Hotz is quoted as saying in the article, "there are only three real competitors: Waymo, Tesla and us."
That's total bullshit. There are so many companies seriously working on autonomous vehicles, such as GM Cruise, Auroa Innovation, Drive.ai, Zoox, Nuro.ai, nuTonomy, Varden Labs, AImotive, Ford, and Nvidia
Edit, because George is on here: George, I want to like you, because I think your tech is really good (the street image segmentation from RGB images is seriously impressive- https://commacoloring.herokuapp.com/) and I think your business model of offering cheap devices and free services to crowd-source data, along with the comma points to incentivize users could give you a big competitive advantage. But the hyperbole makes it difficult to take you seriously.
This is the guy who was supposedly just a few weeks away from shipping a bolt-on smart cruise control module, then immediately canceled the entire thing when the NHTSA asked him some questions about its safety. He seems pretty sharp when it comes to technology, but I'm not sure if he's prepared to make actual products sold to regular people.
The questions he was asked were pretty darn reasonable, IMO. If he's unwilling or unable to answer those questions I have no problem at all with him being prohibited from selling a product that his customers would literally be trusting with their lives.
If he knew about it then why would he have even started the project? It's obvious that regulators would be involved in a project like this. I don't see how he didn't anticipate this from the start.
You are literally agreeing with everyone accusing him of being ignorant though. You think you're defending him, but this is what everyone is saying. The fact that dealing with NHTSA or what that entails is "hindsight" to him is what makes him almost mind-bogglingly ignorant here. I would think a precocious 12-year-old would have been able to predict that, or at least would have the smarts to, say, at least ask somebody ahead of time (like a lawyer) what legal hurdles his business (that has life-and-death consequences, and that he sought funding for) might have to deal with in the future. His own explanation for what happened makes him sound way worse than if he hadn't explained it at all.
Cruise sold for >$1B. If he thought his company was better off than that, it is supremely irrational to not put up with the pain of the NHTSA. Hell, just hire a lawyer to do everything and you don't even need to think about it.
No, from my guess, Hotz copped out when he realized that his prototype, while fun, was no where near production ready and would be completely illegal to ship to any customers.
This is my personal opinion, so take it with a grain of salt.
Hotz never seemed like the guy who would do things similar to what Cruise did. Vogt had already sold two startups prior to Cruise, and he was well versed in the tactics of the startup world. Have great articles put out, polished PR touches, the whole works.
OTOH, Hotz had this 'Hacker' air to whatever he does. From the iPhone, to PlayStation, to even hacking the cars he was building the tech with, he had a very different attitude compared to the let's-be-poised-for-a-buyout vibe that many startups give. Startups like Cruise are scared of breaking rules, worrying about how it might bite them later in the day.
If you ask me, Cruise was never going to make it on its own. The major car companies have decades of supply chain process management and huge amounts of capital behind them. Cruise couldn't never do what it said it would do, and I would imagine, a buy out was always on the founders minds.
Comma.ai is a different beast. They aren't really worried about rules. That's terrible attitude for a 'startup', I agree. People here have valid arguments about thinking about the NHTSA before hand, but I think they just dared to go ahead without giving a crap. It backfired, but I wouldn't attribute his decision to failure in building a working product.
There is a TWIST episode with this guy on it, and he comes of as a massively arrogant prick. The dude who created the first iPhone jailbreak in his teens and got famous at it.
He did a lot more than just jailbreak an old iPhone. The dude's good, who cares if he's arrogant? There's hundreds of big corporations manipulating media for financial gains.
Are you gonna hate this guy just because he has a face and a personal reputation?
Or are you going to watch with bemused interest as he successfully scales the obstacles and actually puts some nice products out there.
