Hacker News new | past | comments | ask | show | jobs | submit login

The real equation is closer to: Radar + LIDAR + Vision + Cost + Latency - Battery

Doing it with vision only saves on cost, latency & energy consumption.




I agree it saves on cost and energy consumption. Not sure about latency. But it's an inferior sensing system [and] it remains to be seen whether it can do the job or not, so far seems like not. Even if it can do the job (by some measure) whether it can outperform the better sensing systems which seems unlikely. I'd pay a little more for better safety, we know the cost of "human safety" as it reflects in our insurance premiums...


If fusing two data sources is necessary prior to making actuation decisions, how could adding another data source not introduce additional processing & latency?

It's not just about paying more dollars, but also range.

You're assuming that a dual system will be safer, but what if such systems are more prone to perception confusion, or other anomalies?

Even if a dual system were safer, it doesn't make sense to say that you will pay for safety absolutely. For example, you can always add an additional smoke alarm to your house for some marginal improvement in safety, but at some point most people decide they are safe enough.




Consider applying for YC's Spring batch! Applications are open till Feb 11.

Guidelines | FAQ | Lists | API | Security | Legal | Apply to YC | Contact

Search: