18067798. MACHINE LEARNING BASED OCCUPANCY GRID GENERATION simplified abstract (QUALCOMM Incorporated)

MACHINE LEARNING BASED OCCUPANCY GRID GENERATION

Organization Name

QUALCOMM Incorporated

Inventor(s)

Volodimir Slobodyanyuk of San Diego CA (US)

Radhika Dilip Gowaikar of San Diego CA (US)

Makesh Pravin John Wilson of San Diego CA (US)

Shantanu Chaisson Sanyal of San Diego CA (US)

Avdhut Joshi of San Marcos CA (US)

Christopher Brunner of San Diego CA (US)

Behnaz Rezaei of San Diego CA (US)

Amin Ansari of Federal Way WA (US)

MACHINE LEARNING BASED OCCUPANCY GRID GENERATION - A simplified explanation of the abstract

This abstract first appeared for US patent application 18067798 titled 'MACHINE LEARNING BASED OCCUPANCY GRID GENERATION

Simplified Explanation: The patent application describes a device that can aggregate sensor data associated with a vehicle and a set of frames to generate an aggregated frame with cells labeled as occupied or unoccupied. The device then uses this data to train a machine learning model to create an occupancy grid, focusing on specific cells with occupancy labels.

Key Features and Innovation:

• Device aggregates sensor data from a vehicle and frames to create an aggregated frame.
• Cells in the aggregated frame are labeled as occupied or unoccupied.
• Machine learning model is trained to generate an occupancy grid based on specific cells with occupancy labels.

Potential Applications: This technology could be used in autonomous vehicles, traffic management systems, and parking assistance systems.

Problems Solved: The technology addresses the need for accurate occupancy detection in various applications, improving efficiency and safety.

Benefits:

• Enhanced accuracy in occupancy detection.
• Improved performance of autonomous systems.
• Increased efficiency in traffic management.

Commercial Applications: Potential commercial applications include autonomous vehicle technology, smart city infrastructure, and transportation management systems.

Prior Art: Prior art related to this technology may include research on sensor fusion in autonomous vehicles and machine learning models for occupancy detection.

Frequently Updated Research: Researchers are continually exploring advancements in sensor technology and machine learning algorithms for improved occupancy detection in various applications.

Questions about Occupancy Detection: 1. How does this technology improve the accuracy of occupancy detection compared to traditional methods? 2. What are the potential challenges in implementing this technology in real-world scenarios?

Original Abstract Submitted

In some aspects, a device may receive sensor data associated with a vehicle and a set of frames. The device may aggregate, using a first pose, the sensor data associated with the set of frames to generate an aggregated frame, wherein the aggregated frame is associated with a set of cells. The device may obtain an indication of a respective occupancy label for each cell from the set of cells, wherein the respective occupancy label includes a first occupancy label or a second occupancy label, and wherein a subset of cells from the set of cells are associated with the first occupancy label. The device may train, using data associated with the aggregated frame, a machine learning model to generate an occupancy grid, based on a loss function that only calculates a loss for respective cells from the subset of cells. Numerous other aspects are described.