My (not GP) issue with him comes from all his whining over the NHTSA stuff. You can't talk about how easy the problem is and how much better you are, and then fold when safety regulators show up. That to me says that he may be incredible at building things, but doesn't know how to take it the last mile. Sure, you can argue against the regulation, but I for one think that self driving cars should have strict safety regulation. And from what I read they weren't asking anything crazy of him that they wouldn't of anyone else.
he released the hardware plans, specs, and software as opensource. You can go build it, today. And if you have a supported car (currently certain honda civics, and accura ILX's.. soon honda crv, toyota prius, and chevy bolt/volt) you can actually use it, today. There are videos on youtube of people doing exactly that.
Changing your business model, is IMO.. the opposite of folding. it's adapting.
He threw a tantrum on twitter to save face. If you want to admire him for his hacking efforts that's one thing (and honestly I don't even agree with that for his work on self-driving cars), but he hasn't done much to build a business yet.
Udacity has their own self-driving vehicle. They built it for their Self-Driving Vehicle Car Engineer Nanodegree program; I just started term 3 yesterday, and apparently they're going ahead with the plan for student to run code on it.
Apparently, they have a test track, and will have a safety driver on-board. For that part of the term (dubbed "Integration"), we'll be broken into teams of 10-20 students, and (somehow) have to coordinate on building the software pieces to run on the vehicle. This will all be done using a custom simulator designed to replicate the test track (similar to what has already been used). Once something is working, the group will then merge the pieces (nodes and modules for ROS and something called AutoWare) all together in a shared github repo. That'll be shipped over to Udacity for testing on "track days", and results sent back to the team for analysis.
I'm not sure how well this whole thing is going to work; it's very much an experiment that I believe is unique for a MOOC and hasn't been tried before (develop software as a group project of international students, to drive a real self-driving vehicle on a test track in Mountain View, CA - yep, that seems reasonable).
I guess we'll see when we get there. The vehicle is named "Carla", and (overall) it is open-sourced. Here are some links to learn more about it:
The vehicle itself is apparently some standard vehicle converted by a third-party company (for the life of me, I can't recall the make or model of the vehicle, nor the company that did the conversion!); if you wanted to DIY this yourself at full scale, you'd basically want a vehicle that uses a mostly drive-by-wire control system for the brakes, accelerator, and steering. If that isn't available, then something that uses electro-hydraulic power braking and steering (or electric power-steering) would be the next best thing.
I'd shy away from trying to do this with a standard vehicle; building the actuators you would need to control everything is not a trivial thing to do (and especially to do so safely and reliably).
Honestly, if you really wanted to do this, and you didn't want to kill yourself, others, or damage property (as much?) - start out smaller with an RC car or similar. There are plenty of examples on how to do this on the internet, but my favorite go-to example is this one:
That one occupies a "soft spot" in me because David Singleton was one of the original students in the Stanford-sponsored ML Class of 2011, taught by Andrew Ng. I was a part of that class; it taught us enough to build such a vehicle, and David was inspired to do so and follow thru with it. What used to cost hundreds-of-thousands of dollars (if not millions) back in the 1980s:
Final note: I don't have any association with any of this other than being a student in the Udacity course and interested in learning about this technology.
It's a Lincoln MKZ. A number of partners helped us with the conversion, including AutonomouStuff and NVidia.
And yes - we're running student code on the car, around a test track, and we'll send you the results (I think a video feed as well). It's your final project in the Self-Driving Car Nanodegree program.
I can't wait to watch the first time a student's code drives it around the track.
He seems to be quite above average, the issue is the ratio hubris / math skillz still seems improperly balanced.
If my sunday psychology profile is correct, he seems to be passionated and fast to hack around and displeased by big corporations business model + slowness + suboptimality. Thus trying to dig diagonally on his own without the enterprise cruft. So far so good, the issue is that it seems he's lying about his abilities. He managed to do 20% and spins it as 70% claiming he'll be at 100% before everybody else. Without independant testing and legislation of course.
Cruise had lane following and smart cruise control, which everybody in the industry has and can be bought as an option on many high-end cars right now. They hyped this heavily and GM bought it.
That was surprising, because GM had a good self-driving effort with CMU, and had progressed to driving in Washington DC traffic autonomously.[1] That was way ahead of Cruise, and working in 2013. Then, somehow, GM totally blew it and lost that project, with the people going elsewhere.
