Nvidia corporation (20240320986). ASSIGNING OBSTACLES TO LANES USING NEURAL NETWORKS FOR AUTONOMOUS MACHINE APPLICATIONS simplified abstract

From WikiPatents
Revision as of 08:16, 26 September 2024 by Wikipatents (talk | contribs) (Creating a new page)
(diff) ← Older revision | Latest revision (diff) | Newer revision → (diff)
Jump to navigation Jump to search

ASSIGNING OBSTACLES TO LANES USING NEURAL NETWORKS FOR AUTONOMOUS MACHINE APPLICATIONS

Organization Name

nvidia corporation

Inventor(s)

Mehmet Kocamaz of Santa Clara CA (US)

Neeraj Sajjan of Santa Clara CA (US)

Sangmin Oh of San Jose CA (US)

David Nister of Bellevue WA (US)

Junghyun Kwon of Santa Clara CA (US)

Minwoo Park of Santa Clara CA (US)

ASSIGNING OBSTACLES TO LANES USING NEURAL NETWORKS FOR AUTONOMOUS MACHINE APPLICATIONS - A simplified explanation of the abstract

This abstract first appeared for US patent application 20240320986 titled 'ASSIGNING OBSTACLES TO LANES USING NEURAL NETWORKS FOR AUTONOMOUS MACHINE APPLICATIONS

The abstract of the patent application describes how live perception from sensors of an ego-machine can be used to detect objects and assign them to bounded regions in real-time or near real-time.

  • Deep neural networks (DNN) are trained to compute outputs such as segmentation masks for object classification and lane identification.
  • Output masks are post-processed to determine object to lane assignments, aiding autonomous or semi-autonomous machines in their environment.

Potential Applications: - Autonomous driving systems - Robotics - Surveillance systems

Problems Solved: - Real-time object detection and lane assignment - Enhancing the capabilities of autonomous machines

Benefits: - Improved safety on the road - Enhanced efficiency in machine operations - Reduced human intervention in certain tasks

Commercial Applications: Title: "Advanced Object Detection and Lane Assignment Technology for Autonomous Machines" This technology can be utilized in the development of autonomous vehicles, industrial robots, and security systems, leading to increased safety and productivity in various industries.

Questions about the technology: 1. How does this technology improve the efficiency of autonomous machines? - This technology enhances the real-time perception capabilities of machines, allowing them to detect objects and assign them to specific lanes, leading to smoother operations and improved safety. 2. What are the potential challenges in implementing this technology in real-world applications? - Some challenges may include the need for robust sensor systems and the integration of complex algorithms into existing machine systems.


Original Abstract Submitted

in various examples, live perception from sensors of an ego-machine may be leveraged to detect objects and assign the objects to bounded regions (e.g., lanes or a roadway) in an environment of the ego-machine in real-time or near real-time. for example, a deep neural network (dnn) may be trained to compute outputs—such as output segmentation masks—that may correspond to a combination of object classification and lane identifiers. the output masks may be post-processed to determine object to lane assignments that assign detected objects to lanes in order to aid an autonomous or semi-autonomous machine in a surrounding environment.