At WWDC 2019 and in the demo project body tracking data is applied to the robot model robot.usdz. I want to use a custom 3D character model. But there is no specification how to rig the character model in order to be compatible with the RealityKit implementation. The only information I found is the statement at WWDC "the model must follow the same structure of robot.usdz". And I can view the joints when I open the robot model with XCode.Since Apple does not provide a specification about the 3D character model. Does anyone know- what is required (i.e. what does RelalityKit read) and what must be the same (e.g. naming, orientation)?- a rig tool which by default provides the required set of joints?- a workflow how to set up a character model? (e.g. import robot.usdz with Mulitverse in Maya, replicate on a new model, export as fbx, convert with RealityConverter to usdz)

WWDC21 announces the support of more body poses and gestures for processor A14. Furthermore rotations are more accurate and you can track these movements from a larger distance. But what are the improvements for devices with processor A12 or A13? Do they also benefit from any improvements when using iOS 15?

WWDC21 announces the support of more body poses and gestures for processor A14. Furthermore rotations are more accurate and you can track these movements from a larger distance. But what are the improvements for devices with processor A12 or A13? Do they also benefit from any improvements when using ARKit 5 and iOS 15?

Our Motion Capture app is not working properly anymore on iOS 16.1. Existing app builds crash on iOS 16, so we are forced to deliver a build targeting iOS 16. But the iOS 16 app build has the issue that the feet of the character are always oriented vertically! I observe the same issue when running the body detection sample app from Apple by using devices with A12 and A13 chip. Is this a bug in iOS 16 or has the app code to be adapted for iOS 16?