Autonomous Driving Path Offsets for Occlusion-Aware Sensing

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Autonomous vehicles face challenges in determining a driving plan effectively due to limited sensing ranges caused by obstacles, which restricts the collection of surrounding environment information and hinders the determination of risk levels in occluded regions.

Innovation Solution

An electronic device equipped with sensors generates a driving plan by determining a target position offset based on sensing range evaluations, allowing the vehicle to adjust its path to maximize the available sensing region and secure an optimal field of view for the sensors.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Reliability

If the vehicle follows a straight driving path, then the control is simple and stable, but the sensing range is limited due to occlusions by obstacles

Engineering Contradiction:
Improvesensing rangeVSAvoiddriving plan complexity
Core Design Contradiction:
ReliabilityVSDevice complexity

Solution Approach 1:

The driving plan is made dynamic by introducing position offsets that adjust the vehicle's path in real-time based on obstacle detection. Instead of following a fixed straight trajectory, the vehicle dynamically modifies its position relative to the original path to maintain optimal sensing coverage while navigating around occluding obstacles.

Inventive Principle:
Principle #15Dynamics

Solution Approach 2:

The system performs preliminary sensing range evaluation to predict potential occlusions before they occur. By evaluating the sensing range in advance and planning position offsets proactively, the vehicle prepares alternative paths that prevent sensing losses rather than reacting after occlusions happen.

Inventive Principle:
Principle #10Preliminary action

2Loss of information

If the vehicle adjusts its path to avoid occlusions, then the sensing range is improved, but the driving control becomes more complex

Engineering Contradiction:
Improvesurrounding environment informationVSAvoiddriving control
Core Design Contradiction:
Loss of informationVSEase of operation

Solution Approach 1:

The system changes the path position parameter by introducing offset values that shift the vehicle's trajectory. Instead of complex navigation algorithms, the solution modifies the position parameter relative to the original path, making the control adjustment mathematically simple while effectively avoiding occlusions and maintaining sensing coverage.

Inventive Principle:
Principle #35Parameter changes

Solution Approach 2:

The driving plan incorporates feedback mechanisms where the vehicle continuously evaluates sensing range and adjusts position offsets based on detected occlusions. This closed-loop control ensures that path adjustments are made only when necessary and are optimized to maintain maximum sensing coverage with minimal control complexity.

Inventive Principle:
Principle #23Feedback

3Illumination intensity

If the vehicle maintains a fixed driving path, then the control is simple, but the field of view for sensors is restricted

Engineering Contradiction:
Improvefield of viewVSAvoidpath determination complexity
Core Design Contradiction:
Illumination intensityVSDevice complexity

Solution Approach 1:

The solution adds a dimensional offset to the original two-dimensional path planning by introducing a position offset parameter that creates a three-dimensional solution space. This allows the vehicle to maintain simplicity in the base path while adding vertical adjustment capability to optimize sensor field of view without fundamentally complicating the path determination system.

Inventive Principle:
Principle #17Another dimension (Dimensionality change)

Data Source

PatentEP4371835B1Method and device with autonomous driving plan
Publication Date: 2025.04.23 SAMSUNG ELECTRONICS CO LTD
  • EP4371835B1 patent drawingFigure 1
  • EP4371835B1 patent drawingFigure 2
  • EP4371835B1 patent drawingFigure 3

AI summary

An electronic device and method for more accurate autonomous driving, where the electronic device includes a sensor disposed in a moving object and configured to generate sensing data, and a processor configured to determine a predicted position of the moving object and a region of interest (ROI) based on a driving plan of the moving object, select a target position offset based on an available sensing region of the sensor in the ROI and the predicted position, and update the driving plan of the moving object based on the target position offset.