Autonomous Vehicle Three-Point Turn for Dead-End Navigation
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Autonomous driving vehicles lack effective systems and algorithms to navigate out of dead-ends, especially when there is not enough clearance for a traditional U-turn.
Innovation Solution
A computer-implemented method and system that allows an autonomous driving vehicle to switch from on-lane mode to open-space mode, enabling it to perform a three-point turn and navigate out of a dead-end by determining a suitable turning point and using sensor data to adjust its position and heading relative to the vehicle lane.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Adaptability or versatility
If a traditional U-turn is performed, then the vehicle can reverse direction, but sufficient road clearance is required which is not available in dead-end scenarios
Solution Approach 1:
The patent divides the single U-turn maneuver into three separate turning points, breaking down the complex motion into manageable segments that can be executed in narrow spaces. The vehicle performs a first turn at a first turning point, a second turn at a second turning point, and a third turn at a third turning point to achieve complete direction reversal without requiring wide road clearance.
Solution Approach 2:
The patent utilizes the temporal dimension by introducing multiple turning points executed at different times and positions along the road, rather than attempting a single spatial U-turn. This transforms the problem from a spatial constraint issue to a temporal sequence of maneuvers, allowing the vehicle to navigate dead-ends with limited clearance.
2Adaptability or versatility
If the vehicle remains in on-lane mode, then lane discipline is maintained, but the vehicle cannot navigate out of dead-ends requiring open-space maneuvers
Solution Approach 1:
The patent implements dynamic switching between on-lane mode and open-space mode based on the vehicle's operational context. The system automatically transitions from constrained lane-following behavior to unconstrained open-space maneuvering when detecting dead-end conditions, and returns to lane discipline after completing the three-point turn, optimizing adaptability without permanent complexity.
Solution Approach 2:
The patent creates a unified navigation system that can operate in multiple modes (on-lane mode and open-space mode) depending on situational requirements. The same autonomous vehicle control system performs both lane-disciplined cruising and dead-end rescue maneuvers, eliminating the need for separate specialized systems and reducing overall complexity.
3Area of stationary object
If multiple turning points are used instead of a single U-turn, then road clearance requirements are reduced, but the number of maneuvers and transition points increases
Solution Approach 1:
The patent changes the spatial parameters of the turning maneuver by distributing the total turning angle across three separate turning points rather than concentrating it in a single U-turn. This parameter distribution reduces the clearance requirement at any single point while maintaining the overall directional reversal function.
Data Source
Figure 1
Figure 2
Figure 3A
AI summary
In one embodiment, an autonomous driving vehicle (ADV) operates in an on-lane mode, where the ADV follows a path along a vehicle lane. In response to determining that the ADV is approaching a dead-end, the ADV switches to an open-space mode. While in the open-space mode, the ADV conducts a three-point turn using a series of steering and throttle commands to generate forward and reverse movements until the ADV is within a) a threshold heading, and b) a threshold distance, relative to the vehicle lane. The ADV can then return to the on-lane mode and resume along the vehicle lane away from the dead-end.