LiDAR Virtual Box Heading Correction for Autonomous Driving

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Existing vehicle control systems using LiDAR sensors often inaccurately identify the heading direction of external objects, leading to potential issues in autonomous driving.

Innovation Solution

A processor-based system that generates a first virtual box from LiDAR data, applies a designated algorithm to determine a heading confidence value, adjusts the heading direction using an angle value, and outputs a second virtual box to improve accuracy, enhancing autonomous driving control.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Difficulty of detecting and measuring

If a LiDAR sensor is used to identify external objects, then object detection capability is improved, but heading direction accuracy deteriorates

Engineering Contradiction:

Improveobject detection capabilityVSAvoidheading direction accuracy

Core Design Contradiction:

Difficulty of detecting and measuringVSMeasurement precision

Solution Approach 1:

The system calculates a loss function that measures the discrepancy between the current virtual box orientation and the optimal orientation. This loss function provides feedback that is used to iteratively adjust the virtual box heading direction until the loss is minimized, thereby improving heading direction accuracy while maintaining object detection capability

Inventive Principle:

Principle #23Feedback

Solution Approach 2:

The system generates an initial virtual box with estimated heading direction before performing the loss function optimization. This preliminary virtual box serves as a starting point that maintains object detection capability while allowing subsequent refinement to improve heading direction accuracy

Inventive Principle:

Principle #10Preliminary action

2Loss of information

If a virtual box is generated to represent object bounding box, then object identification is improved, but heading direction accuracy deteriorates

Engineering Contradiction:

Improveobject identification accuracyVSAvoidheading direction accuracy

Core Design Contradiction:

Loss of informationVSMeasurement precision

Solution Approach 1:

The loss function provides continuous feedback on the accuracy of the virtual box heading direction by comparing it against expected or optimal orientations. This feedback loop enables iterative refinement of the heading direction while preserving the virtual box's object identification function

Inventive Principle:

Principle #23Feedback

Solution Approach 2:

The system separates the object identification function (maintained by the virtual box) from the heading direction estimation function (refined by loss function optimization). This segmentation allows each function to be optimized independently, improving heading direction accuracy without compromising object identification

Inventive Principle:

Principle #1Segmentation

Data Source

PatentUS20250362409A1Apparatus for Controlling Vehicle and Method Thereof

Publication Date: 2025.11.27 HYUNDAI MOTOR CO LTD

AI summary

An apparatus for controlling autonomous driving of a vehicle is introduced. The apparatus may comprise a sensor to obtain a cluster points representing an object and a processor to generate a first virtual box corresponding to the object based on sensor data. The processor may further obtain a heading confidence value for the heading direction of the first virtual box by applying a loss function associated with a designated algorithm. This loss function indicates the algorithm's accuracy in determining the heading direction. Based on the heading confidence value, the processor may derive an angle value to adjust the heading direction, resulting in a second virtual box with the adjusted heading. A signal is generated indicating the second virtual box, and this signal may be used to control the autonomous driving of the vehicle.