17945952. AUTONOMOUS VEHICLE SENSOR CALIBRATION ALGORITHM EVALUATION simplified abstract (GM Cruise Holdings LLC)

From WikiPatents
Jump to navigation Jump to search

AUTONOMOUS VEHICLE SENSOR CALIBRATION ALGORITHM EVALUATION

Organization Name

GM Cruise Holdings LLC

Inventor(s)

Annett Bordoley of Seattle WA (US)

Ankit Rohatgi of Pacifica CA (US)

Zhonghua Ma of San Jose CA (US)

AUTONOMOUS VEHICLE SENSOR CALIBRATION ALGORITHM EVALUATION - A simplified explanation of the abstract

This abstract first appeared for US patent application 17945952 titled 'AUTONOMOUS VEHICLE SENSOR CALIBRATION ALGORITHM EVALUATION

Simplified Explanation

The disclosed technology involves evaluating sensor calibration algorithms, specifically in autonomous vehicle deployments. The process includes determining calibration parameters for a sensor on an AV, injecting faults to determine offsets in the calibration parameters, and modifying the parameters based on the fault offsets. Sensor data is collected and used to evaluate the calibration algorithm based on the fault offsets and data.

  • Determining calibration parameters for a sensor on an autonomous vehicle
  • Injecting faults to determine offsets in the calibration parameters
  • Modifying calibration parameters based on fault offsets
  • Collecting sensor data to evaluate the calibration algorithm
  • Improving sensor calibration in autonomous vehicle deployments

Potential Applications

The technology can be applied in various industries such as automotive, robotics, and industrial automation for enhancing sensor calibration processes.

Problems Solved

1. Ensures accurate sensor calibration in autonomous vehicles 2. Improves the reliability and performance of sensor data in AV deployments

Benefits

1. Enhances the safety and efficiency of autonomous vehicles 2. Reduces the risk of sensor malfunctions and inaccuracies

Potential Commercial Applications

Optimizing sensor calibration in autonomous vehicles for improved performance and safety

Possible Prior Art

Prior art related to sensor calibration algorithms in autonomous vehicles may include research papers, patents, or industry standards that address similar challenges in sensor calibration processes.

Unanswered Questions

How does this technology compare to existing sensor calibration methods in terms of accuracy and efficiency?

The article does not provide a direct comparison between this technology and existing sensor calibration methods.

What are the potential limitations or challenges of implementing this technology in real-world autonomous vehicle systems?

The article does not address potential limitations or challenges that may arise when implementing this technology in practical AV deployments.


Original Abstract Submitted

The disclosed technology provides solutions for evaluating sensor calibration algorithms and in particular, for evaluating calibration mechanisms used in autonomous vehicle (AV) deployments. The disclosed technology encompasses a process that includes steps for determining calibration parameters for a sensor mounted to an autonomous vehicle (AV), determining a fault injection offset for at least one of the one or more calibration parameters, and modifying at least one of the one or more calibration parameters based on the fault injection offset. The process may additionally include steps for collecting sensor data from the sensor and evaluating a calibration algorithm associated with the sensor based on the fault injection offset and sensor data. Systems and machine-readable media are also provided.