameras, consumer-grade IMU, two low-cost wheel encoders, and a detachable high-precision LiDAR. The dataset spans a one-year period and features planar robot motion, moving pedestrians in the scene, as well as environmental and lighting variations. These factors pose severe challenges to SLAM algorithms. Furthermore, the dataset provides several evaluation metrics for assessing visual place recognition algorithms. This dataset is suitable for evaluating SLAM and place recognition methods, especially for addressing practical application challenges in real-world autonomous navigation tasks.

- 1Segway DRIVE Benchmark: Place Recognition and SLAM Data Collected by A Fleet of Delivery Robots九号机器人有限公司 · 2019年



