Autonomous Vehicle Three-Point Turn Path Planning
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
There is a lack of efficient methods for planning and controlling autonomous driving vehicles to perform a three-point turn, which is complex due to the need for precise navigation and angle calculations.
Innovation Solution
A computer-implemented method generates sets of forward and backward turning paths based on maximum turning angles, calculates path costs using a predetermined cost function, and selects the path with the lowest cost to execute a three-point turn, ensuring smooth and accurate vehicle navigation.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Productivity
If traditional path planning methods are used for three-point turns, then the vehicle can complete the maneuver, but the planning process becomes complicated and inefficient
Solution Approach 1:
The patent segments the three-point turn path planning into distinct components: forward turning paths, backward turning paths, and lane entry paths. Each segment is generated independently based on specific constraints (maximum turning angles, lane boundaries), then combined to form complete path candidates. This segmentation simplifies the overall planning complexity while maintaining planning efficiency.
2Measurement precision
If multiple path candidates are generated and evaluated, then navigation accuracy improves, but computational time and processing complexity increase
Solution Approach 1:
The patent applies preliminary action by pre-defining constraints and cost functions before path generation. Maximum forward and backward turning angles are predetermined, lane boundaries are pre-identified, and a cost function incorporating multiple navigation criteria is pre-established. This allows rapid evaluation of path candidates without complex real-time calculations, improving navigation accuracy while reducing computational time.
3Ease of operation
If the vehicle follows a direct turning path, then the maneuver is simpler, but the vehicle cannot achieve proper alignment with the target lane
Solution Approach 1:
The patent divides the turning maneuver into three distinct path segments: forward turning to reach the boundary, backward turning to reposition, and forward movement to enter the target lane. This segmentation allows each segment to be optimized independently for both simplicity and precision, achieving proper lane alignment while maintaining operational simplicity through systematic path construction.
Data Source
AI summary
According to one embodiment, in response to a request for a three-point turn, a set of forward turning paths is generated based on a maximum forward turning angle associated with an ADV. A set of backward tuning paths is generated based on a maximum backward turning angle associated with the ADV. A set of three-point turn path candidates is generated based on the forward turning paths and the backward turning paths. For each of the three-point turn path candidates, a path cost is calculated using a predetermined cost function. One of the three-point turn path candidates with the lowest path cost is selected as the final three-point turn path to drive the ADV to make a three-point turn.