Nvidia corporation (20240135173). 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 20240135173 titled 'DISTANCE TO OBSTACLE DETECTION IN AUTONOMOUS MACHINE APPLICATIONS

Simplified Explanation

The abstract describes a patent application related to training a deep neural network to predict distances to objects and obstacles using image data alone, with the network being trained with ground truth data generated from depth predicting sensors. Camera adaptation algorithms and safety bounds operations are also mentioned.

• Deep neural network trained to predict distances using image data
• Ground truth data generated from depth predicting sensors
• Camera adaptation algorithms used to adapt the network for different camera parameters
• Safety bounds operation executed on predictions to ensure safety-permissible range

Potential Applications

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

Problems Solved

This technology solves the problem of accurately predicting distances to objects and obstacles using only image data, without the need for additional sensors.

Benefits

The benefits of this technology include improved accuracy in distance prediction, reduced reliance on additional sensors, and enhanced safety in various applications.

Potential Commercial Applications

Potential commercial applications of this technology include autonomous vehicles, security systems, industrial automation, and virtual reality platforms.

Possible Prior Art

One possible prior art could be the use of machine learning algorithms in combination with depth sensors for object detection and distance estimation in various applications.

How does the camera adaptation algorithm work to adjust the deep neural network for different camera parameters?

The camera adaptation algorithm likely involves adjusting the network's weights and biases based on the specific parameters of the camera, such as field of view and resolution. Further details on the specific mechanisms and algorithms used for this adaptation process would provide a clearer understanding of its functionality.

What safety measures are implemented in the post-processing safety bounds operation to ensure predictions fall within a safety-permissible range?

Details on the specific criteria and thresholds used in the safety bounds operation, as well as any additional checks or validations performed on the predictions, would be helpful in understanding how the system ensures safety in deployment scenarios.

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.