Understanding a Dynamic World: Dynamic Motion Estimation for Autonomous Driving using LIDAR

In a society that is heavily reliant on personal transportation, autonomous vehicles present an increasingly intriguing technology. They have the potential to save lives, promote efficiency, and enable mobility. However, before this vision becomes a reality, there are a number of challenges that must be solved. One key challenge involves problems in dynamic motion estimation, as it is critical for an autonomous vehicle to have an understanding of the dynamics in its environment for it to operate safely on the road. Accordingly, this thesis presents several algorithms for dynamic motion estimation for autonomous vehicles using LIDAR.

First, we propose a novel dynamic object tracking algorithm. The proposed method takes as input a stream of LIDAR data from a moving object collected by a multi-sensor platform. It generates an estimate of the object's trajectory over time and a point cloud model of its shape.

Second, we present a method for scene flow estimation from a stream of LIDAR data. Inspired by optical flow and scene flow from the computer vision community, our framework can estimate dynamic motion in the scene without relying on segmentation and data association while still rivaling the results of state-of-the-art object tracking methods.

Third, we leverage deep learning tools to build a feature learning framework, allowing us to train an encoding network to estimate features from a LIDAR occupancy grid. We demonstrate that using the learned feature space improves our estimate of the dynamic motion in the environment over time.

In summary, this thesis presents three methods to aid in understanding a dynamic world for autonomous vehicle applications using LIDAR. We demonstrate the performance of all our proposed methods on a collection of real-world datasets.