Tejon Ranch to Gilroy With Tesla HW2 Autopilot

Headed North today on California’s interstate 5, with plenty of charge to make it to the Buttonwillow supercharger, I pulled into Tejon Ranch supercharger around lunchtime today not because of the nearby In-N-Out Burger but hoping I had driven enough for the cameras on my Tesla to have completed calibration. It can take from 1 to 5 hours of driving for the cameras to calibrate after you install the 2.50.185 firmware, you don’t get a message saying calibration is complete, and you have to stop and restart your car after calibration is complete for the new autopilot functionality to become available. But it was worth it, even without the burger. As I drove back onto CA 5 North the dashboard immediately lit up showing the availability of the traffic aware cruise control (beta) autopilot feature.

While the current low speed autosteer functionality only works below 35 MPH, the dashboard display clearly shows that the NVIDIA powered HW2 system is working to track the lane the car is driving down, preparing for future upgrades. The position of the car in lane is not a canned image, by all appearances it is being generated in real time as you drive down the lane. Steer towards the right or left of the lane and the display tracks your every move.

The beta autosteer feature, as noted, only works below 35 MPH and only on “restricted highways” (I have not figured out what that means yet), and I haven’t had a chance to try it out yet, so more on the traffic aware cruise control.

My last car had so called “adaptive cruise control”, which I used often, but simply can’t be compared to the Tesla’s conceptually similar feature. The Tesla system offers 7 settings which let you control how close you follow other vehicles by twisting the autopilot control stalk on the steering column. I found 3 was an ideal setting for the 70 MPH speed limit on CA 5. Later in the day, on CA 101 in the rain, I adjusted the setting to 4 to leave a little more space. The system worked flawlessly for all 225 miles from Tejon Ranch to Gilroy.

One of the biggest differences from my old car was perhaps not due entirely to the HW2 but to the instant torque of the Tesla’s electric motor. In my old car, when the system slowed down due to a slow moving car, it took ten or more seconds for the car to accelerate back to the cruise setting, something that no doubt raised the blood pressure of many a driver who grew impatient with my failure to instantly respond to a slow car ahead pulling over into the slow lane. On the Tesla, the response is near instantenous.

Of course in California, on long stretches of CA 5, you still have a few reckless drivers that will try to pass you even if there is barely a car length between you and the car ahead. This sends more commonplace adaptive cruise control systems into another brake and slowly re-accelerate cycle, but the Tesla system again responded flawlessly to the few rude drivers that tried to cut in front of me today.

Google Maps on my phone estimated 5 hours 30 minutes for my drive today, while the Tesla nav system, including two charging stops, showed 6 hours 10 minutes. Actual time was within 5 minutes. But I arrived at my destination significantly more refreshed thanks to having the opportunity to get out and walk a bit as my car recharged and thanks to the first autopilot features. I can’t wait to see what comes out in the next update. Keep up the great work, Tesla!

Advertisements

About Marc Hamilton

Marc Hamilton – Vice President, Solutions Architecture and Engineering, NVIDIA. At NVIDIA, the Visual Computing Company, Marc leads the worldwide Solutions Architecture and Engineering team, responsible for working with NVIDIA’s customers and partners to deliver the world’s best end to end solutions for professional visualization and design, high performance computing, and big data analytics. Prior to NVIDIA, Marc worked in the Hyperscale Business Unit within HP’s Enterprise Group where he led the HPC team for the Americas region. Marc spent 16 years at Sun Microsystems in HPC and other sales and marketing executive management roles. Marc also worked at TRW developing HPC applications for the US aerospace and defense industry. He has published a number of technical articles and is the author of the book, “Software Development, Building Reliable Systems”. Marc holds a BS degree in Math and Computer Science from UCLA, an MS degree in Electrical Engineering from USC, and is a graduate of the UCLA Executive Management program.
This entry was posted in AI Car, Tesla. Bookmark the permalink.

One Response to Tejon Ranch to Gilroy With Tesla HW2 Autopilot

  1. Matt Ingenthron says:

    While I still like the idea of piloting myself, another part of me loves the technical aspect of seeing this work. Next time you’re in the OC area with some spare time to do a live demo, let me know. I’ll trade a double double for it!

Comments are closed.