Tesla HW2 Autosteer First Drive

Yesterday evening I was driving on the CA 87 freeway in Santa Clara, heading South to San Jose with three other NVIDIA solution architects. It was after sunset, raining, and slow traffic even in the carpool lane. Then, alsmost as if on queue for Jensen’s CES keynote which we were off to watch, the low-speed autosteer icon appeared on my dashboard, indicating autosteer was available.

In current beta form, low-speed autosteer is only available when driving 35 miles per hour or slower. Traffic in the non-carpool lanes was stop-and-go, but the carpool lane was moving in the mid-30’s, perfect conditions to test out autosteer. Even at nighttime and in the rain, the system steered the car dead down the center of the lane. Driving manually, I would typically hug the left side of the carpool lane since that section of CA 87 has a wide left shoulder, so being a few inches closer to the stop-and-go traffic in the lane just to my right was at first a bit unnerving. After about a mile, however, I got used to letting autosteer do the work. The system is actually quite intuitive with just a little bit of practice.

After only a few miles I had to disable autosteer to merge across 3 lanes of traffic for my exit. As soon as I entered the slow lane, however, the autosteer available icon re-appeared so I gave it a try for the last half mile. Once again, the system worked flawlessly, even steering the car off the freeway and down the right lane of the three lane exit ramp at Park Ave.

The only thing more exciting than testing out autosteer was of course Jensen’s CES keynote where we heard about the latest innovations for AI for self driving cars, for your home, and in PC gaming. In case you missed the yesterday’s keynote, you can watch the replay below.

The NVIDIA channel on YouTube has the keynote nicely divided into segments, like the AI for Self Driving car segment.

Our you can watch the entire keynote, about 90 minutes, on UStream.


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 Uncategorized. Bookmark the permalink.