Autonomous Vehicle Three-Point Turn Obstacle Adaptation
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing methods for performing a three-point turn in autonomous driving vehicles are inefficient, particularly in complex scenarios with obstacles, as they rely on rule-based parameters and lack effective speed management during turn sections.
Innovation Solution
The system determines the type and motion of obstacles within a predetermined proximity and calculates the wait time based on obstacle factors, using preconfigured expected wait time curves to decide when to end one turn section and start another, optimizing the three-point turn process.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Adaptability or versatility
If rule-based methods with specific parameters are used for three-point turn, then the control logic is simple, but the system cannot efficiently handle complex scenarios with many obstacles
Solution Approach 1:
The three-point turn process is divided into multiple turn sections (first turn section, second turn section, third turn section), each with specific entry conditions and exit conditions. This segmentation allows the system to handle complex scenarios by breaking them down into manageable discrete steps with clear decision points.
Solution Approach 2:
The system dynamically adjusts the three-point turn execution based on real-time obstacle detection and classification. Different obstacle types (pedestrian, vehicle, bicycle) trigger different time thresholds and wait times, making the control system adaptive rather than static. The speed threshold and wait time parameters are dynamically determined based on obstacle factors.
2Productivity
If the vehicle moves quickly through turn sections, then productivity is improved, but safety is compromised when obstacles are present
Solution Approach 1:
The system continuously monitors vehicle speed, obstacle presence, and turn section progress to determine when to end one turn section and start another. The exit conditions for each turn section include checking if vehicle speed is below a threshold and if the vehicle has traveled a predetermined distance, providing feedback-based control that balances speed and safety.
Solution Approach 2:
The system determines obstacle types and calculates appropriate wait times before executing turn sections. By pre-determining the appropriate time thresholds based on obstacle classification, the system prepares safety parameters in advance, allowing quick execution when safe while preventing accidents when obstacles are present.
3Reliability
If the vehicle waits longer for obstacles to clear, then safety is improved, but the time to complete the three-point turn increases
Solution Approach 1:
The system changes the time threshold parameter based on the type of obstacle detected. Different obstacle types (pedestrian, vehicle, bicycle) have different associated time thresholds, allowing the system to wait appropriately for each obstacle type without using a conservative fixed wait time for all scenarios. This optimizes the balance between safety and efficiency.
Data Source
AI summary
In one embodiment, it is determined that a speed of an autonomous driving vehicle (ADV) is below a predetermined speed threshold during a current turn section of a three-point turn, where the three-point turn includes at least three turn sections. In response, detecting an obstacle within a predetermined proximity of the ADV, determining a type of obstacle. An amount of time during which the speed of the ADV remains below the predetermined speed threshold is determined. It is determined whether the amount of time is greater than a time threshold corresponding to the type of the obstacle. If the amount of time is greater than the time threshold, the current turn section is ended and a next turn section is started.