Every Toyota comes equipped with lane following and smart cruise control. They call it Toyota Safety Sense, and even the lowest priced, $18k Corolla has it.
That's great for software that runs on your computer, it's not so great for software that runs on a car and can kill people. Regulatory bodies exist for a reason, onerous though they may be.
Edit: I'm actually curious now that I think about it. Are there any good examples of hacker projects (or specifically projects that aren't intended to make money or pay people's salaries) that had to deal with any sort of regulatory hurdles?
This is a depressing comment. I'm assuming the parent comment is talking about GNU, Linux, the variety of userspace software from Unix times... not node.js template systems.
Linux didn't become particularly useful or relevant until folks spent a whole lot of very businessy time and money on it. That's why RedHat even exists (not that they were alone, but they survived).
GNU wasn't hackers in the meaning of 2010s hackers. It took smart individuals and years to come up with something tangibles. Same for Linux.
I cannot compare anything in the casual software world, no matter how complex it is, to driving a car in streets. It's bridging physics and AI. Maybe hotz has a point and other SDV module vendors are as fake but that's irrelevant.
I doubt Geohotz didn't do his homework before he made this conclusion. He went to CMU, Google and Facebook and had worked with the smartest professors/scientists/engineers in the field of AI before he founded Comma.ai. He's pretty much single-handed built a level 3 drive assist prototype within a year where other companies spent billions and many years R&D but not even came close to what he was originally intended to release.[1]
So when George said, "there are only three real competitors: Waymo, Tesla and us." What he really says is that Comma.ai's technology is on par with Waymo and Tesla's. The rest of the companies are either subpar or have no existing product to demo, likely both.
He also famously said "shippability" is the biggest differentiator between Comma One and the rest but decided not to fight the uphill legal battle being that he's taking the Android approach to grab the market share.
The chffr app (video / nav data) + panda dongle (sensor data) is a simple way to let anybody participate in data collection, and for comma.ai to build enterprise value by accruing and organizing a gigantic data set that's critical to them or any third party executing the ML at core of self driving.
Now pair this with a tweet they posted in June:
"Just realized something. You are really going to be happy you have comma points. Get in early... http://getchffr.com/ #ICO"(1)
I think that's an incredibly compelling / fascinating ACTUAL use case for an ICO vs the current litany of pyramiding and outright scams we're seeing.
Take their chffr app + panda dongle and give people a financial INCENTIVE to accrue "points" by running the two data harvesting mechanisms and suddenly I am seeing comma's strategy in a new light.
The real winner in the race to mandate OBD-II monitoring is the auto insurance industry.
Sure, you could install Hotz's dongle, give Hotz your data, earn "comma points", feel like you are helping to train self driving cars, and trade these comma points for - what exactly? a comma plushie? - while Hotz turns around and sells your data to insurance companies.
Or you could get a free OBD dongle directly from your current insurance company [1] and watch your rates go up/down depending on how safe of a driver you are.
Ultimately, Comma.ai needs to find an automotive partner. It will be nearly impossible for the company to beat Google, Uber, and (presumably) Apple, who all have strong partnerships with auto OEMs, in quality or quantity of driving data without direct integration and extensive testing on vehicles designed for autonomous driving. Not to mention Tesla, which is an OEM itself, and can design in data collection/processing for self driving vehicles from the ground up.
Not a comma plushie. He mentioned ICO, so cryptocurrency. Which with something of value like this behind it the comma "points" (tokens?) could be worth quite a lot if you're an early adopter.
ICO as a way to convert "Internet Points" into something of material value and reward users directly for contributions is incredibly fascinating to me.
It's not "internet points", it's simply a way to more easily measure how much data you've contributed to comma's database. Fundamentally, that data is only valuable to insurance companies, which are already willing to pay you ~$160 (in lower insurance rates) for a year's worth of driving data.
In theory Hotz could (and should) just pay you directly in $USD for your driving data, arbitraging a bit off the top before selling it to insurance companies.
