首页|'Smartphone-Based Inertial Odometry' in Patent Application Approval Process (USP TO 20240271938)
'Smartphone-Based Inertial Odometry' in Patent Application Approval Process (USP TO 20240271938)
扫码查看
点击上方二维码区域，可以放大扫码查看
原文链接
NETL
NSTL
The following quote was obtained by the news editors from the background informa tion supplied bythe inventors: ““The present invention relates to inertial odometry.“Smartphone-based odometry systems for pedestrian tracking in indoor, GPS-denied environments havereceived considerable attention in recent years. These system s may help a person reach a gate in an airport[1] or a shop in a mall [2], navigate a museum [3], or find one’s car in a parking lot [4]. Among the variousapproaches considered in the literature , technology based on inertial sensors have a number of practicaladvantages. Fo r example, inertial-based odometry does not require the installation of infrastr ucturesuch as Bluetooth low energy (BLE) beacons [5] . In addition, no prior calibration (“fingerprinting”) isnecessary, unlike for systems based on Wi-Fi [6] or BLE beacons. Compared with systems that use a camerato determine the user’s location (visua l-based odometry [7]), and that, thus, req uire good un-occludedvisibility of the scene, inertial systems are able to trac k the user even when they keep the phone in theirpocket. The downside of this m odality is that the user’s location is tracked by integrating inertial data, which leads to possibly large errors due to accumulated drift. A number of strategi es to deal with drift havebeen proposed, including zero-velocity updates [8], spatial constraints (e.g., Bayes filtering using a mapof the environment [9]), and machine learnin g [10]. Multiple well-calibrated inertial datasets (containingdata from accelerometer and gyros) collected from regular s martphones carried by human walkers havebeen made available in recent years [10-12].
AlgorithmsCyborgsEmerging Technologi esMachine LearningUniversity of California
NETL
NSTL
