Editor's Opinion
Why Autopilot 2.0 is a Big Deal
To fully appreciate Autopilot 2.0, one must understand the limitations of Autopilot 1.0. Autopilot 1.0 was built upon Mobileye’s object recognition system, which was based on a low-power GPU and rigid rules for object recognition. In some cases, Mobileye’s system would/could not recognize certain objects and this posed a serious limitation (and danger) to Tesla’s Autopilot system. Tesla built a complex and very capable system (that included HD mapping, radar analysis, and driving decision making) on top of Mobileye’s object recognition system. But the flaws of Mobileye’s system could only be mitigated by Tesla and not overcome. In order to truly improve Autopilot in a substantial manner, Tesla needed to develop their own object recognition system and own the entire software stack of autonomous driving. This is what they did for Autopilot 2.0.
Put simply, Autopilot 2.0 takes the input from cameras, radar, sensors and processes them on a high-powered GPU and computer. The key is Tesla is not using rigid rules (that have limitations) but rather they’re using a "neural net" (a type of AI system), which continuously gets better and will easily be 10x (if not 100x) more accurate than their previous system. (note: for more info on neural networks, see link below in Deep Learning Simplified)
As the neural net gets trained, it becomes increasingly accurate. The process should be fairly quick, and Autopilot 2.0 should be more accurate than Autopilot 1.0 within a 3-4 months (my guess). Within 6-12 months, Autopilot 2.0 will likely be 2-3x more capable and accurate than Autopilot 1.0. This is a big deal because it’s safety we’re dealing with, and Autopilot 2.0 will be a substantially safer experience.
The reason why Elon thinks Autopilot 2.0 will reach full self-driving capabilities within a couple years is because he’s confident in the power of the neural net (and the power of AI) to make itself better. In Elon’s words, this is a “solved problem.” Regulatory approval might take longer, depending on the country/jurisdiction, but the technology is at our doorstep.
Tesla Energy
Tesla and Panasonic to Collaborate on Photovoltaic Cell and Module Production in Buffalo, New York
Tesla and Panasonic have entered into a non-binding letter of intent under which they will begin collaborating on the manufacturing and production of photovoltaic (PV) cells and modules in Buffalo, New York. Under this agreement, which is contingent upon shareholders' approval of Tesla’s acquisition of SolarCity, Tesla will use the cells and modules in a solar energy system that will work seamlessly with Powerwall and Powerpack, Tesla’s energy storage products. With the aid of installation, sales and financing capabilities from SolarCity, Tesla will bring an integrated sustainable energy solution to residential, commercial, and grid-scale customers. The parties intend for Panasonic to begin PV cell and module production at the Buffalo facility in 2017. Tesla intends to provide a long-term purchase commitment for those cells from Panasonic.
Model 3
Tesla Model 3 Unveiling Will Include a "Part 3"
It's not necessarily a surprise that Tesla is planning a part three unveiling. There are still many unknowns about the vehicle, such as the finalized design, battery capacity, EPA-rated driving range on a single charge, available battery upgrades, and the pricing of upgradeable options.
Don’t plan on using your autonomous Tesla to earn money with Uber or Lyft
On Tesla's website, the section that describes the new "Full Self-Driving Capability" (A $3,000 option at the time of purchase, $4,000 after the fact) states "Please note also that using a self-driving Tesla for car sharing and ride hailing for friends and family is fine, but doing so for revenue purposes will only be permissible on the Tesla Network, details of which will be released next year."
Autopilot
All Tesla Cars Being Produced Now Have Full Self-Driving Hardware
We are excited to announce that, as of today, all Tesla vehicles produced in our factory – including Model 3 – will have the hardware needed for full self-driving capability at a safety level substantially greater than that of a human driver. Eight surround cameras provide 360 degree visibility around the car at up to 250 meters of range. Twelve updated ultrasonic sensors complement this vision, allowing for detection of both hard and soft objects at nearly twice the distance of the prior system. A forward-facing radar with enhanced processing provides additional data about the world on a redundant wavelength, capable of seeing through heavy rain, fog, dust and even the car ahead.
To make sense of all of this data, a new onboard computer with more than 40 times the computing power of the previous generation runs the new Tesla-developed neural net for vision, sonar and radar processing software.
Watch Tesla’s new fully self-driving car navigate around Palo Alto, driving through intersections & finding its own parking spot
Tesla released a video demonstration of a Model X equipped with its latest self-driving sensor suite, which is going into Tesla’s vehicles right now, and using the most advanced version of the software, which will be pushed to owners gradually throughout the coming year. The demo shows the Model X self-driving around Palo Alto, near Tesla’s headquarters. There are parts of the video on the highway which might look just like the Model X is on the current Autopilot, but once the SUV is on the streets of Palo Alto, it becomes clear that the vehicle is powered by something else.
Tesla October 19th 2016 Autopilot 2.0 Conference Call
Tesla announces Autopilot 2.0 hardware on all cars starting today, including Model 3. Allows for full level 5 autonomy when software is ready and pushed out to the fleet over time. They expect to demonstrate full autonomous driving from LA to NY by late next year (just in time for Model 3 deliveries to begin). We live in an amazing world.
This is a must-listen as Elon explains more details of Autopilot 2.0.
Elon Musk Promises Self-Driving Autonomous Tesla Motors Cars By the End of 2017
Tesla hopes its ghost in the machine will be fully ready by the end of next year, and the proof will be a cross country road trip. Musk said he could have a Tesla pick someone up from their home in LA and drop them off in the bright lights of Times Square, New York—then park itself. “It will do this without the need for a single touch, including the charger,” says Musk.
Deep Learning SIMPLIFIED: The Series Intro
Are you overwhelmed by overly-technical explanations of Deep Learning? If so, this series will bring you up to speed on this fast-growing field – without any of the math or code. The goal of this series is to give you a road map with enough detail that you’ll understand the important concepts, but not so much detail that you’ll feel overwhelmed. The hope is to further explain the concepts that you already know and bring to light the concepts that you need to know. In the end, you’ll be able to decide whether or not to invest additional time on this topic.
Elon mentioned in that Tesla has developed their own "neural net" for Autopilot 2.0. This video series gives a good background on understanding what a "neural net" is.
V8.0 Autopilot prevented a rear-end collision
It turned out traffic came to a complete stop because of an accident on the opposite direction of I-78, and Cherokee probably didn't notice the slow down traffic until the last minute. However, new V8.0 AP in MX spotted the Toyota infront of the Cherokee using radar and applied the hard brake. I really can't see Toyota at all until Cherokee was out of way. If I was driving, it will definitely be too late to apply the brake and I would have rear-ended the Toyota.
Other News
How Apple Scaled Back Its Titanic Plan to Take on Detroit
In the following months, engineers started leaving. Some chose to quit amid doubts over job security and skepticism that an Apple car product would ever come to market. Others were cut. In August, a first wave of employees was let go, followed by a second round in September. More than 120 software engineers working on a car operating system and testing procedures were cut. Several hundred hardware engineers working on car chassis, suspensions, and undercarriages also left, the people said.
Looks like the so-called Apple Car is dead.