But the genius of him "paying" you in cryptocurrency is that it will get you to give it away for free "points"! And to pay him for the hardware to do so! Because you think that a market might develop around these "points" where they will get bought up by a bigger fool, pumping up their value way beyond their fundamental value to the end consumers of this data - insurance companies.
These "points" have no other value or use, as they would not otherwise function as currency (store of value, medium of exchange, unit of account) unless Hotz decoupled point generation from car data generation and just started minting an arbitrary virtual currency.
There's absolutely no point in having this be a cryptocurrency, unless there is some way that all the driving data will be posted to the blockchain and verified not to be fake by the blockchain. And blockchains definitely don't have the storage or computation to do any of that, plus who wants their driving data to be public?
Otherwise, it's just sending data to Comma in exchange for points. If you have one master account minting tokens (throughout the life of the currency), it's not really decentralized. They could have a SQL database with the same decentralization and security profile.
My guess is that the only use of blockchains here is to jump on the current ICO hype.
I saw a new player in self-driving yesterday - a blue Peterbilt truck equipped with many cameras and some of the puck-sized Velodyne laser scanners. Nevada license AU 0030. They were driving on US 101 southbound from Menlo Park to Mountain View, where they exited the freeway and got back on, northbound. They were bobtailing; no trailer.
In that location, I'd first though it was one of Google's vehicles But why the Nevada plate? Turns out this is Embark.[1] They even show their AU 0030 license plate in the video.
Embark has been testing in Nevada, where the regulations are looser and there's less traffic. Their demo video is on a a deserted, straight two-lane road, closed for the occasion. Good place to debug.
Embark isn't on the list of CA DMV autonomous vehicle test companies. Also, CA won't allow autonomous vehicle testing of vehicles over 10,000 pounds, figuring that if something goes wrong, it's better to have car accidents than heavy truck accidents.
When Otto did that "autonomous delivery" of Budweiser with a semi, their vehicle was surrounded by chase cars. It was a much more controlled environment than the video indicates. There's too much "fake it until you make it" in this business. Waymo and Volvo are building systems that can handle unexpected trouble. Some of the others, not so much.
Hi John, I'm Alex Rodrigues, CEO at Embark. Thanks for your interest. Our testing is legal and we are in close communication with the DMV to ensure we stay that way. In California we restrict our system to Level 2 (like Tesla autopilot), in order to comply with regulations.
Watch Chris Urmson's self-driving car talk at SXSW 2016.[1] Especially the part where the Google car encounters someone in a powered wheelchair chasing a duck with a broom. Google can handle that.
You know you can link to a specific time in a YouTube video right? Pretty hard to find that 20 second section in a 1 hour video ;-). It is a good drawand worth watching that part first, in my opinion
he's answering in the comments, he says typical OBD interfaces are slow and fragile, which I surely believe. Is it me or is his ego made of titanium ? the reporter quotes "we're 3, waymo, tesla and us" .. yet he's building a cuter, faster obdII bridge I don't get it.
Those are the three players with actual networks of deployed self driving cars today. Granted, we are in third with 73 cars (and 1000's on chffr), but well ahead of every other startup. Waymo has around 200, we expect to pass them by the end of the year.
What about GM/Cruise's existing fleet of 50 with an additional 100+ on the way? [1] All equipped with LIDAR which to my knowledge you and Tesla don't have, but will need for level 5. I know Uber ATG also has a sizable fleet as well.
I have a lot of respect for your technical chops and the iPhone/PlayStation hacking you did back in the day, but the lofty claims here are hard to back up. At least Tesla has high margin electric car sales to keep them alive while they catch up to their claims.
It's easy to fool the lay public and tech journalists who don't have any technical backgrounds, but there is a world of a difference between doing fundamental AI research and development vs. patching together off the shelf commodity hardware and wiring it all up with some python.
That said, I wish you all the luck, I think a16z is betting on an acquisition like GM did with Cruise when they didn't really have anything that advanced either.
