Autonomous Vehicle Blind-Spot Detection With Dynamic Sensor Priority
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Autonomous vehicles face challenges in accurately recognizing target vehicles in blind spots due to intermittent diffused reflections from driving and parking environments, leading to potential collisions and errors in position and heading angle recognition.
Innovation Solution
The method involves using a combination of a camera and a blind spot radar sensor to recognize target vehicles, with the processor determining the priority of each sensor based on the driving environment to enhance recognition accuracy.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Device complexity
If only a blind spot radar sensor is used to recognize target vehicles, then the device complexity is reduced, but the measurement precision and reliability deteriorate due to intermittent diffused reflections in certain driving environments
Solution Approach 1:
The patent combines multiple types of sensors (radar sensor, camera, and optionally lidar) into an integrated sensing system. The processor fuses data from these different sensor types to recognize target vehicles, lane lines, and road environments, thereby overcoming the limitations of any single sensor type in specific driving conditions.
Solution Approach 2:
The patent implements a multi-functional sensing system where the same sensor suite (radar, camera, lidar) is used for multiple purposes: target vehicle recognition, lane line detection, road environment assessment, and positioning. This universal approach allows the system to adapt to various driving environments without requiring environment-specific hardware.
2Reliability
If multiple sensors with varying priorities are used to recognize target vehicles, then the measurement precision and robustness improve, but the device complexity and computational load increase
Solution Approach 1:
The patent implements dynamic sensor priority adjustment based on the detected driving environment. The processor varies the priorities of different sensors according to environmental conditions (e.g., giving higher priority to radar in heavy rain, or camera in good visibility). This dynamic adaptation optimizes system performance without requiring all sensors to operate at maximum capacity simultaneously.
Solution Approach 2:
The patent changes operational parameters (sensor priorities, determination weights) based on environmental conditions. The processor adjusts the weight given to each sensor's data depending on the driving environment, such as increasing radar weight in heavy rain or snow conditions where camera performance degrades, thereby maintaining reliable target recognition across varying conditions.
3Measurement precision
If sensor priorities are varied based on driving environment, then the measurement precision improves in adverse conditions, but the computational complexity and processing time increase
Solution Approach 1:
The patent performs preliminary environmental assessment using the sensor network to classify the current driving environment (e.g., heavy rain, snow, fog, good visibility) before proceeding with target vehicle recognition. This preliminary classification allows the system to pre-select appropriate sensor priorities and processing parameters, avoiding the need for complex real-time adjustments during target recognition.
Solution Approach 2:
The patent implements a feedback loop where the processor continuously monitors sensor data quality and environmental conditions, adjusts sensor priorities accordingly, and validates recognition results. This feedback mechanism ensures that the system adapts to changing conditions while maintaining efficient processing by only adjusting parameters when necessary.
Applied Scientific Principles
This section explains which scientific principles are used to turn an abstract innovation direction into a practical engineering solution.
Function Achieved in This Case
This approach improves the robustness of autonomous driving functions by accurately recognizing target vehicles in various environments, reducing false warnings and improving positional accuracy, thereby enhancing safety and operational efficiency.
Implementation Method 1
a side and rear radar sensor (or a blind spot radar sensor)
Implementation Method 2
using a camera configured to recognize the rear and sides
Data Source
AI summary
A method of controlling an autonomous vehicle, according to an embodiment of the present disclosure, can be under control of the processor, and can include determining whether an actual lane line of a driving road is recognized by receiving sensing information from a plurality of sensors on the autonomous vehicle, initially recognizing a target vehicle driving behind the autonomous vehicle and on another lane based on a result of the determining, and secondly recognizing the target vehicle by varying priorities of the plurality of sensors based on an environment of the driving road on which the initially recognized target vehicle is driving.