公开(公告)号：US12233917B2

公开(公告)日：2025-02-25

申请号：US18155088

申请日：2023-01-17

Applicant: Magna Electronics Inc.

Inventor： Patrick R. Barragan ,  Charles A. Richter

IPC: B60W60/00 ,  G06V10/82 ,  G06V20/58

Abstract: A vehicular vision system includes a forward-viewing camera disposed at a vehicle, and an electronic control unit (ECU). Electronic circuitry of the ECU includes an image processor for processing image data captured by the forward-viewing camera. The vehicular vision system, responsive to processing by the image processor of image data captured by the forward-viewing camera, detects a target vehicle. The vehicular vision system, responsive to detecting the target vehicle, predicts, using a machine learning model, a probability for each action of a set of actions, with each action in the set of actions representing a potential action by the target vehicle. The machine learning model includes at least one discrete latent variable and at least one continuous latent variable. The vehicular vision system, responsive to predicting the probability for each action, autonomously controls the equipped vehicle.

公开(公告)号：US20230227073A1

公开(公告)日：2023-07-20

申请号：US18155088

申请日：2023-01-17

Applicant: Magna Electronics Inc.

Inventor： Patrick R. Barragan ,  Charles A. Richter

IPC: B60W60/00 ,  G06V20/58 ,  G06V10/82

CPC classification number: B60W60/0027 ,  G06V20/58 ,  G06V10/82 ,  B60W2420/42 ,  B60W2554/40

Abstract: A vehicular vision system includes a forward-viewing camera disposed at a vehicle, and an electronic control unit (ECU). Electronic circuitry of the ECU includes an image processor for processing image data captured by the forward-viewing camera. The vehicular vision system, responsive to processing by the image processor of image data captured by the forward-viewing camera, detects a target vehicle. The vehicular vision system, responsive to detecting the target vehicle, predicts, using a machine learning model, a probability for each action of a set of actions, with each action in the set of actions representing a potential action by the target vehicle. The machine learning model includes at least one discrete latent variable and at least one continuous latent variable. The vehicular vision system, responsive to predicting the probability for each action, autonomously controls the equipped vehicle.