Is your plan to release pieces of a self driving kit gradually and crowdsource through early adopter kind of customers(or collaborator in a way) ?
I'm sorry but the hardest parts are still missing and reading you're competing with actual companies with serious power (brain and money) it's more than curious to stay polite.
ps: also waymon fleet might be 200, but if they inherited Google past years of data they have tons of terrain and sensors data. I mean wat.
> Waymo has around 200, we expect to pass them by the end of the year.
Do you have any idea how ridiculous you sound? Waymo is a serious engineering effort with a lot of talented people working to do it right. There's a lot more to it than just how much data you throw at your NN.[0] Not to mention other companies comply with the law and report all their accidents.[1] Last year, you canceled your product[2] rather than answer a very short and simple safety questionnaire[3]. (Seriously, I've seen SaaS security compliance questionnaires with five times as many questions on them; that letter from the NHTSA was nothing!)
If you're still driving your vehicles around the streets of the SF Bay Area without any permits you are putting a lot of people in danger, including me. Pardon me if I think you're not only full of it, but irresponsible as well.
You can find similar products that work over bluetooth for under $10 on Amazon. I use an old smartphone on a mount to show all of the same information using a third-party app - no need for an $88 proprietary dongle.
There doesn't seem to be anything new about this product other than marketing and a high price tag. I'd love for that to not be the case, however. Maybe I'm missing some features of it.
It supports 3x CAN, 2x LIN, and 1x GMLAN. It also charges a phone. On the computer side, it has both USB and Wi-Fi.
It uses an STM32F413 for low level stuff and an ESP8266 for Wi-Fi. They are connected over high speed SPI, so the panda is actually capable of dumping the full contents of the busses over Wi-Fi, unlike every other dongle on amazon. ELM327 is weak, panda is strong.
Interesting. Seems to be more of an enthusiast data-focused product rather than something aimed towards traditional car-folk then. Might be interesting to play around with even if you don't want to contribute the data back to comma.ai
None of the < $100 ones can dump all the data, they don't have the bandwidth. Or be reliable enough to send a packet at 100hz for hours without dropping any. Trust me, I wouldn't be building hardware if I didn't have to.
ODB2 Bluetooth readers for Smartphones can be had for $10 [1]. I guess the hard part is writing the software that logs all the data. Currently most Android apps simply display the data and don't log it. The logging/software aspect of this is certainly where the value is added.
Not sure if you're interested in such things, but I've written a Python data acquisition framework (and a shitty GUI for my RaspPi) that works with those cheapo $10 dongles that I'll be releasing under the MIT license as soon as I can be bothered.
Main reason I haven't released it yet is that the connection management, while quite resilient, is so hackish that I am bit embarrassed by it.
I've been using Torque[1] for about three years now. It's got a pretty nice UI to show just about anything your car outputs via OBD-II, and lots of things that can be derived from that, as well as integrating GPS and accelerometer data. You can log the data to your phone, as well has have it uploaded to the cloud.
The only time I've really used that data was the time some jerk stopped me, cursing at me for driving like a maniac and endangering his children (who he'd been allowing to play in the street). With the logged data, I was able to show that from the time I turned onto his street, I had been going no faster than 10mph below the limit.
The OBD-II error-reading software is very useful. It showed me that the Hyundai mechanics were completely incompetent. After holding my car in the shop for a week, they finally concluded that the problem is exactly what these diagnostics told me they were (plus 10 minutes of googling).
Legal compliance is not equivalent to courteous driving. The other guy may or may not have been a jerk, but there are also plenty of plausible scenarios in which you were also the jerk, even though fully compliant. e.g. rapid acceleration, scary engine rev noise, aiming the vehicle towards the kids as they were moving off the street. Not to say you did any of those things, but I just wanted to point out that being within the law and not-being-a-jerk are somewhat orthogonal .
Excited about this. I've been looking for something like this for a while. Tried a couple of different types of OBD-II adapters from Ebay, but trying to get data from them over bluetooth or wifi was just a pain. Panda with a direct interface to my laptop will enable me to get all the information I've been trying to get from the OBD-II port of my car, specifically steering angles, acceleration and braking. Using them together with feeds from a couple of cameras, and some interesting applications can be hacked together.
