Lucid unveils advanced driver assist features to compete with Autopilot

[diplomat33]

Lucid gave more details on DreamDrive:

"Lucid Motors, which seeks to set new standards for sustainable transportation with its advanced luxury EVs, today announced Lucid DreamDrive, a new benchmark in advanced driver-assistance systems (ADAS). The first-of-its-kind platform combines the most comprehensive sensor suite on the market with a cutting-edge driver monitoring system, all standard on the first versions of the Lucid Air. Taken as a whole, Lucid DreamDrive signals Lucid’s intent to deliver sophisticated assisted driving capabilities in its vehicles"

Along with the Lidar sensors, the Air is equipped with 32 sensors including camera, radar, and ultrasonic sensors.

Here are the main features delivered by Lucid DreamDrive:

Safety:

• Surround View Monitoring
• Blind Spot Display
• Cross Traffic Protection
• Traffic Sign Recognition
• Automatic Emergency Braking
• Alerts for distracted or drowsy drivers

Driving:

• Full Speed Highway Assist (a combination of Adaptive Cruise Control and Lane Centering)
• Traffic Drive-Off Alert
• Headlight Assist

Parking:

• Autonomous Parking Assist
• Pullout Control
• Maneuver Comfort Braking

Lucid says that the system is going to deliver more features through over-the-air software updates next year.

"Lucid DreamDrive is also the first ADAS system built upon a high-speed Ethernet Ring, a unique cornerstone of Lucid Air’s advanced electric architecture, which additionally serves as a fully redundant platform for key functions such as steering, brakes, sensors, and more. This includes redundant independent power sources and communications paths, fail-operational actuators, and fault-tolerant computation"
Lucid unveils its driver-assist plan to compete with Tesla's Autopilot - Electrek

 

[thewishmaster]

Nice wish list... now where’s the demonstration of these did they ever mention which OEM they would partner with for this, or are they doing it from scratch?

 

[diplomat33]

Here are some more details:

• Lucid will equip its upcoming Air electric sedan with standard lidar and in-car monitoring for future Level 3 self-driving capability in what it calls DreamDrive.
• The Air will launch with less tech than what Tesla currently offers, but within a year it will likely be on par with Cadillac’s Super Cruise hands-free system and within three years, will have Level 3 hands off and eyes-off capabilities, which no automaker currently offers.
• The vehicles are not planned to become Level 4 ready because Lucid sees Level 3 as a goal it can achieve without adding additional cost to its vehicles.

Lucid Air EV Will Have Lidar and Driver-Assist Systems on Board

 

[diplomat33]

Nice wish list... now where’s the demonstration of these did they ever mention which OEM they would partner with for this, or are they doing it from scratch?

Lucid is using Mobileye.

I am sure we will get demos later this year. Lucid is expected to unveil the final production version of the Air later this year, around September (I think).

 

[Bladerskb]

5x Radars
1x Lidar
9x ADAS Camera
4x Parking Camera
12x Ultrasonic

I think it will be interesting to learn what gen of Radar these are.
Most probably the latest gen from Continental/Radar and also the camera MP.

 

[diplomat33]

5x Radars
1x Lidar
9x ADAS Camera
4x Parking Camera
12x Ultrasonic

I think it will be interesting to learn what gen of Radar these are.
Most probably the latest gen from Continental/Radar and also the camera MP.

Thanks for sharing. I think these sensors are awesome! And it will be powered by Mobileye so the computer power should be really good too. It looks to me like Lucid should be able to provide excellent highway L3.

Interesting. It looks like they did trim down the sensors a bit since an earlier diagram showed side and rear lidar coverage as well. But I like the front lidar. I think the front lidar should provide excellent reliability for those situations like a stopped vehicle or a white semi crossing in front.

I find it very interesting that even with all these sensors, Lucid doesn't consider the current sensor/hardware good enough for L4 and therefore only plans to do L3 right now. I am guessing it is because it lacks side and rear lidar. So for city driving where you might have a lot of objects all around you, the sensors lack a bit of redundancy on the sides and rear. You don't want a situation where the car does not see cross traffic at an intersection because the side cameras misses it. Hence, why they don't want to attempt L4 on this sensor suite.

 

[mtndrew1]

So nice they’re promising reasonable capabilities and timelines. Would be nice if another company did that...

I would be really happy with a solid L3 right now.

 

[AmokTime]

I only have 2 optical sensors on a swivel-mount, and I can do L5.

 

[Soda Popinski]

I only have 2 optical sensors on a swivel-mount, and I can do L5.

But your FSD computer is way more advanced.

 

[MP3Mike]

Traffic Drive-Off Alert

What is "Traffic Drive-Off Alert"? Does that mean that if you are stopped in traffic and the vehicle in front of you goes that it will alert you and not actually start moving on it's own?

 

[diplomat33]

What is "Traffic Drive-Off Alert"? Does that mean that if you are stopped in traffic and the vehicle in front of you goes that it will alert you and not actually start moving on it's own?

