Tesla Autopilot 2.0 Spreadsheet Tracks Systems Functionality

Tesla Autopilot


Tesla Autopilot

Tesla Autopilot

As Tesla continually adds incremental updates to bring its Autopilot 2.0 up to parity with the original first-generation Tesla Autopilot; what works and what doesn’t?

It’s outstanding that we have all these skilled and dedicated people in the tech field that are willing to go to great lengths to research and organize data related to EVs. Recently, a Tesla owner took the time to put all Autopilot features in a nifty spreadsheet, in order to show how the latest second-gen features compare the the original Mobileye Autopilot 1.0.

Tesla Autopilot

A self-driving Model X with new enhanced hardware was demonstrated by Tesla in October

The new Autopilot system in the Tesla Model S and X has additional hardware, referred to as Hardware 2, which initially wasn’t configured to offer all of the standard features that Tesla owners came to know and love. Tesla has been in a lengthy process of not only building its own proprietary version of the Mobileye system, but also using continual over-the-air updates to bring features to parity.

The timeline has been longer than many expected, and there have surely been some bumps along the way. Knowing what works and what doesn’t, related to each update, is valuable information. The user that put the spreadsheet together shows each function, when the firmware was released, and whether or not parity has been achieved.

According to the Google Doc spreadsheet, the latest update (17.22.46), which Elon Musk calls smooth as silk”, has nearly every function enabled. However, the automatic rain-sensing windshield wipers are still not active. Some functions still have a “?” listed, since the user hasn’t found any information verifying parity. The Automated Emergency Braking is back, but it still only functions up to 28 mph.

Other reports have shown that the new updates are “smoother”, but there are still some issues with local roads. Meanwhile, highway driving has improved substantially. Tesla continues to have repeated departures and new hires in the Autopilot department, and more specifically with regards to those in charge. The automaker still asserts that the new system, once fully updated, will be capable of a much higher level of autonomy than the outgoing technology.

Source: Green Car Reports

Category: Tesla

Tags: , , , , ,

3 responses to "Tesla Autopilot 2.0 Spreadsheet Tracks Systems Functionality"
  1. It would be interesting if they could gather test data, and have some leading ‘Extra Beta’ level lead testers in different cities, testing for them, the ‘Next Step’ features, prior to general release, as well!

    Maybe such cars could add multiple ‘Dash Cams’ inside, pointing in all directions, for testers to review, as well, like in a ‘Multi-camera’ Security Cam approach?

  2. Four Electrics says:

    Having A/B tested the new and old AP, I can tell you that the old, Mobileye based Autopilot remains far superior to “2.0” (really 0.6).

  3. Michael DeKort says:

    Autonomous Levels 4 and 5 will never be reached without Simulation vs Public Shadow Driving for AI

    Every AV or SDC maker using public shadow drivers for AI will have to drive each vehicle type ONE TRILLION miles at an expense of at least $300B and will be putting those public shadow drivers and the public at risk. A risk that will result in injuries and fatalities as the scenarios progress from the currently benign to progressively more complicated and dangerous scenarios. Like accident scenarios that will have to be driven thousands of times each to train the AI. Factor in the fact that shadow driving itself leads to 17-24 second response times, especially in critical situations, and you can see this whole situation is untenable. Autonomous levels 4 and 5 will NEVER be reached this way. (To date no children nor families have been killed because the scenarios are benign. When they move to actual accident scenarios this will change. Governments, insurance companies and litigators will ensure it.)

    Regarding the cost. One trillion public shadow driving miles in 10 years is 228k vehicles driving 24×7. (Since most vehicles cannot take 400k miles a year you will wind up using more than that 228k). Those driving 24×7 takes 3 drivers a day that is 684k drivers. (Drivers who have to be skilled enough to get every action right or AI doesn’t learn the right thing). My very conservative $300B estimate is for the vehicles, gas sensors and drivers only (At a rate of $20k for the vehicle and sensors). Beyond that cost will be the cost of litigation for the accidents, injuries and loss of life that will occur. You cannot drive and redrive dangerous complicated scenarios over and over, thousands or more times, and not have accidents. Especially for scenarios that are meant to learn what to do in actual accident scenarios. Are you going to have shadow drivers drive accident scenarios in bad weather, with bad road conditions with dozens of other vehicles, pedestrians etc around? And keep driving billions of miles restumbling on them to train AI? Just counting the known or anticipated accent scenarios you would causes thousands, hundreds of thousands or more accidents till you got it right. (And that doesn’t count AI getting it right but the other drivers overcoming that and causing an unavoidable accident). That will be thousands in not tens or hundreds of thousands of injuries and loss of life and property.

    Now let’s factor in the litigation and government intervention. As it is no children have died in a public shadow driving accident to date. Even in benign conditions. (The current non-complicated or dangerous situations. Where the streets are well lined lines, mapped and learned and there are good weather and street conditions without a lot of complexity. That alone could shut the whole thing down for quite a while starting tomorrow). Let’s say it doesn’t happen and some time goes by until the dangerous scenarios are run. There is absolutely no way various levels of governments, insurance companies, lawyers and individuals let you turn public roads into accident scenario beta test or Guinea pig sites. When this happens everything will come to a grinding halt leaving most of the complicated, dangerous or accident scenarios unlearned. That will stop L4 and L5 progress. (Tesla, comma.ai, PolySync etc are on this path now with the public not paid drivers as those beta testers).

    So what is the answer. . . Simulation for AI data gathering, engineering and testing. Augmented with test tracks and other sources where simulation cannot actually meet the burden and to ensure the accuracy of the simulation.

    Let me address the first thing folks usually say at this point. That simulation is not up to this. YES it is. Why don’t most folks know that? Because most of them come from Commercial IT or even the automakers and they do not have exposure to nor experience in simulation in the aerospace industry. Which has had most of the capabilities needed for 20 years. Is this more complicated than that? Yes. But the technology is there. Beyond that I believe that some of the current simulation products are not that far away. The problem is that part of the industry is disjointed. Not everyone knows what is available, what the capability gaps are or how to close them. That is why I am proposing an international association and trade study exhibit be created. (We have recently determined we want to add test tracks and all non-public AI and testing entities to the association.)

    Update 7-7-2016 – Chris Urmson declares L3 cannot be reached with public shadow driving. This confirms it cannot lead to L4 or L5 either

    Car companies’ vision of a gradual transition to self-driving cars has a big problem


    This is EXACTLY what happens in shadow driving. If you can’t expect a human being who owns the car to handle level 3 due to computer to human handover issues how can you handle ONE TRILLION MILES of public shadow driving to handle teaching AI, engineering and testing? You cannot have it both ways. And keep in mind these folks are figuring this out in benign or easy conditions. Wait until bad weather, slippery roads, complex situations or actual accident scenarios hit.

    For more detail on all of this as well as references for information I cited please see the articles below

    Stop relying on AI to make Autonomous Vehicles – You are wasting time, $80B and risking lives

    Autonomous Vehicle and Mobility Simulation Association and Trade Study

    Who will get to Autonomous Level 5 First and Why.