20240051568. DISCRIMINATOR NETWORK FOR DETECTING OUT OF OPERATIONAL DESIGN DOMAIN SCENARIOS simplified abstract (Motional AD LLC)
DISCRIMINATOR NETWORK FOR DETECTING OUT OF OPERATIONAL DESIGN DOMAIN SCENARIOS
Organization Name
Inventor(s)
Edouard Francois Marc Capellier of Singapore (SG)
DISCRIMINATOR NETWORK FOR DETECTING OUT OF OPERATIONAL DESIGN DOMAIN SCENARIOS - A simplified explanation of the abstract
This abstract first appeared for US patent application 20240051568 titled 'DISCRIMINATOR NETWORK FOR DETECTING OUT OF OPERATIONAL DESIGN DOMAIN SCENARIOS
Simplified Explanation
The patent application describes methods for detecting when a vehicle is encountering an out of operational design domain (ODD) scenario. This is achieved by training a generative adversarial network (GAN) consisting of a generator network and a discriminator network. The generator network is trained to generate synthesized scenarios, while the discriminator network is trained to distinguish between true scenarios and the synthesized scenarios generated by the generator network. The trained discriminator network is then applied to detect when a vehicle encounters an ODD scenario. Additionally, the methods include controlling the motion of the vehicle in response to the output of the trained discriminator network indicating that the vehicle is encountering an ODD scenario. Systems and computer program products are also provided.
- Methods for detecting when a vehicle encounters an out of operational design domain (ODD) scenario
- Training a generative adversarial network (GAN) with a generator network and a discriminator network
- Generator network is trained to generate synthesized scenarios
- Discriminator network is trained to distinguish between true scenarios and synthesized scenarios
- Trained discriminator network is applied to detect when a vehicle encounters an ODD scenario
- Controlling the motion of the vehicle based on the output of the trained discriminator network
- Systems and computer program products are provided
Potential applications of this technology:
- Autonomous vehicles: Detecting and responding to ODD scenarios can enhance the safety and performance of autonomous vehicles.
- Vehicle testing: The synthesized scenarios can be used to simulate various ODD scenarios for testing and validation purposes.
- Driver training: The technology can be used to create simulated ODD scenarios for training drivers in handling challenging situations.
Problems solved by this technology:
- Detection of ODD scenarios: The technology provides a method for accurately detecting when a vehicle encounters an ODD scenario, which can help prevent accidents and improve safety.
- Motion control in response to ODD scenarios: The technology enables the vehicle to autonomously adjust its motion in real-time based on the detection of an ODD scenario, improving the vehicle's ability to navigate challenging situations.
Benefits of this technology:
- Improved safety: By detecting and responding to ODD scenarios, the technology can help prevent accidents and reduce the risk of collisions.
- Enhanced performance: The ability to detect and adapt to ODD scenarios can improve the performance and capabilities of autonomous vehicles.
- Cost-effective testing: The synthesized scenarios can provide a cost-effective way to simulate and test various ODD scenarios without the need for physical prototypes or real-world testing.
Original Abstract Submitted
provided are methods for detecting when a vehicle is encountering an out of operational design domain (odd) scenario, which can include training a generative adversarial network (gan) including a generator network and a discriminator network. the generator network may be trained to generate synthesized scenarios. the discriminator network may be trained to distinguish between true scenarios and the synthesized scenarios generated by the generator network. the trained discriminator network may be applied to detect when a vehicle encounters an out of operational design domain (odd) scenario. some methods described also include controlling the motion of the vehicle in response to an output of the trained discriminator network indicating that the vehicle is encountering the out of operational design domain (odd) scenario. systems and computer program products are also provided.