18051114. ALLOCATING RESPONSIBILITY FOR AUTONOMOUS AND SEMI-AUTONOMOUS MACHINE INTERACTIONS AND APPLICATIONS simplified abstract (NVIDIA Corporation)
Contents
- 1 ALLOCATING RESPONSIBILITY FOR AUTONOMOUS AND SEMI-AUTONOMOUS MACHINE INTERACTIONS AND APPLICATIONS
- 1.1 Organization Name
- 1.2 Inventor(s)
- 1.3 ALLOCATING RESPONSIBILITY FOR AUTONOMOUS AND SEMI-AUTONOMOUS MACHINE INTERACTIONS AND APPLICATIONS - A simplified explanation of the abstract
- 1.4 Simplified Explanation
- 1.5 Potential Applications
- 1.6 Problems Solved
- 1.7 Benefits
- 1.8 Potential Commercial Applications
- 1.9 Possible Prior Art
- 1.10 Unanswered Questions
- 1.11 Original Abstract Submitted
ALLOCATING RESPONSIBILITY FOR AUTONOMOUS AND SEMI-AUTONOMOUS MACHINE INTERACTIONS AND APPLICATIONS
Organization Name
Inventor(s)
Ryan Cosner of Altadena CA (US)
Karen Yan Ming Leung of Los Altos CA (US)
Marco Pavone of Stanford CA (US)
ALLOCATING RESPONSIBILITY FOR AUTONOMOUS AND SEMI-AUTONOMOUS MACHINE INTERACTIONS AND APPLICATIONS - A simplified explanation of the abstract
This abstract first appeared for US patent application 18051114 titled 'ALLOCATING RESPONSIBILITY FOR AUTONOMOUS AND SEMI-AUTONOMOUS MACHINE INTERACTIONS AND APPLICATIONS
Simplified Explanation
The abstract describes a patent application related to training neural networks to generate outputs indicating estimated levels of responsibilities associated with interactions between vehicles or machines and other objects. The neural networks are trained using real-world data representing scenes depicting actual interactions between vehicles and objects, and the vehicles can use the outputs to determine controls for navigating.
- Neural networks are trained to estimate levels of responsibilities in interactions between vehicles or machines and other objects.
- Real-world data, such as scenes depicting interactions and parameters associated with them, is used to train the neural networks.
- Vehicles, such as autonomous vehicles, can use the neural network outputs to determine controls for navigating interactions.
Potential Applications
This technology could be applied in various industries, including autonomous vehicles, robotics, and industrial automation.
Problems Solved
This technology helps vehicles and machines navigate interactions with other objects more effectively and safely by estimating levels of responsibility.
Benefits
The benefits of this technology include improved safety, efficiency, and decision-making in various machine interactions.
Potential Commercial Applications
Commercial applications of this technology could include autonomous vehicle systems, industrial automation solutions, and robotics platforms.
Possible Prior Art
One possible prior art could be the use of machine learning algorithms to improve decision-making in autonomous vehicles or robotics systems.
Unanswered Questions
How does the neural network determine the estimated levels of responsibility in interactions?
The abstract does not provide specific details on the methodology used by the neural network to estimate responsibility levels.
What types of controls can vehicles determine based on the neural network outputs?
The abstract does not mention the specific controls that vehicles can determine for navigating interactions based on the neural network outputs.
Original Abstract Submitted
In various examples, learning responsibility allocations for machine interactions is described herein. Systems and methods are disclosed that train a neural network(s) to generate outputs indicating estimated levels of responsibilities associated with interactions between vehicles or machines and other objects (e.g., other vehicles, machines, pedestrians, animals, etc.). In some examples, the neural network(s) is trained using real-world data, such as data representing scenes depicting actual interactions between vehicles and objects and/or parameters (e.g., velocities, positions, directions, etc.) associated with the interactions. Then, in practice, a vehicle (e.g., an autonomous vehicle, a semi-autonomous vehicle, etc.) may use the neural network(s) to generate an output indicating a proposed or estimated level of responsibility associated with an interaction between the vehicle and an object. The vehicle may then use the output to determine one or more controls for the vehicle to use when navigating.