Look into PLX Devices Kiwi 3 - probably one of the best out there, if not the best. I tried the el-cheapo interfaces, and it was hit or miss with my vehicles.
So I said "f-it" and dropped the coin for the original wired Kiwi, and that worked perfectly.
When they announced the Kiwi 3 kickstarter, I jumped on that with funding, and it works great - but with Bluetooth; it's a quality device. You get what you pay for.
I was able to use the "apps" to get obd2 data's. What I wanted to do is get acceleration, steering and breaking data and along with feeds from two cameras try to train deep learning models. Getting that working over Bluetooth or wifi was a pain due to poor documentation.
Cool - but since Torque can present that data for a whole range of ODB2 dongles, it must be achievable? Maybe reach out to those guys or reverse engineer their app?
So it's an ODB II dongle that made from what looks like parts from Sparkfun and 3d printed case (Although, that's bit of wild speculation on my part), sold at apparently 8x the price of competitors. Sure the ODB exports out some common info, but isn't most of it encrypted and vendor specific? Also, calling this and a camera "a self driving car kit" is an overstatement even for Silly-Con Valley.
As others have pointed out there are a TON of OBDII loggers on the market with price points down to <$10. So maybe they make it slightly more universal by interpreting more codes (?) but that seems to be mostly on the software side, this is really still a device manufactured for probably $5.
It seems the real value for comma.ai is just collecting a huge amount of driver data and then selling it to Autonomous car makers or generating algorithms based or the data themselves. Either way, if that's the case why sell it for $88??? sell it at cost ($5) or even give it away for free and just quickly build a huge user base. Am I way off here?
As I understand it users don't necessarily opt in to contributing data to comma's database. So there will be a large subset of hobbyists that just use it to monitor their own driving data privately - these are the users that comma needs to charge up front.
Plus, psychologically it feels like an investment with ROI in "comma points" for those who do contribute their data, with some vague promise of a reward later when someone (who?) decides to purchase comma points. So the upfront cost is justified.
Comma.ai's autonomous driving software implements the main control loop in Python. It's full of memory allocations. The project is far from serious engineering.
I remember George Hotz stating in an interview a year ago that he was going to be a billionaire by the end of 2016. He has quite the ego, there's tons of OBD-II adapters that have been around for a while and many successful Kickstarter campaigns launching better OBD-II adapters.
should be integrated with the ones by the given manufacturer on the specific model, and AFAIK all the money is in the software that can read those non-standard PID's.
And this is border-line (or downright just over the border) with hacking and/or reverse engineering the manufacturer's own software.
Slightly off topic, but can someone here explain what in OpenPilot that makes it so technically superior? Or is the (partial?) open source part of it the most seductive part?
I only quickly looked over the source code so I am not sure if I missed something. But looking at the top level code, it seems like something anyone can accomplish after taking the Udacity SDC class (minus the CAN interfacing, but that shouldn't be all that hard?)?
I have one of those; as far as I could tell they're crappy non-compliant Chinese knockoffs of real ELM327 chips. I wasn't able to get much of anything good or interesting out of it and had to get a Beaglebone with CAN bus cape to get any farther (other problems with that but that's separate).
Hotz confirms if you read the comments on the article.
While this plugs into the OBD-II port but the main use is to dump the CAN bus. Comparing it with OBD-II dongles where the functionality is restricted to the OBD part is misleading. It's far from universal, as not all cars expose all the CAN bus at the OBD-II socket, but a good start for sure. I ordered mine.
I experimented with OBD-II devices for a while, paired with a phone app like Torque, and I found that the lower-level information (e.g. data about any particular air sensor) just wasn't interesting or useful to me. And other useful info (e.g. speed) I can get from my dash or other sources.
Where these devices come in extremely handy, however, is by allowing you to look up the opaque fault codes that your car's computer produces when something goes wrong.
