Autonomous Vehicle Stationary State Detection for Lane Change Decisions
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Autonomous vehicles face challenges in distinguishing between short-term and long-term stationary vehicles, which affects their navigation and decision-making processes, particularly in determining when to change lanes or routes to avoid stationary vehicles that may remain still for extended periods.
Innovation Solution
The method involves using computing devices to detect visible indicia such as lights and map data to determine whether a stationary vehicle is in a short-term or long-term stationary state, considering factors like traffic control locations and obstructions, allowing the autonomous vehicle to adjust its control strategy accordingly.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If the autonomous vehicle uses basic detection methods to identify stationary vehicles, then the detection process is simple and fast, but the vehicle cannot distinguish between short-term and long-term stationary states, leading to inappropriate navigation decisions
Solution Approach 1:
The patent segments the stationary vehicle detection problem into multiple analysis dimensions: visible indicia detection (lights, signs), traffic control factor identification (stop signs, traffic lights, crosswalks), and duration-based classification. This segmentation allows the system to accurately distinguish between short-term and long-term stationary states by evaluating multiple independent factors rather than relying on a single complex detector.
Solution Approach 2:
The system performs preliminary detection of visible indicia and traffic control factors before making the final stationary state determination. By pre-identifying key indicators such as hazard lights, emergency vehicle lights, construction warning lights, and traffic control locations, the system prepares classification data in advance, enabling faster and more accurate stationary state classification without adding significant computational overhead during critical decision-making.
2Reliability
If the autonomous vehicle waits for a fixed predetermined period before changing determination from short-term to long-term stationary state, then the decision-making process is simple, but it may not accurately reflect the actual stationary nature of the vehicle
Solution Approach 1:
The patent implements a dynamic determination system where the stationary state classification is continuously updated based on real-time monitoring of visible indicia and traffic control factors. Rather than using a fixed predetermined waiting period, the system dynamically adjusts its determination based on the presence or absence of key indicators such as hazard lights, emergency vehicle lights, construction warning lights, and traffic control locations. This dynamic approach allows the system to reliably classify stationary states without unnecessary time delays.
3Ease of operation
If the autonomous vehicle does not distinguish between short-term and long-term stationary vehicles, then the navigation system is simpler, but the vehicle may make unsafe maneuvers or unnecessary route changes
Solution Approach 1:
The patent applies different navigation control strategies based on the locally determined stationary state of detected vehicles. When a vehicle is classified as long-term stationary (indicated by hazard lights, emergency vehicle lights, construction warning lights, or prolonged presence at traffic control locations), the autonomous vehicle executes maneuvers to change lanes or routes. When classified as short-term stationary (absent of these indicators), the system maintains current navigation plans. This localized adaptation of control strategy ensures safe and appropriate maneuvers without unnecessary complexity.
Data Source
AI summary
Aspects of the disclosure relate to an autonomous vehicle that may detect other nearby vehicles and designate stationary vehicles as being in one of a short-term stationary state or a long-term stationary state. This determination may be made based on various indicia, including visible indicia displayed by the detected vehicle and traffic control factors relating to the detected vehicle. For example, the autonomous vehicle may identify a detected vehicle as being in a long-term stationary state based on detection of hazard lights being displayed by the detected vehicle, as well as the absence of brake lights being displayed by the detected vehicle. The autonomous vehicle may then base its control strategy on the stationary state of the detected vehicle.