Risk of Tesla camera-only self-driving

[mostlylong]

@rtichy

doesn’t mean that all forms of other systems are just as useful nor just as easy as others to merge into a cohesive understanding of space.

I don’t claim “just as easy” and neither does Nuro.

In fact, quite the opposite:

@mostlylong

A common counterargument is that adding sensors increases system complexity. That is true to some extent. But complexity, in this case, is an engineering problem rather than a fundamental barrier. Sensor fusion, calibration, and redundancy are hard problems, but they are solvable ones. When solved well, they yield systems that are more robust across lighting conditions and environmental variability, with multiple sensing modalities providing complementary and redundant information.

Applying foundational principles from statistics and information theory, multiple modalities should be at minimum just as good as a single modality (from a pure information content perspective), and most times better for well-thought sensor fusion.

In another thread, I argued that sensor-fusion can have an analytical processing cost:

@mostlylong

@mostlylong

Processing sensory inputs (including synchronizing the data in space and time, and also calculating correlated, interacting features) from multiple sensor types (camera + lidar) might require more analytical processing (somehow appropriately defined) relative to processing from a single sensor type (camera only).
One can imagine additional neurons and connections and specialized features (in artificial and/or biological intelligence) to process vision plus sound, versus either alone.

Maybe you pay for it one way or the other?

High res vision data (space and time) and crazy detailed and advanced feature and AI modeling.

or

Multi-sensor data that must be synchronized together and then modeled together in AI.

No free lunch?

Some posters are more amenable and open-minded to other ideas than their own, other posters, not so much.

I don’t “block” other posters, because I don’t want to exclude information, of whatever quality, from my purview.

I’m swayed by what the available data and known theory in machine learning tells us.

I’m much less persuaded by marketing ploys and anecdotes.

One in a million accident rates needed for better-than-human safety in AVs cannot be estimated from anecdotes nor inferred from marketing stunts.

Waymo is doing 4 million true autonomous miles per week, and accelerating. Everyone else, in the US at least, is basically near zero such miles.

That’t the most telling data point on what technological approach actually works today and in the near term.