Dynamic to Static Lidar Scan Reconstruction Using Adversarially Trained Auto Encoder

Abstract

Accurate reconstruction of static environments from LiDAR scans of scenes containing dynamic objects, which we refer to as Dynamic to Static Translation (DST), is an important area of research in Autonomous Navigation. This problem has been recently explored for visual SLAM, but to the best of our knowledge no work has been attempted to address DST for LiDAR scans. The problem is of critical importance due to wide-spread adoption of LiDAR in Autonomous Vehicles. We show that state-of the art methods developed for the visual domain when adapted for LiDAR scans perform poorly. We develop DSLR, a deep generative model which learns a mapping between dynamic scan to its static counterpart through an adversarially trained autoencoder. Our model yields the first solution for DST on LiDAR that generates static scans without using explicit segmentation labels. DSLR cannot always be applied to real world data due to lack of paired dynamic-static scans. Using Unsupervised Domain Adaptation, we propose DSLR-UDA for transfer to real world data and experimentally show that this performs well in real world settings. Additionally, if segmentation information is available, we extend DSLR to DSLR-Seg to further improve the reconstruction quality. DSLR gives the state of the art performance on simulated and real-world datasets and also shows at least 4× improvement. We show that DSLR, unlike the existing baselines, is a practically viable model with its reconstruction quality within the tolerable limits for tasks pertaining to autonomous navigation like SLAM in dynamic environments.

Parallel Radars: From Digital Twins to Digital Intelligence for Smart Radar Systems

“…The physical environment in artificial scenarios includes common buildings, driving cars, and different weather conditions, while the social environment focuses on human behaviors and knowledge. Due to the involvement of social space, Descriptive Radars are able to generate massive more realistic synthetic data compared with the current digital twins' radars in CPS [16][17][18][19][20][21][22][23][24][25].…”

“…With the rapid development of artificial intelligence and computer science, digital twins in cyber-physical systems (CPS) [13][14][15], which are regarded as the key to the next industrial revolution, are being used to construct digital radars in cyberspace to achieve intelligence. Radar models in CPS [16][17][18][19][20][21][22][23][24][25] have already been extensively researched and demonstrated to be effective in solving many problems, including generating virtual data for various downstream tasks [26][27][28][29][30][31][32][33][34] and closed-loop testing.…”