English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

We tackle the problem of producing realistic simulations of LiDAR pointclouds, the sensor of preference for most self-driving vehicles. We argue that,by leveraging real data, we can simulate the complex world more realisticallycompared to employing virtual worlds built from CAD/procedural models. Towardsthis goal, we first build a large catalog of 3D static maps and 3D dynamicobjects by driving around several cities with our self-driving fleet. We canthen generate scenarios by selecting a scene from our catalog and "virtually"placing the self-driving vehicle (SDV) and a set of dynamic objects from thecatalog in plausible locations in the scene. To produce realistic simulations,we develop a novel simulator that captures both the power of physics-based andlearning-based simulation. We first utilize ray casting over the 3D scene andthen use a deep neural network to produce deviations from the physics-basedsimulation, producing realistic LiDAR point clouds. We showcase LiDARsim'susefulness for perception algorithms-testing on long-tail events and end-to-endclosed-loop evaluation on safety-critical scenarios.

LiDARsim: Realistic LiDAR Simulation by Leveraging the Real World