Abstract:Segmentation of three-dimensional (3D) point clouds is an important task for autonomous systems. However, success of segmentation algorithms depends greatly on the quality of the underlying point clouds (resolution, completeness etc.). In particular, incomplete point clouds might reduce a downstream model's performance. GRNet is proposed as a novel and recent deep learning solution to complete point clouds, but it is not capable of part segmentation. On the other hand, our proposed solution, GRJointNet, is an architecture that can perform joint completion and segmentation on point clouds as a successor of GRNet. Features extracted for the two tasks are also utilized by each other to increase the overall performance. We evaluated our proposed network on the ShapeNet-Part dataset and compared its performance to GRNet. Our results demonstrate GRJointNet can outperform GRNet on point completion. It should also be noted that GRNet is not capable of segmentation while GRJointNet is. This study1, therefore, holds a promise to enhance practicality and utility of point clouds in 3D vision for autonomous systems.
Abstract:Driving in dense traffic with human and autonomous drivers is a challenging task that requires high level planning and reasoning along with the ability to react quickly to changes in a dynamic environment. In this study, we propose a hierarchical learning approach that uses learned motion primitives as actions. Motion primitives are obtained using unsupervised skill discovery without a predetermined reward function, allowing them to be reused in different scenarios. This can reduce the total training time for applications that need to obtain multiple models with varying behavior. Simulation results demonstrate that the proposed approach yields driver models that achieve higher performance with less training compared to baseline reinforcement learning methods.