FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W4386076483> ?p ?o ?g. }

• W4386076483 abstract "Rigorously testing autonomy systems is essential for making safe self-driving vehicles (SDV) a reality. It requires one to generate safety critical scenarios beyond what can be collected safely in the world, as many scenarios happen rarely on our roads. To accurately evaluate performance, we need to test the SDV on these scenarios in closed-loop, where the SDV and other actors interact with each other at each timestep. Previously recorded driving logs provide a rich resource to build these new scenarios from, but for closed loop evaluation, we need to modify the sensor data based on the new scene configuration and the SDV's decisions, as actors might be added or removed and the trajectories of existing actors and the SDV will differ from the original log. In this paper, we present UniSim, a neural sensor simulator that takes a single recorded log captured by a sensor-equipped vehicle and converts it into a realistic closed-loop multi-sensor simulation. UniSim builds neural feature grids to reconstruct both the static background and dynamic actors in the scene, and composites them together to simulate LiDAR and camera data at new viewpoints, with actors added or removed and at new placements. To better handle extrapolated views, we incorporate learnable priors for dynamic objects, and leverage a convolutional network to complete unseen regions. Our experiments show UniSim can simulate realistic sensor data with small domain gap on downstream tasks. With UniSim, we demonstrate, for the first time, closed-loop evaluation of an autonomy system on safety-critical scenarios as if it were in the real world." @default.
• W4386076483 created "2023-08-23" @default.
• W4386076483 creator A5007577768 @default.
• W4386076483 creator A5010890057 @default.
• W4386076483 creator A5026746739 @default.
• W4386076483 creator A5037547726 @default.
• W4386076483 creator A5058557954 @default.
• W4386076483 creator A5061402622 @default.
• W4386076483 creator A5078250869 @default.
• W4386076483 date "2023-06-01" @default.
• W4386076483 modified "2023-10-06" @default.
• W4386076483 title "UniSim: A Neural Closed-Loop Sensor Simulator" @default.
• W4386076483 cites W1510994837 @default.
• W4386076483 cites W156975732 @default.
• W4386076483 cites W1808974695 @default.
• W4386076483 cites W2006466397 @default.
• W4386076483 cites W2014824949 @default.
• W4386076483 cites W2034825286 @default.
• W4386076483 cites W2050513283 @default.
• W4386076483 cites W2074242340 @default.
• W4386076483 cites W2158782408 @default.
• W4386076483 cites W2167340365 @default.
• W4386076483 cites W2891656793 @default.
• W4386076483 cites W2912798476 @default.
• W4386076483 cites W2936459520 @default.
• W4386076483 cites W2962785568 @default.
• W4386076483 cites W2963800363 @default.
• W4386076483 cites W2963926543 @default.
• W4386076483 cites W2967177252 @default.
• W4386076483 cites W2968042644 @default.
• W4386076483 cites W2968557240 @default.
• W4386076483 cites W2999862950 @default.
• W4386076483 cites W3004162282 @default.
• W4386076483 cites W3034264193 @default.
• W4386076483 cites W3034716600 @default.
• W4386076483 cites W3035507572 @default.
• W4386076483 cites W3134621679 @default.
• W4386076483 cites W3167914619 @default.
• W4386076483 cites W3173629300 @default.
• W4386076483 cites W3175727500 @default.
• W4386076483 cites W3176179930 @default.
• W4386076483 cites W3176762345 @default.
• W4386076483 cites W3179022832 @default.
• W4386076483 cites W3179442871 @default.
• W4386076483 cites W3180799285 @default.
• W4386076483 cites W3183092879 @default.
• W4386076483 cites W3183784042 @default.
• W4386076483 cites W3184957317 @default.
• W4386076483 cites W3195620846 @default.
• W4386076483 cites W3203570626 @default.
• W4386076483 cites W3203806429 @default.
• W4386076483 cites W3209102426 @default.
• W4386076483 cites W3214824629 @default.
• W4386076483 cites W3215048956 @default.
• W4386076483 cites W3215589927 @default.
• W4386076483 cites W3215769467 @default.
• W4386076483 cites W3216473017 @default.
• W4386076483 cites W4200150166 @default.
• W4386076483 cites W4200313684 @default.
• W4386076483 cites W4221151978 @default.
• W4386076483 cites W4288242633 @default.
• W4386076483 cites W4301141993 @default.
• W4386076483 cites W4312280420 @default.
• W4386076483 cites W4312433568 @default.
• W4386076483 cites W4312453532 @default.
• W4386076483 cites W4312546206 @default.
• W4386076483 cites W4312679369 @default.
• W4386076483 cites W4313017495 @default.
• W4386076483 cites W4383101317 @default.
• W4386076483 doi "https://doi.org/10.1109/cvpr52729.2023.00140" @default.
• W4386076483 hasPublicationYear "2023" @default.
• W4386076483 type Work @default.
• W4386076483 citedByCount "1" @default.
• W4386076483 crossrefType "proceedings-article" @default.
• W4386076483 hasAuthorship W4386076483A5007577768 @default.
• W4386076483 hasAuthorship W4386076483A5010890057 @default.
• W4386076483 hasAuthorship W4386076483A5026746739 @default.
• W4386076483 hasAuthorship W4386076483A5037547726 @default.
• W4386076483 hasAuthorship W4386076483A5058557954 @default.
• W4386076483 hasAuthorship W4386076483A5061402622 @default.
• W4386076483 hasAuthorship W4386076483A5078250869 @default.
• W4386076483 hasConcept C127413603 @default.
• W4386076483 hasConcept C133731056 @default.
• W4386076483 hasConcept C142362112 @default.
• W4386076483 hasConcept C153083717 @default.
• W4386076483 hasConcept C153349607 @default.
• W4386076483 hasConcept C154945302 @default.
• W4386076483 hasConcept C2776035091 @default.
• W4386076483 hasConcept C3019251811 @default.
• W4386076483 hasConcept C41008148 @default.
• W4386076483 hasConcept C44154836 @default.
• W4386076483 hasConcept C79403827 @default.
• W4386076483 hasConcept C81363708 @default.
• W4386076483 hasConceptScore W4386076483C127413603 @default.
• W4386076483 hasConceptScore W4386076483C133731056 @default.
• W4386076483 hasConceptScore W4386076483C142362112 @default.
• W4386076483 hasConceptScore W4386076483C153083717 @default.
• W4386076483 hasConceptScore W4386076483C153349607 @default.
• W4386076483 hasConceptScore W4386076483C154945302 @default.
• W4386076483 hasConceptScore W4386076483C2776035091 @default.

• next