Nvidia corporation (20240211748). DETERMINING OBJECT ASSOCIATIONS USING MACHINE LEARNING IN AUTONOMOUS SYSTEMS AND APPLICATIONS simplified abstract
Contents
DETERMINING OBJECT ASSOCIATIONS USING MACHINE LEARNING IN AUTONOMOUS SYSTEMS AND APPLICATIONS
Organization Name
Inventor(s)
Neeraj Sajjan of Sunnyvale CA (US)
Mehmet Kocamaz of San Jose CA (US)
Parthiv Parikh of Santa Clara CA (US)
DETERMINING OBJECT ASSOCIATIONS USING MACHINE LEARNING IN AUTONOMOUS SYSTEMS AND APPLICATIONS - A simplified explanation of the abstract
This abstract first appeared for US patent application 20240211748 titled 'DETERMINING OBJECT ASSOCIATIONS USING MACHINE LEARNING IN AUTONOMOUS SYSTEMS AND APPLICATIONS
Simplified Explanation: The patent application discusses systems and methods for determining associations between objects in sensor data and predicted states of the objects in multi-sensor systems like autonomous vehicles. These systems use neural network models to learn association costs between sensor measurements and predicted object states.
- Neural network models, such as multi-layer perceptron (MLP) or deep neural network (DNN) models, are employed in learning association costs between sensor measurements and predicted states of objects.
- During training, data is generated to update parameters of the neural network models.
- The neural network models can then receive sensor data and predicted states during deployment and provide corresponding association costs.
Potential Applications: 1. Autonomous vehicle perception systems. 2. Robotics for object recognition and tracking. 3. Surveillance systems for monitoring and analyzing object movements.
Problems Solved: 1. Enhancing object recognition accuracy in multi-sensor systems. 2. Improving the efficiency of associating sensor data with predicted object states. 3. Streamlining the process of updating neural network model parameters.
Benefits: 1. Increased accuracy in predicting object states. 2. Enhanced performance of autonomous systems. 3. Improved decision-making capabilities based on sensor data.
Commercial Applications: Title: Advanced Object Association Technology for Autonomous Vehicles This technology can be utilized in the development of autonomous vehicles, robotics, and surveillance systems. It has the potential to revolutionize object recognition and tracking in various industries, leading to safer and more efficient operations.
Questions about Object Association Technology: 1. How does this technology improve the efficiency of object recognition in autonomous vehicles?
- The technology utilizes neural network models to learn association costs between sensor measurements and predicted object states, enhancing the accuracy of object recognition.
2. What are the potential applications of this technology beyond autonomous vehicles?
- This technology can be applied in robotics for object tracking and surveillance systems for monitoring and analyzing object movements in various industries.
Original Abstract Submitted
in various examples, systems and methods are disclosed relating to determining associations between objects represented in sensor data and predicted states of the objects in multi-sensor systems such as autonomous or semi-autonomous vehicle perception systems. systems and methods are disclosed that employ neural network models, such as multi-layer perceptron (mlp) models or other deep neural network (dnn) models, in learning association costs between sensor measurements and predicted states of objects. during training, the systems and methods can generate data for updating parameters of the neural network models such that, during deployment, the neural network models can receive sensor data and predicted states, and provide corresponding association costs.
