Tag: selfdriving

Human Self-Driving Cars

The reason Uber [is] expensive is because you’re not just paying for the car, you’re paying for the [driver] in the car.” In other words, from Uber’s perspective, a self-driving car is a car where they don’t have to pay for a driver; the implementation details don’t matter.

With that in mind, think again about the commute problem: right now 75% of Americans drive alone to work. Every one of those solo commuters is a potential UberPool driver, and not just that: because they are making the trip whether they are an UberPool driver or not, they are, from Uber’s perspective, self-driving cars. They are drivers Uber would not need to pay for. This, I believe, will be Uber 2.0: human-powered self-driving cars primarily focused on commutes.

Selfdriving advantage

Error-Prone is cute little game of chaos and carnage made for 26 people to play around 1 keyboard. The end result illustrates perfectly how self driving cars are vastly superior to their human counterparts in terms of traffic grid lock, efficiency and avoiding road accidents. A screen shows 26 autonomous cars driving in a loop—one for each letter of the alphabet. Up to that many humans can take control of the cars by pressing the corresponding letter. But doing so is the first step in the inevitable path toward traffic flow inefficiency, at best, and a massive pileup, at worst.

Remote driving

it will still have a driver to monitor the truck’s systems and intervene in the event of a malfunction.

a bit of a stretch to call this autonomous, and it’s not obvious to me why this is economically better, but a nice start.
2022-01-29: this is becoming a broader trend, with 1 operator ideally controlling several systems at once:

“There’s just no way this isn’t going to explode as a category”. As industrial machines become more capable and connected, the number and variety of these jobs will grow. New forms of remote physical work may involve supervising multiple autonomous machines. Some companies see remote human helpers as a stopgap. Phantom Auto has sold its remote driving technology to companies working on self-driving cars and delivery robots. These vehicles can handle many situations on the road autonomously but struggle with unusual situations, poor weather conditions, or instrument anomalies, requiring a person to step in and help.

Robot Logistics

Amazon Warehouse Automation Challenge. As with everything, Amazon are cheapskates. The price money is just $25k, hardly appropriate for this. For how it is in those warehouses, check out fulfillment
2019-05-21: USPS Tests Self-Driving

For this pilot, the human driver will handle the truck on surface streets, but TuSimple is already looking to a second phase of the pilot, where the robot does all the work. Meanwhile, it’s 400-person team is working to expand the robot’s operating envelope. The system can handle high winds, night driving (handling high beams was a pain), and rain, while ice on the road remains “a nasty problem.” If it never succeeds, the postal service has a team of mules up for the task.

2020-03-20: Missed Logistics Opportunity

Suddenly the world has been thrust into a crisis with 3 interesting aspects:

  1. A huge upswing in demand, and delivery companies are falling way behind.
  2. A sudden desire to not have a delivery driver touch packages, and drivers don’t want to interact with people.
  3. The roads in some areas have become almost deserted due to lockdowns.

What a glorious opportunity this could have been for the road based delivery vehicles. While they have not yet reached the safety level needed to do full time operations with no human on board in regular traffic, it’s quite possible that they can do it on mostly deserted streets. Particularly if low speed operations can be tolerated on those streets. However, even if that’s true, since nobody anticipated this, nobody has worked to build proof of that level of safety.

2020-06-26: Zoox

The ability to deliver anything in an Amazon warehouse on short notice will be a very attractive product. The cost of robot delivery will be low enough to be bundled in with Amazon Prime. If you can get anything in one of those giant Amazon warehouses in 30 minutes, that’s scary news for the rest of retail.

2020-12-14: Zoox robotaxi

this is interesting from a design perspective: what assumptions are no longer true and can be revised for a better experience? Passengers face one another, allowing for a more social experience. The interior is spartan, not the overcrowded complex dashboard of current cars and some robotaxi designs. Just a small display and charging port. The seats mix taxi goals (ease of cleaning and able to handle heavy use) with car design. The electric vehicle design allows a low center of gravity, and combined with wheels moved to the corners of the vehicle, a more flexible interior design with more space for the same footprint. Each wheel can also turn independently, allowing for an 8.6m turning radius. In many cases, it will not turn at all, when it wants to change direction of travel, it just changes. The vehicle is narrow and short enough, given that, to handle streets and driveways that might be a challenge for wider vehicles. Airbags are integrated into the special seats and their enclosing walls for extra crash safety.

2021-07-06: Posthuman Logistics

Outside of London is a massive supermarket—one that customers cannot enter. Instead it’s dedicated to fulfilling online orders. It’s filled with an upper-level cartesian grid swarming with over 2000 wheeled robots that zoom around in the X- and Y-axes. Beneath the robots’ wheels, each square of the grid is filled with up to 21 milk crates loaded with grocery products. The ‘bots can suck these bins up through their bottoms, then zip them over to the periphery, where additional sorting ‘bots pick-and-package them.

2023-02-23: Zoox goes public in California

Last week, the California DMV granted us our permit to operate our robotaxi autonomously on public roads. This weekend, we hit the road! It marked the first time in history that a purpose-built robotaxi—with no manual controls—drove autonomously on open public roads with passengers.

Selfdriving dealbreakers

Are today’s challenges of making robocars dealbreakers? short answer: no

Maps are too important, and too costly

Google’s car, and others, rely on a clever technique that revolutionized the DARPA challenges. Each road is driven manually a few times, and the scans are then processed to build a super-detailed “ultramap” of all the static features of the road. This is a big win because big server computers get to process the scans in as much time as they need, and see everything from different angles. Then humans can review and correct the maps and they can be tested. That’s hard to beat, and you will always drive better if you have such a map than if you don’t.

Any car that could drive without a map would effectively be a car that’s able to make an adequate map automatically. As things get closer to that, making maps will become cheaper and cheaper.

Naturally, if the road differs from the map, due to construction or other changes, the vehicle has to notice this. That turns out to be fairly easy. Harder is assuring it can drive safely in this situation. That’s still a much easier problem than being able to drive safely everywhere without a map, and in the worst case, the problem of the changed road can be “solved” by just the ability to come to a safe stop. You don’t want to do that super often, but it remains the fail-safe out. If there is a human in the car, they can guide the vehicle in this. Even if the vehicle can’t figure out where to go to be safe, the human can. Even a remote human able to look at transmitted pictures can help the car with that — not live steering, but strategic guidance.

Rebuild cities before population decline

What we need is for self-driving cars to become available and cheap enough in cities that are still growing fast enough, and which have legal and political support for driving such cars fast close together, so they can achieve high throughput. That is, people need to be sufficiently rewarded for using cars in ways that allow more road throughput. And then economic activity needs to move from old cities to the new more efficient cities.