Virtual Spring Lane Change for Autonomous Vehicles
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Autonomous vehicles face challenges in safely and efficiently changing lanes due to the need to consider dynamic driving conditions of both the current and target lanes, requiring accurate localization and complex decision-making processes.
Innovation Solution
A spring-based system is implemented, where virtual springs connect the autonomous vehicle with surrounding objects, generating forces based on relative positions, which are aggregated to determine lane-changing parameters such as speed and turning angle, using Hooke's law to decide when and how to change lanes.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If the autonomous vehicle uses complex decision-making processes to consider dynamic driving conditions of both current and target lanes, then the safety and accuracy of lane-changing is improved, but the computational complexity and processing time increase
Solution Approach 1:
The decision-making process is segmented into distinct modules: perception module for detecting surrounding objects, virtual spring generation module for creating force vectors, aggregation module for combining forces, and execution module for performing lane-changing. This modular segmentation reduces overall system complexity while maintaining comprehensive safety checks.
Solution Approach 2:
Virtual springs are introduced as intermediary elements that mediate between the vehicle and surrounding objects. These virtual springs translate complex spatial relationships and safety constraints into intuitive force vectors, simplifying the decision-making process while preserving safety considerations.
2Measurement precision
If the autonomous vehicle continuously determines lane-changing state with high accuracy localization, then the precision of lane-changing is improved, but the computational load and processing requirements increase
Solution Approach 1:
The complex mechanical-like process of continuous state determination and localization is replaced with a virtual physics-based spring system. The virtual springs automatically adjust their forces based on relative positions, eliminating the need for complex continuous state machine transitions while maintaining high localization accuracy.
3Reliability
If the autonomous vehicle considers multiple surrounding objects and their potential impacts, then the safety of lane-changing is improved, but the computational complexity of force aggregation increases
Solution Approach 1:
Multiple force vectors from different virtual springs corresponding to various surrounding objects are merged into a single aggregated force vector. This consolidation simplifies the computational process by reducing multiple individual calculations into one unified force determination, while still accounting for all surrounding objects' impacts.
Applied Scientific Principles
This section explains which scientific principles are used to turn an abstract innovation direction into a practical engineering solution.
Function Achieved in This Case
This approach enables autonomous vehicles to make informed decisions about lane changes, ensuring safety and efficiency by analyzing the potential impact of surrounding objects and determining optimal lane-changing parameters.
Implementation Method 1
each virtual spring is associated with a specific spring model to generate a force based on relative positions of an associated object and the autonomous vehicle
Data Source
Figure 1
Figure 2
Figure 3
AI summary
In one embodiment, in response to a request for changing lane, one or more objects surrounding an autonomous vehicle are perceived. For each of the perceived objects, a virtual spring is assigned to connect the object and the autonomous vehicle. Each virtual spring is associated with a specific spring model to generate a force based on relative positions of an associated object and the autonomous vehicle. One or more forces generated from one or more virtual springs corresponding to the one or more surrounding objects are aggregated to generate an aggregated force. One or more lane-changing parameters for the autonomous vehicle are determined based on the aggregated force and a direction of the aggregated force.