Posted on May 29, 2016 by Matt Pressman
How does Tesla Motors [NASDAQ: TSLA] approach implementing self-driving cars into its fleet? Some answers came this past week, Sterling Anderson, Director of Tesla’s Autopilot program spoke at the MIT Technology Review* EmTech Digital conference. According to Anderson, "The ability to pull high-resolution data from these vehicles and to update the vehicles over the air is a significant part of what’s allowed us [Tesla] in 18 months to go from very behind the curve to what is today one of the more advanced autonomous or semi-autonomous driving features."
Above: Sterling Anderson speaks at the MIT Technology Review EmTech Digital conference (Source: Electrek)
However, Anderson stated that, "Autopilot is not an autonomous system and should not be treated as one,” said Anderson. “We ask drivers to keep their hands on [the wheel] and be prepared to take over.” Tesla's 12 ultrasonic sensors positioned around the car sense nearby objects, and the forward-facing cameras and radar units were intended for bigger things. Tesla engineers began using data streaming from cars with those sensors and information on their locations to start testing autonomous driving features.
Above: Based on the same data with the Autopilot off versus on, Anderson shows how Tesla Autopilot is more "cruise missile" like in its ability to stay in a more narrow corridor safely away from other vehicles versus a human driving manually (Source: Electrek)
Anderson explained, “We will often install an ‘inert’ feature on all our [Tesla] vehicles worldwide,” said Anderson. “That allows us to watch over tens of millions of miles how a feature performs... Since introducing this hardware 18 months ago we’ve accrued 780 million miles. We can use all of that data on our servers to look for how people are using our cars and how we can improve things.” Every 10 hours Tesla gets another million miles worth of data, he said.
Above: Slide showing difference of miles driven with Autopilot on and off which is crucial to Tesla’s development and roll-out process (Source: Electrek)
In addition, Electrek reported on Anderson's talk and noted, "Tesla is now gathering more data from autonomous miles driven in a day than Google’s program has logged since its inception in 2009... [in addition] Google’s miles are city miles, while the [Tesla] Autopilot is for highway driving which gives a distinct advantage to Tesla in term of racking up data based on miles driven... [and] the data Tesla is gathering while the Autopilot is not turned on is also extremely valuable and covers a wider range of road types." For additional insights into Anderson's point of view on autonomous driving, check out his fascinating TEDx Talk (see video above) last year.
Above: Sterling Anderson's TEDx Talk (Source: TEDx Talks)
Anderson's background is ideal for his at role at Tesla Motors as he, "has spent the better part of the last decade questioning the how of autonomous vehicle development. He spent much of this time at MIT, where his work in shared autonomy generated nearly $2M in research funding, four patents, several academic publications and hundreds of print and online articles worldwide. He... currently leads the Model X program at Tesla Motors." And, since the time of this Tedx Talk, Anderson now leads Tesla's self-driving vehicle efforts as Director of Autopilot Programs. We're looking forward to what Anderson has in store for Tesla's upcoming software updates.
*Source: MIT Technology Review