We can reduce mass shooting with AI, Robotics and Non-Lethal Defense

Robotics and AI to Respond to Mass Shootings

Mass shootings are a horrible American phenomena. We have a problem with guns crossed with an overly aggressive society. I believe the number of mass shootings *can* be reduced even if our politicians won’t act on gun control. How? By using AI, Computer Vision, and non-lethal robotic responses to help people fight back against shooters. A summary of robotic self defense of soft targets like schools against shooters 24 seconds:

There are many details. Yes, it’s complex as hell. I KNOW. HELP US.

Because it IS possible to “help people fight back.”

An MVP model for robotic self defense is as simple as a human who points at the bad actor from a remote location on their iphone/android and activates the wall mounted robots. The robots, under human control, act in unison to disorient the shooter. Yes, it still requires a human response against the shooter. But we don’t have a damn thing right now. Can we just admit that our babies, our kids, our kids’ teachers are the first responders before the first responders get there?

We can possibly defend ourselves, and AI can help us using non-lethal means to defend ourselves, to enable our kids in their schools to defend themselves, when some evil person brings in an AR15 to attack the innocents. We CAN fight back.

Starting SOMA Robotics is why I went to San Francisco for the last year. To try to get funding to save lives.

I failed.

I don’t know the game. But surely someone out there does. Please?

I’ve been busting my ass trying to get funding for Tendenci in the valley since 2011. As I’ve said before, I have a phd in f’n up. Yet damnit, this might work. Right?

I still believe that we CAN reduce the impact of mass shooters at schools and other “soft targets” using existing technology.

Watch the video. Slow it down and then if you think it has potential, the potential to help US THE PEOPLE, THE KIDS, FIGHT BACK before our heroic first responders arrive, then please HELP ME.

This isn’t about the money, it’s about the kids.

Triangulate Shooter Location with Mobile App – Possible?

Text exchange with a friend about how to defend crowds from threats like the shooter in Las Vegas.

[redacted section]




Yup, saving the world, or trying to, one bear at a time.

Triangulating on a sound with data from thousands of willing opt-in smart phones is possible. Pitch, yaw, acceleration, relative volume compared to those in proximity to normalize. Calculate position from last known good if towers go out.

Mesh grid relative to each other if no service. Share UDP 5353 and change multicast DNS into a “people finder”.

The app, when turned on, would send a cascade of data flowing in with lots of noise. The analysis is the same thing anyone who has done log analysis with an ELK stack is familiar with. Have a buffer of say 10 seconds backwards until triggered.

With a few datasets from simulations (like having 30 people in a room and see if the app can figure out who blew the dog whistle.

Sensor based smart phone triangulation is one way we could defend ourselves in an attack on any soft target.

Note: the concept is somewhat related to what we are building at somarobotics.com. However I’m putting it out there because I’d love to see someone build a system to automatically respond and help.