For $10-$20 off eBay or similar online stores, you can get a device that will tell you, for instance, when you have a cylinder misfire without having to go to a mechanic. (You may have to go to a mechanic to get it fixed, but at least you'll have a rough idea what needs fixing.)
Some mechanics charge you $120 literally just to plug in their OBD2 adapter and read the code, so yeah, even if it saves you one diagnostic fee, it's a bargain.
Note that Hotz is claiming his readers will do a lot more than the conventional ones you've seen before. Whether or not that's true remains to be seen.
Most auto parts stores will read the codes for you for free. Some will even loan you tools to fix your car. They are in the business of selling parts and are happy to sell you whatever part you need to fix the problem.
The nice thing about Torque and an OBD-II dongle is the fact that it can help you diagnose those "random" issues that only happen occasionally.
You set up Torque into logging mode, clear your codes, turn on the GPS and mapping, and drive away. When your car does "that thing" take a note of the time, then when you get home, go back thru the logs around that time mark, and take a look at all the sensor data, plus any thrown codes. If you know your car, and understand what is going on, it can help you to narrow down the diagnosis.
While a regular code reader (or getting the codes read) will help you by giving you the codes, being able to get the codes, timestamped in a log along with sensor data can go much farther in telling you where a particular problem lies.
While there are other code readers out there that will do this logging and tracking too, they typically cost hundreds or thousands of dollars - well out of the price range of most home mechanics.
There are many other things that Torque can do or be used for (for instance, virtual gauges are a nice feature - you can set up an Android tablet with a cluster of them giving you much more feedback than you can get from your regular dash instrument cluster, and it's cheaper and easier than setting up a bunch of physical gauges on a stock vehicle).
if all you care about is rpm's and high level stuff, I absolutely agree. a $10 bluetooth dongle is more the sufficient. However, data about any particular sensor becomes significantly more intersting if you look at the bigger picture comma.ai is presenting. with their openpilot platform (ie, the actual self driving code/product) it needs to know what those sensors are reporting. ie, is the radar reporting an object in front of you?
panda+cabana allows joe user to identify (and report back to the project) what they are seeing on the CAN bus.. so it can be catalogged and added to the database for all the thousands of different vehicle makes/models on the road.
Isn't ODB-II just doesn't have anything useful for self-driving? What's is "fragile" part of ODB-II? How does this yet another dongle solve "fragile" part? Isn't it just arduino-like board and ODB-II shield?
Depending on the car, it has many things relevant to self driving. Vehicle speed, RPM, steering wheel angle, etc. For some cars, you can jump to the CAN bus via that port and get more.
It is though, far short of everything needed. He's pitching it as perhaps part 1 of a bunch of other stuff you would need. That's aside from the idea that DIY self driving sounds, er, unwise.
OBD2 is the connector and the protocols used on that connector. The vehicle CAN bus is on the OBD2 port, and the "K-line", which is diagnostic only, is also there.
The connector has at least 1 CAN bus on it, some pins are "manufacturer discretion" meaning the manufacturer may put CAN or other signals on the connector.
Nowadays most vehicles have several CAN and LIN buses and it's unlikely that all traffic gets routed to the OBD2 connector, but some stuff is. Again, it depends on the manufacturer.
There's an israeli start-up doing much more with that car data. telling you about problems and more. and it costs as much as 20-30$
https://engieapp.com/
So it turns out geohotz is great at breaking other peoples' stuff and finds making products is harder. Who knew? Soon a 16-year-old will find a massive security vuln in this ODB bridge and the cycle will be complete
Or even new. It's an OBDII bridge.. except maybe with a software mindset instead of an automobile one, thus some wifi chip (looks like an ESP32 on the picture) and a cute form factor. I ... don't get it.
I thought hotz finally found his spot and excepted some small nuc like board + a set of cam and sensors ..
I've been following Comma.ai since I read the Bloomberg article about George hacking a self-driving car in his garage. While I have read the criticism on HN and think it is reasonable, I must admit I'm rooting for George and his team. I'm happy to see they launched this product and are continuing to make progress after the NHTSA incident. I'm looking forward to testing their tech myself.
