Revision history [back]

You can definitely find more about how that's done using Autoware's repository and documentations (including publications). One easy example is Lidar and Camera data fusion: Essentially Lidar detects the objects and knows where it is placed at, on the other hand Camera detects what is the object, then the combo of two gives you "what's where". Lidars IMUs and GPS can be fused to get a better localization and/or resets ndt_matching if localizer is lost.

https://github.com/CPFL/Autoware-Manuals/blob/master/en/Autoware_QuickStart_v1.1.pdf