Autonomous Lane Change Control Using Target Space Selection
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing autonomous driving technologies face challenges in safely and efficiently making lane changes, particularly when immediate lane changes are not possible due to other vehicles, leading to potential collisions and wasted movement.
Innovation Solution
A vehicle control apparatus equipped with sensors and a processor determines the need for a lane change based on lane characteristics and driving paths, identifies other vehicles in adjacent lanes, calculates target spaces for safe entry, and adjusts vehicle speed and trajectory to execute the lane change efficiently.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If the vehicle waits for a safe gap to make a lane change, then collision risk is reduced, but lane change time is extended
Solution Approach 1:
The system performs preliminary detection of target spaces and prediction of arrival times before the actual lane change maneuver. By pre-identifying safe gaps and calculating expected arrival times at these gaps, the system prepares the lane change in advance, reducing the actual execution time while maintaining safety through pre-planned trajectories that account for the vehicle's speed and acceleration characteristics.
2Loss of time
If the vehicle accelerates to reach a target space faster, then lane change time is reduced, but collision risk increases
Solution Approach 1:
The system dynamically adjusts the vehicle's speed trajectory based on the detected target space and calculated arrival time. Rather than using fixed acceleration patterns, the control apparatus continuously adapts the speed profile to match the specific geometric and temporal constraints of each lane change scenario, optimizing the balance between reaching the target space efficiently and maintaining safe distances from other vehicles.
Solution Approach 2:
The system uses real-time feedback from sensor data about surrounding vehicles' positions and speeds to continuously update the predicted arrival time and adjust the lane change trajectory. This closed-loop control allows the vehicle to respond to changing conditions during the maneuver, reducing collision risk while maintaining optimal lane change time through adaptive trajectory modification.
3Reliability
If the vehicle checks multiple target spaces, then safety is improved, but computational complexity increases
Solution Approach 1:
The system segments the adjacent lane into multiple discrete target spaces rather than treating it as a continuous domain. By dividing the lane into specific candidate zones and evaluating each independently for safety and reachability, the system simplifies the computational problem while maintaining comprehensive safety coverage. This segmentation allows parallel processing of multiple target space evaluations without exponentially increasing complexity.
Data Source
AI summary
An apparatus for controlling a vehicle may comprise a sensor, a memory storing at least one instruction, and a processor operatively coupled to the sensor and the memory. The instruction, when executed by the processor, is configured to determine, based on a lane characteristic and a driving path of the vehicle, whether to make a lane change. The characteristic and driving path are obtained using the sensor. Upon determining to make a lane change, the sensor detects another vehicle in a second lane adjacent to the first lane. The apparatus determines at least one target space between the vehicle and the other vehicle for the lane change, selects a specified target space based on arrival times and expected speed trajectory, and controls the vehicle to enter the specified target space and make the lane change based on the vehicle's relative position to the target space satisfying a condition.