Nvidia corporation (20240232616). DISTANCE TO OBSTACLE DETECTION IN AUTONOMOUS MACHINE APPLICATIONS simplified abstract

DISTANCE TO OBSTACLE DETECTION IN AUTONOMOUS MACHINE APPLICATIONS

Organization Name

nvidia corporation

Inventor(s)

Yilin Yang of Santa Clara CA (US)

Bala Siva Sashank Jujjavarapu of Sunnyvale CA (US)

Pekka Janis of Uusimaa (FI)

Zhaoting Ye of Santa Clara CA (US)

Sangmin Oh of San Jose CA (US)

Minwoo Park of Saratoga CA (US)

Daniel Herrera Castro of Uusimaa (FI)

Tommi Koivisto of Uusimaa (FI)

David Nister of Bellevue WA (US)

DISTANCE TO OBSTACLE DETECTION IN AUTONOMOUS MACHINE APPLICATIONS - A simplified explanation of the abstract

This abstract first appeared for US patent application 20240232616 titled 'DISTANCE TO OBSTACLE DETECTION IN AUTONOMOUS MACHINE APPLICATIONS

Simplified Explanation

A deep neural network is trained to predict distances to objects using only image data, with ground truth data generated from depth predicting sensors. Camera adaptation algorithms are used to adapt the network for different camera parameters, and safety bounds are applied to ensure predictions fall within a safe range.

Key Features and Innovation

• Training a deep neural network to predict distances to objects using image data alone.
• Ground truth data generated and encoded using sensors like radar, lidar, and sonar.
• Camera adaptation algorithms used to adapt the network for varying camera parameters.
• Post-processing safety bounds operation to ensure predictions fall within a safety-permissible range.

Potential Applications

This technology can be applied in autonomous vehicles, robotics, surveillance systems, and augmented reality applications.

Problems Solved

• Accurate prediction of distances to objects using only image data.
• Adaptation of neural networks for different camera parameters.
• Ensuring predictions fall within a safe range for deployment.

Benefits

• Improved accuracy in predicting distances to objects.
• Versatile adaptation for different camera parameters.
• Enhanced safety measures for deployment in various applications.

Commercial Applications

This technology has potential commercial uses in the automotive industry, security systems, and virtual reality applications. It can improve the efficiency and safety of various systems that rely on object detection and distance prediction.

Questions about Deep Neural Network for Distance Prediction

How does the ground truth data impact the training of the deep neural network?

Ground truth data generated from sensors like radar, lidar, and sonar provides accurate distance information that helps train the network to make precise predictions based on image data alone.

What are the potential applications of using deep neural networks for distance prediction in various industries?

The technology can be applied in autonomous vehicles, robotics, surveillance systems, and augmented reality applications to improve object detection and distance prediction accuracy.

Original Abstract Submitted

in various examples, a deep neural network (dnn) is trained to accurately predict, in deployment, distances to objects and obstacles using image data alone. the dnn may be trained with ground truth data that is generated and encoded using sensor data from any number of depth predicting sensors, such as, without limitation, radar sensors, lidar sensors, and/or sonar sensors. camera adaptation algorithms may be used in various embodiments to adapt the dnn for use with image data generated by cameras with varying parameters—such as varying fields of view. in some examples, a post-processing safety bounds operation may be executed on the predictions of the dnn to ensure that the predictions fall within a safety-permissible range.