Tesla Has Published A Patent 'Predicting Three-Dimensional Features For Autonomous Driving'

Featured image: Shutterstock

An autonomous car is a vehicle capable of sensing its environment and operating without human involvement. But achieving full autonomous vehicle operation is a very difficult task.

Tesla has made significant progress in this area and continues to improve. During the Q2 2020 Earnings Call, answering a question about Autopilot, Musk explained that what Tesla has done so far is pretty much operating in 2.5D (D-dimension). But 2.5D is not well-correlated in time, so the company is aiming for 4D. "You're thinking about the world in three dimensions and the fourth dimension being time," said Musk. Therefore, the company still has a lot to improve on the way to its goal.

Tesla has published a patent application "Predicting three-dimensional features for autonomous driving."

Patent filing date: February 1, 2019
Patent publication date: August 6, 2020


FIG. 2 is a flow diagram illustrating an embodiment of a process for training and applying a machine learning model for autonomous driving
Source: Tesla patent

Deep learning systems used for applications such as autonomous driving are developed by training a machine learning model. Traditionally, much of the effort to curate a training data set is done manually by reviewing potential training data and properly labeling the features associated with the data.

The patent discloses a machine learning technique for generating highly accurate machine learning results. Using data captured by sensors on a vehicle to capture the environment of the vehicle and vehicle operating parameters, a training data set is created.

In some, a three-dimensional representation of a feature, such as a lane line, is created from the group of time-series elements that correspond to the ground truth. This ground truth is then associated with a subset of the time series elements.

The trained machine learning model is used to predict a three-dimensional representation of one or more features for autonomous driving. For example, instead of identifying a lane line in two-dimensions from image data by segmenting an image of a lane line, a three-dimensional representation is generated using the time series of elements and odometry data corresponding to the time series. The three-dimensional representation includes changes in elevation that greatly improve the accuracy of lane line detection and the detection of corresponding lanes and identified drivable paths.

Tesla has made significant strides in the development of Full Self-Driving, as the company aims to achieve Level 5 Autonomy soon.

Follow @EvaFoxU