Autonomous Vehicle Path Planning Using Vehicle-Type Risk Assessment
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current autonomous vehicle technologies face challenges in effectively perceiving and responding to various types of nearby vehicles, particularly in complex road situations, due to limitations in sensor-based and connection-based perception methods, which affect safe path planning and maneuvering.
Innovation Solution
A method and device for planning a traveling path of an autonomous vehicle by detecting nearby vehicles using sensors and V2X technology, determining risks based on vehicle type, and adjusting the path to maintain safety distances, change lanes, or adjust speed to mitigate potential collisions.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If sensor-based perception technology is used to detect nearby vehicles, then the vehicle can perceive the external environment, but the measurement precision and reliability are insufficient in complex road situations
Solution Approach 1:
The patent combines sensor-based perception (ultrasonic sensors, cameras, radars, lidars) with connection-based perception (V2X communication technology) to create a fused perception system. This merging allows the vehicle to receive both direct sensor data and indirect information from other vehicles and infrastructure, significantly improving detection accuracy and reliability in complex scenarios where single methods fail.
Solution Approach 2:
The perception system is designed to handle multiple types of targets (vehicles, pedestrians, infrastructure) and multiple detection modes (sensor-based and connection-based) through a unified architecture. The risk determination unit universally processes information from various sources to assess risks from different target types, making the system adaptable to diverse road situations.
2Loss of information
If connection-based V2X perception technology is used to communicate with surrounding vehicles, then information such as position, distance, and speed can be shared, but the system complexity increases
Solution Approach 1:
The patent introduces a risk determination unit that acts as an intermediary between the V2X communication module and the path planning module. This intermediary processes and filters the raw information from V2X communication, translating it into risk assessments that the path planning system can use directly. This mediation simplifies the overall system architecture by providing a clear interface between information gathering and decision-making components.
Solution Approach 2:
The perception and decision-making system is segmented into distinct functional units: sensor modules, V2X communication module, risk determination unit, and path planning unit. Each unit has a specific responsibility, which reduces system complexity by allowing independent development, testing, and optimization of each component while maintaining clear data flow between them.
3Reliability
If the vehicle maintains large safety distances from all nearby vehicles to ensure safety, then collision risk is reduced, but the traveling efficiency and productivity decrease
Solution Approach 1:
The risk determination unit assesses risks differently for different nearby vehicles based on their specific characteristics (type, speed, distance, behavior patterns). Instead of applying a uniform large safety distance to all vehicles, the system dynamically adjusts safety margins locally for each target. This allows the vehicle to maintain larger distances from high-risk targets while reducing distances from low-risk targets, thereby improving overall traveling efficiency while maintaining safety.
Solution Approach 2:
The safety distance is not a fixed parameter but dynamically adjusted based on real-time risk assessments. The path planning unit continuously updates safety margins as the vehicle's environment changes, allowing the vehicle to optimize its trajectory by reducing unnecessary safety buffers when risks are low, thus improving productivity while maintaining reliability when risks are high.
4Reliability
If the vehicle frequently changes lanes to avoid nearby vehicles, then collision avoidance is improved, but the stability of the traveling path deteriorates
Solution Approach 1:
The risk determination unit performs preliminary risk assessment before the path planning unit generates avoidance maneuvers. By evaluating the risk level of nearby vehicles in advance, the system can determine whether lane changes are truly necessary or if other adjustments (speed changes, distance adjustments) would suffice. This preliminary action prevents unnecessary lane changes that would disrupt path stability while still ensuring collision avoidance when risks are genuine.
Solution Approach 2:
The path planning system incorporates feedback from continuous risk assessments to adjust its maneuvers. After each lane change or path adjustment, the system re-evaluates the risk landscape and only makes further changes if new risks are detected. This feedback mechanism ensures that lane changes are made purposefully and minimally, maintaining path stability while achieving collision avoidance goals.
Data Source
Figure 1
Figure 2~3
Figure 4
AI summary
Provided is a method including detecting at least one external vehicle located within a predetermined distance from a first vehicle using at least one sensor; determining a risk due to the at least one external vehicle based on a type of the at least one external vehicle; and planning a traveling path of the first vehicle based on the risk due to the at least one external vehicle.