Nice, I’m eager to see that 
@Wolfgange when dealing with speech recognition you cannot go cheap when it comes to a microphone. There really just is no way to get around that.
Yeah, you bring up a good point, however the dummy mycroft unit’s microphone could have a sole purpose of two-way communication between rooms. So although the dummy Mycroft units wouldn’t be able to initiate a conversation with Mycroft or use speech recognition, the person in another room could have a conversation through this unit.
Mycroft in the car is an awesome idea! I am very much interested in this, as a matter of fact Mycroft portability period. The hard part I see is how will Mycroft interface with other devices, like say all aspects of my car’s computer? I know I am still very much new to the community, but these are the things I would like to understand and figure out. If we could develop an array of interfacing devices running some sort of Mycroft API, wouldn’t that be a great start?
I am interested and would like to connect my car to mycroft or have a version that run in the car. But it needs to communicate to the main server. A lot of work . If you are interested, let us talk.
We’ve been talking about the value and challenges of working in a car environment. One advantage is that modern cars usually have a pretty good microphone system for picking our the driver’s voice and a nice set of speakers. The obvious challenge for Mycroft or any voice assistant is how to deal with internet connectivity. I’ve been thinking about “offline” options for the Speach to Text (definitely possible), but I think most of what you really want Mycroft for still requires reaching out to the internet at the Skills level. Do you agree? Or is there much value in a purely offline Mycroft that can talk to the car’s CAN Bus?
I don’t think it would be that difficult given the explosion in wireless, cheap, but capable ARM based SOC’s : http://hackaday.com/2014/10/25/an-sdk-for-the-esp8266-wifi-chip/
That is an older article on the now ubiquitous esp8266; however, a newer bluetooth 4.1/wifi module is available. These are literally 5 bucks (not in volume) and have enough on board cpu / mem to do this simple ‘proxy’ / ‘wireless voice bridge’ (?) type of application, right?
I think the design question is whether you want to require the car system to be reliant on you phone for its internet connection, or if you want to build some kind of 3G/LTE support right in to the system. For a system to be successful and not just a toy that becomes irritating, the car’s internet connection would need to be really solid.
A completely disconnected Mycroft would definitely require much more than an ESP8266. The storage and processing power for Speech To Text far exceeds that, almost certainly more than even the Pi 3.
I’ve been thinking about mycoft in the car as well, seems a logical place for voice controlled AI to be.
I think probably best to first reach out to this project http://i-carus.com/ as they’ve already got a linux car product and hardware. I’m not sure how active this project still is but I’ve been planning on purchasing the components from them and having a go at getting mycroft running, or shoe-horning in the mycoft internals when the backer devices are shipping.
To me would seem to save time and money if there is someone that already had components ready and just needs the Mycroft AI software .
I’ve heard different reports of this companies service though so I dunno but I thought it was worth mentioning in this thread.
Be great to know your thoughts also
Thanks
Automotive Grade Linux is thè reference distro:
https://www.automotivelinux.org/
They seem to need a Speech Services subteam btw 
https://wiki.automotivelinux.org/agl-distro
1 Like
Does anyone here have experience with the new Dashbot from Next Thing, Co?
I think anything has to be designed and built with 5G/LTE in mind, Concentrate on getting it into the car and the rest will come, once its in there connection will not be an issue in 2 - 3 years, and anything that has been on the drawing board that long for Mycroft will be able to be deployed.
CES 2017:-Qualcomm CEO Steve Mollenkop: 5G Brings the Invention Revolution. start a 7 mins.
I envisage mycroft as a hub, and you will have a 5G connection to home to your hardware, if that is still necessary. I mean there’s an android core so no it won’t be soon.
It can be a pi with a wireless or blutooth connection to your ph, and whatever services that is capable of that makes it useful.
You will ask Mycroft for directions and they will appear on your navigator screen or HUD, and you will ask it to make a phone call or schedule a task for your home or public or private calender. Monitor your vehicle, does not have to be a car.
Sorry another long post. ATM I just want lots more skills. oh and a handheld version.
It’s been almost a year since last comment. ‘MycroftKitt’ sounds fascinating. Is anyone working on something like this? Would anyone be interested in collaborating on such a project?
The automotive ecosystem has changed a bit since last comment, and I have some big, bad, bold ideas building on what we have here. Definitely agree one should integrate Waze and other popular car apps with this system – I think that’d a very valuable data source for the system. 3/4/5G/LTE integration sounds like it’d be vital for Mycroft in the car (and other cloud services the car uses). What if we went further, integrating Mycroft with some of these new burgeoning DIY self-driving car kits? How about custom on-board sensor and mods? What about tapping into some of these telematics solutions? What about remote controlling an entire fleet of other autonomous vehicles at once? This project has huge potential to blow even the proprietary solutions out of the friggin’ water.
Who’s down for some collab?
I would love to help. Mycroftkitt sounds like the perfect idea. Ive been thinking about something like that for awhile now. Sadly i am new to the diy world. Message me for anything i can help with!
In Croatia, our police said that they encourage the use of the police warning apps because it’s making their job easier and that is forcing drivers to slow down on the particular parts of roads which are more dangerous and cause crashes.
I had this idea years ago and was planning on attempting to make something similar using Android and Tasker. The problem is, most double din android stereos are Android 4.4 which is a dinosaur. Aside from that, they can take up to 45 seconds to initially launch.
Anyone look at the AutoPi dongle doo hickey that’s currently on the market if I’m not mistaken. Is there anyway that can be used as a start point 
🤷🏿
The AutoPI is based on the RPi Zero, which I believe isn’t recommended for PiCroft. Has anyone tried it on the Orange Pi 4G-IOT? I’m thinking that might get more connectivity
I am attempting to intergrate my mycroft and all my trucks electronics…Radio, navigation, backup cams into one harmonious unit. Right now I have the dash apart and i’m figuring out all the wiring issues. If any one wants to collaborate or has gone this route before any assistance, ideas, comments would be fantastic. I am very new to Mycroft but its a fun project with no real deadline, so I do it in my spare time. We need a place for pictures or a spot for video to see everyones projects.
2 Likes
Sounds like you’re having plenty of fun 
Definitely feel free to start a dedicated thread for your project, or were you thinking a general pics/video’s thread?