dhanson865
Well-Known Member
Thanks. I've listened to parts of it, didn't get through the whole thing. I didn't get the same impression you did, but maybe I just didn't listen to enough of it.
From what I understood and would expect: A properly trained algorithm/map database would need several independent entries. Not just 1 person driving over the road and the database to be updated automatically. I could be wrong.
I never made a claim about independence of the entries. He didn't specify if a single driver's data could influence behavior for the fleet.
It is possible that the system will use a single source of human input since that data isn't the primary data source for the autopilot.
If the camera, radar, sonar says everything is good then the system won't reference the human input.
Prior or subsequent trips will lay new track data and could override or confirm the track with human input.
The key concept for the wording I chose was that it has track data from the fleet not just your car. So I said "any car" to give the concept that it didn't have to be just your car. I even threw in the discalimer of "(data as a whole not single cases necessarily)" and somehow you ignored that even though you quoted it.
Last edited: