System and method for map vectorization in advanced driving assistance system

A computing system, comprising:

• a processor;
• and
• a memory coupled to the processor and storing instructions that when executed by the processor cause the processor to perform a method for training a machine learning model to generate vectorized maps for autonomous driving, the method comprising:
• obtaining labeled training samples comprising images and vectorized ground truth information associated with the images;
• generating, based on a machine learning model, a prediction output for each training sample, the prediction output comprising a vectorized map;
• applying a differentiable rasterization technique to a vectorized map element within the vectorized map to obtain a segmentation mask;
• and
• applying the differentiable rasterization technique to the vectorized ground truth information associated with the vectorized map element to obtain a ground 13 truth segmentation mask;
• computing a segmentation loss function based on the segmentation mask and the ground truth segmentation mask;
• and
• updating the machine learning model based on the segmentation loss function, thereby facilitating optimized generation of vectorized maps.

A non-transitory computer-readable storage medium storing instructions that when executed by a computer cause the computer to perform a method for generating vectorized maps:

• obtaining labeled training samples comprising images and vectorized ground truth information associated with the images;
• generating, based on a machine learning model, a prediction output for each training sample, the prediction output comprising a vectorized map;
• applying a differentiable rasterization technique to a vectorized map element within the vectorized map to obtain a segmentation mask;
• and
• applying the differentiable rasterization technique to the vectorized ground truth information associated with the vectorized map element to obtain a ground truth segmentation mask;
• computing a segmentation loss function based on the segmentation mask and the ground truth segmentation mask;
• and
• updating the machine learning model based on the segmentation loss function, thereby facilitating optimized generation of vectorized maps.