社区室外场景定位与建图标准数据集

主要面向自主机器人与人工智能研究、高质量多传感器SLAM数据集需求建设，基于自主研发的一体式多传感器平台采集产生，基于双目彩色相机、双目灰度相机、激光雷达、轮速计、IMU等传感器进行高时空精度的同步采集，采集场景为上海交通大学学生创新中心，场景特点为存在复杂光照、光照变化(室内外切换)等挑战性因素。

This dataset is developed to meet the demands of high-quality multi-sensor SLAM datasets for autonomous robotics and artificial intelligence research. It was collected using an independently developed integrated multi-sensor platform, with synchronized high spatiotemporal accuracy data acquired via multiple sensors including binocular color cameras, binocular grayscale cameras, LiDAR, wheel speed sensors, and Inertial Measurement Units (IMUs). The data collection was conducted at the Student Innovation Center of Shanghai Jiao Tong University, which features challenging conditions such as complex lighting and illumination changes including indoor-outdoor transitions.

搜集汇总

背景与挑战

背景概述

该数据集是一个面向自主机器人与人工智能研究的多传感器SLAM标准数据集，基于双目相机、激光雷达、IMU等多种传感器高精度同步采集，旨在支持复杂光照和室内外切换等挑战性环境下的定位与建图算法开发。数据集由上海交通大学创建，属于国家重点研发计划项目，数据量为49.65GB，适用于高动态复杂场景的研究应用。