Simultaneous localization and mapping (SLAM) is critical to the implementation of autonomous driving. Most LiDAR-inertial SLAM algorithms assume a static environment, leading to unreliable localization in dynamic environments. Furthermore, accurate tracking of moving objects is of great significance for the control and planning of autonomous vehicle operation. This study proposes LIMOT, a tightly-coupled multi-object tracking and LiDAR-inertial SLAM system capable of accurately estimating the poses of both ego-vehicle and objects. First, we use 3D bounding boxes generated by an object detector to represent all movable objects and perform LiDAR odometry using inertial measurement unit (IMU) pre-integration result. Based on the historical trajectories of tracked objects in a sliding window, we perform robust object association. We propose a trajectory-based dynamic feature filtering method, which filters out features belonging to moving objects by leveraging tracking results. Factor graph-based optimization is then conducted to optimize the bias of the IMU and the poses of both the ego-vehicle and surrounding objects in a sliding window. Experiments conducted on KITTI datasets show that our method achieves better pose and tracking accuracy than our previous work DL-SLOT and other SLAM and multi-object tracking baseline methods.

翻译：同步定位与地图构建（SLAM）是实现自动驾驶的关键技术。大多数激光雷达-惯性SLAM算法假设静态环境，导致在动态环境中定位不可靠。此外，精确跟踪运动物体对自动驾驶车辆的控制与规划具有重要意义。本研究提出LIMOT，一种紧耦合的多目标跟踪与激光雷达-惯性SLAM系统，能够精确估计自车和物体的位姿。首先，我们利用目标检测器生成的三维边界框表示所有可移动物体，并基于惯性测量单元（IMU）预积分结果执行激光雷达里程计。基于滑动窗口中已跟踪物体的历史轨迹，我们进行鲁棒的物体关联。本文提出一种基于轨迹的动态特征滤波方法，通过利用跟踪结果滤除属于运动物体的特征。随后进行基于因子图的优化，在滑动窗口中优化IMU偏置及自车与周围物体的位姿。在KITTI数据集上的实验表明，我们的方法相较于先前工作DL-SLOT及其他SLAM和多目标跟踪基线方法，在位姿估计与跟踪精度上均取得更优结果。