Paper Reading AI Learner

SR-LIO: LiDAR-Inertial Odometry with Sweep Reconstruction

2022-10-19 09:44:37
Zikang Yuan, Fengtian Lang, Xin Yang

Abstract

This paper proposes a novel LiDAR-inertial odometry (LIO), named SR-LIO, based on an improved bundle adjustment (BA) framework. The core of our SR-LIO is a novel sweep reconstruction method, which segments and reconstructs raw input sweeps from spinning LiDAR to obtain reconstructed sweeps with higher frequency. Such method can effectively reduce the time interval for each IMU pre-integration, reducing the IMU pre-integration error and enabling the usage of BA based LIO optimization. In order to make all the states during the period of a reconstructed sweep can be equally optimized, we further propose multi-segment joint LIO optimization, which allows the state of each sweep segment to be constrained from both LiDAR and IMU. Experimental results on three public datasets demonstrate that our SR-LIO outperforms all existing state-of-the-art methods on accuracy, and reducing the IMU pre-integration error via the proposed sweep reconstruction is very importance for the success of a BA based LIO framework. The source code of SR-LIO is publicly available for the development of the community.

Abstract (translated)

URL

https://arxiv.org/abs/2210.10424

PDF

https://arxiv.org/pdf/2210.10424.pdf


Tags
3D Action Action_Localization Action_Recognition Activity Adversarial Agent Attention Autonomous Bert Boundary_Detection Caption Chat Classification CNN Compressive_Sensing Contour Contrastive_Learning Deep_Learning Denoising Detection Dialog Diffusion Drone Dynamic_Memory_Network Edge_Detection Embedding Embodied Emotion Enhancement Face Face_Detection Face_Recognition Facial_Landmark Few-Shot Gait_Recognition GAN Gaze_Estimation Gesture Gradient_Descent Handwriting Human_Parsing Image_Caption Image_Classification Image_Compression Image_Enhancement Image_Generation Image_Matting Image_Retrieval Inference Inpainting Intelligent_Chip Knowledge Knowledge_Graph Language_Model Matching Medical Memory_Networks Multi_Modal Multi_Task NAS NMT Object_Detection Object_Tracking OCR Ontology Optical_Character Optical_Flow Optimization Person_Re-identification Point_Cloud Portrait_Generation Pose Pose_Estimation Prediction QA Quantitative Quantitative_Finance Quantization Re-identification Recognition Recommendation Reconstruction Regularization Reinforcement_Learning Relation Relation_Extraction Represenation Represenation_Learning Restoration Review RNN Salient Scene_Classification Scene_Generation Scene_Parsing Scene_Text Segmentation Self-Supervised Semantic_Instance_Segmentation Semantic_Segmentation Semi_Global Semi_Supervised Sence_graph Sentiment Sentiment_Classification Sketch SLAM Sparse Speech Speech_Recognition Style_Transfer Summarization Super_Resolution Surveillance Survey Text_Classification Text_Generation Tracking Transfer_Learning Transformer Unsupervised Video_Caption Video_Classification Video_Indexing Video_Prediction Video_Retrieval Visual_Relation VQA Weakly_Supervised Zero-Shot