I don't know. I can't find any more details on what the feature does. We know Adaptive Cruise Control would move the car forward automatically if the traffic ahead starts moving. So I think the driver assist could move the car forward on its own and not need to alert the driver. My guess is that it is for when you are driving manually. Say you are driving manually and get distracted in stop and go traffic and don't realize that the traffic ahead has started moving, then it will alert you. So it would only be for when you are driving manually and are distracted. That's my guess. But it could something else entirely. We will have to wait to Sept 9 for the unveil to hopefully get more info.

 

[J1mbo]

What is "Traffic Drive-Off Alert"? Does that mean that if you are stopped in traffic and the vehicle in front of you goes that it will alert you and not actually start moving on it's own?

Exactly that. Mobileye already supports this feature. It saves you from those embarrassing moments when you are stuck in traffic and have just discovered a great memestorm on Twitter so don't notice the cars moving off around you.

 

[Watts_Up]

Well, as people said... it looks good on paper.

I have not too much doubt that in perfect condition (freeway with no obstacle) everything would work as describe...

but in real life it would have the same issues that the Tesla FSD encounters and will make news paper front pages too.

 

[Huskyf]

Mores sensors more problems last week I saw on newspapers that to much lidar/radar can scramble signal of others cars with the sames suit of sensors. Why not 1000 sensors on a car next time for me is too much the human vision have 180° vision but not whn you drive only what you saw from windows and can heard problems sometimes and haman have two eyes not 8 not 32 two.

 

[diplomat33]

Mores sensors more problems last week I saw on newspapers that to much lidar/radar can scramble signal of others cars with the sames suit of sensors. Why not 1000 sensors on a car next time for me is too much the human vision have 180° vision but not whn you drive only what you saw from windows and can heard problems sometimes and haman have two eyes not 8 not 32 two.

Lidar does not scramble the signal of other cars. That is a common myth.

Autonomous cars need more sensors than humans to compensate for the fact that their vision is not as good compared to humans and their computers are pretty fast but dumb compared to humans.

 

[diplomat33]

Well, as people said... it looks good on paper.

I have not too much doubt that in perfect condition (freeway with no obstacle) everything would work as describe...

but in real life it would have the same issues that the Tesla FSD encounters and will make news paper front pages too.

Why would it necessarily have the same issues as Tesla? The front lidar should solve the problem of hitting stopped objects that Tesla cars have. Also, the driver monitoring system on the Lucid will greatly reduce cases of the driver not paying attention when the driver assist does something stupid. The Lucid won't have those accidents like Teslas have.

Remember they are not unsolvable issues that everybody has. GM has not had those accidents with SuperCruise. The only reason Teslas have these problems is because Teslas don't have enough sensors.

 

[J1mbo]

Why would it necessarily have the same issues as Tesla? The front lidar should solve the problem of hitting stopped objects that Tesla cars have. Also, the driver monitoring system on the Lucid will greatly reduce cases of the driver not paying attention when the driver assist does something stupid. The Lucid won't have those accidents like Teslas have.

Remember they are not unsolvable issues that everybody has. GM has not had those accidents with SuperCruise. The only reason Teslas have these problems is because Teslas don't have enough sensors.

GM probably have 1 SuperCruise mile (on curated routes in the US) for every 100,000 Autopilot miles (global, on almost any route), so probably not a great comparison...

Lidar's not the answer to the issue of hitting stopped objects. It's a software problem, not a sensor problem. Lidar just makes the software easier to write. I would hope it is finally resolved by Tesla in the "4D" release.

 

[diplomat33]

Lidar's not the answer to the issue of hitting stopped objects. It's a software problem, not a sensor problem. Lidar just makes the software easier to write. I would hope it is finally resolved by Tesla in the "4D" release.

Lidar is a more reliable solution. And if it is easier to solve with lidar, then it would make more sense to solve it that way, no? As you said, you "hope" Tesla will solve it with the 4D rewrite. "Hope" implies there is no guarantee. There is the possibility that the 4D rewrite will still not solve this issue. And the longer you go with the problem going unresolved, the more time for potentially another accident to happen. To me, it does not make sense to rely on a method that will take longer to solve the problem, if it solves it at all, and prolong the risk of an accident, when there is a better method that will be easier and more reliable. After all, this a safety issue. It makes sense to solve the problem in the most reliable and expedient manner possible in order. Furthermore, we are not talking about a cost prohibitive solution either. We just need one front lidar that is affordable (~$500) and software that you admit is easier to do. That seems like an obvious "win". The other solution is to save a few bucks but have a harder time writing the software that might not fix the problem, at least not right away. It seems to me like the lidar approach is the more common sense approach here.

 

[MP3Mike]

We just need one front lidar that is affordable (less than $1000)

But it isn't just a thousand dollars, that would cost more than $30,000,000/month, with that ramping up quickly past that as they expand capacity.

 

[diplomat33]

But it isn't just a thousand dollars, that would cost more than $30,000,000/month, with that ramping up quickly past that as they expand capacity.

It's less than $1000 per car on a car that costs around $100k. I doubt it will cut too much into the profit margins.