{"arxiv_id":"2307.00014","incoming":{"papers":9,"sentences":9,"groups":[{"kind":"background","label":"Cites it as background","papers":5,"sentences":5,"quotes":[{"arxiv_id":"2402.05790","title":"Underwater MEMS Gyrocompassing: A Virtual Testing Ground","url":"/paper/2402.05790","section":"Introduction","sentence":"Furthermore, recent machine learning and deep learning approaches have further advanced performance in various navigation tasks [ref] .","intent_p":0.84,"contests_p":null},{"arxiv_id":"2401.15620","title":"Data-Driven Strategies for Coping with Incomplete DVL Measurements","url":"/paper/2401.15620","section":"Introduction","sentence":"As hardware capabilities advanced to handle heavy computational loads, the utilization of machine learning (ML) and deep learning (DL) techniques emerged to enhance AUV navigation [ref] .","intent_p":0.9,"contests_p":null},{"arxiv_id":"2407.21676","title":"Pedestrian Inertial Navigation: An Overview of Model and Data-Driven Approaches","url":"/paper/2407.21676","section":"Data-Driven Pedestrian Dead Reckoning","sentence":"These approaches are used in a variety of navigation tasks [ref] , including PDR [ref] , as described below.","intent_p":0.8,"contests_p":null},{"arxiv_id":"2603.08265","title":"Airborne Magnetic Anomaly Navigation with Neural-Network-Augmented Online Calibration","url":"/paper/2603.08265","section":"A Unified Framework for State Estimation and Model Learning","sentence":"NNs are typically integrated with EKFs by either performing specific tasks, like predicting INS errors during GNSS outages to correct state estimates [ref] , or by adaptively tuning the filter's parameters, such as its noise covariance matrices or the KF gain [ref] .","intent_p":0.99,"contests_p":null},{"arxiv_id":"2502.07726","title":"DeepVL: Dynamics and Inertial Measurements-based Deep Velocity Learning for Underwater Odometry","url":"/paper/2502.07726","section":"RELATED WORK","sentence":"Currently, the domain of exclusively imu-based odometry estimation has developed into a diverse field including a multitude of methods deployed across diverse robot configurations [ref] .","intent_p":0.89,"contests_p":null}]}],"unlabelled_sentences":4},"outgoing":{"papers":12,"sentences":12,"groups":[{"kind":"background","label":"Cites as background","papers":4,"sentences":4,"quotes":[{"arxiv_id":"2303.03757","title":"Deep Learning for Inertial Positioning: A Survey","url":"/paper/2303.03757","section":"Introduction","sentence":"A survey was conducted in [ref] to examine inertial positioning using recent DL methods.","intent_p":0.86,"contests_p":null},{"arxiv_id":"2302.11089","title":"Recent Advancements in Deep Learning Applications and Methods for Autonomous Navigation: A Comprehensive Review","url":"/paper/2302.11089","section":"Introduction","sentence":"In [ref] there is a discussion of end-to-end DL methods employed in autonomous navigation, including subjects other than navigation such as obstacle detection, scene perception, path planning, and control.","intent_p":0.85,"contests_p":null},{"arxiv_id":"2002.11310","title":"From Seeing to Moving: A Survey on Learning for Visual Indoor Navigation (VIN)","url":"/paper/2002.11310","section":"Introduction","sentence":"In light of DL's significant advances in the fields of image processing and computer vision, vision-based navigation surveys were conducted for different platforms and in general [ref] .","intent_p":0.83,"contests_p":null},{"arxiv_id":"2108.04097","title":"Deep Learning for Embodied Vision Navigation: A Survey","url":"/paper/2108.04097","section":"Introduction","sentence":"In light of DL's significant advances in the fields of image processing and computer vision, vision-based navigation surveys were conducted for different platforms and in general [ref] .","intent_p":0.83,"contests_p":null}]}],"unlabelled_sentences":8},"claims":[],"thresholds":{"intent_p":0.8,"supports_p":0.95,"contests_p":0.7},"method":"Citing sentences come from each paper's LaTeX source; every \\cite marks the sentence and the works it cites. Pith's classifier typed each sentence. A label is shown at intent probability 0.8 or more (0.95 for support), a contest at 0.7 or more. Measured accuracy against two blind model families is at https://pith.science/accuracy. The quoted sentences are the citing authors' own.","held_up":null,"_links":{"html":"https://pith.science/paper/2307.00014"}}