Looks like they're just trying to get additional sensor data to train their neural nets (crowd source the data). I'm not sure if a single camera from a dash mounted mobile device plus vehicle control data is enough for training a neural net for fully autonomous driving, but it's certainly valuable for driver assist features.
He also said he will "ship" his product and badmouthed his competitors for not shipping. Then he cancelled his product after one cease and desist. George is a brilliant mind, but I hope he figures out how to become a better entrepreneur. He has so much potential.
If you want some of the features of the Panda interface (not the cloud connected dashcam) it seems like Automatic [1] seems to do the job. Any happy users of Automatic?
I used automatic for a while. It was pretty limited, and pricey. I've been using a panda for several weeks now, and FAR more capable. It probably boils down to: do you want a pretty UI dumbing the info down for you, or do you want the raw data so you can do things with it?
I got it actually, they reimplemented ODB-II in a more stable manner to provide better stability and performance, ELM327 is the only player on the field and provide less CAN busses (they are just not connected at all)
I didn't understand what comma is trying to do and how selling 1000 "FitBits for your car" to "car enthusiasts and hackers" for $88 helps to compete with Waymo.
Given the absurd insecurity of the OBD II CAN interface on all modern vehicles, it seems insane to install anything there with a wireless interface on it.
You have to unlock most modules, or input a code along with updates, otherwise you brick the the module.
Current generation vehicle electrical architectures are not network safe and rely on physical security.
There is a big trade-off here for the next generation; the electrical architecture will be COMPLETELY locked down, and end users will be locked out of making any updates to modules - something that tinkerers and home-brewers are at odds with. Read only access will still be allowed.
That's nonsense. if his claims were true, he could've sold the lot for nine or ten figures to somebody who was willing to deal with NHTSA.
It is exceedingly foolish to believe George Hotz's extremely obvious lies. George Hotz is a smart guy who made some big mistakes, and isn't man enough to admit that he was lying.
If you mean what you say: buy this thing, install it on your car, and use it daily.
I dare you.
Oh right, you'd never do that, because some tiny part of you knows that George Hotz was lying his ass off about his tech, and that you'd have to be a crazy person to trust such a flagrant liar with your life.
Yeah you're right. I want to buy it though, and then wait a couple of months before plugging it into my own car. I'm just saying you can't just dismiss the guy's ability because he comes across arrogant. He's proven he's a hacker, and now he's trying to prove he's a maker as well.
Maybe this Panda thing is engineered really well, and the money and reputation will get him to a point where he can run a nice company. Maybe not and this things get some people killed and he will be thrown in jail for building a recklessly unsafe product, I don't know. I don't own a car right now so all I can do is talk big.
The issue is that he was obviously lying. He claimed he was weeks away from autonomous cars. If this was true, he would've sold the tech for a staggering pile of cash.
Instead, all the evidence looks like he thought he could solve the problem on his own, in record time. Then he made a pretty basic POC (able to handle a small number of very simple conditions). Then he realized he couldn't do it. And so he pretended that he'd solved a problem nobody else had, but wasn't going to share or sell the answer with anybody else because the government is bad.
Unfortunately, some people hate the government enough that they want to believe this. But it's a dumb story and an obvious lie. George Hotz does not have autonomous driving technology. He never did, and he never fucking will. He's a snake oil salesman.
That's total bullshit. There are so many companies seriously working on autonomous vehicles, such as GM Cruise, Auroa Innovation, Drive.ai, Zoox, Nuro.ai, nuTonomy, Varden Labs, AImotive, Ford, and Nvidia
Edit, because George is on here: George, I want to like you, because I think your tech is really good (the street image segmentation from RGB images is seriously impressive- https://commacoloring.herokuapp.com/) and I think your business model of offering cheap devices and free services to crowd-source data, along with the comma points to incentivize users could give you a big competitive advantage. But the hyperbole makes it difficult to take you seriously.