Adjacent-Lane Speed Management for Anticipatory Vehicle Control
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Conventional autonomous systems face challenges in safely and efficiently managing vehicle speed due to varying traffic conditions across different lanes, failing to anticipate lane changes and other traffic-related factors effectively.
Innovation Solution
The system determines traffic speeds in adjacent lanes by averaging and smoothing detected speeds, using machine learning models to generate a desired upper speed bound for the vehicle's lane based on road geometry and traffic patterns, thereby facilitating adaptive speed management.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Productivity
If the autonomous system relies on data about the vehicle and environment to plan and control motion, then the navigation function is achieved, but the performance becomes challenging when conditions change
Solution Approach 1:
The system performs preliminary actions by determining desired upper speed bounds for multiple lanes before actual lane changes occur. By analyzing traffic speeds in adjacent lanes and road geometry in advance, the system prepares speed adjustment parameters that will be needed when lane changes or traffic conditions change, enabling smoother transitions and more reliable performance.
Solution Approach 2:
The system implements dynamics by continuously adjusting speed parameters based on changing traffic conditions. The desired upper speed bound is not fixed but dynamically determined based on real-time traffic speeds in adjacent lanes, road geometry, and predicted traffic patterns, allowing the navigation performance to adapt to changing environmental conditions.
2Reliability
If the system determines traffic speeds by averaging and smoothing detected speeds, then the speed data becomes more reliable, but the system complexity increases
Solution Approach 1:
The system applies feedback mechanisms by comparing determined traffic speeds with predicted traffic speeds and using this comparison to refine the desired upper speed bound. The averaging and smoothing processes provide feedback-based filtering that improves reliability by eliminating outliers and noise, while the feedback loop continuously adjusts parameters based on actual versus predicted performance.
3Adaptability or versatility
If the system generates desired upper speed bound using machine learning models, then the speed management becomes more adaptive, but the computational requirements increase
Solution Approach 1:
The machine learning model performs preliminary action by pre-processing traffic speed data and road geometry information to generate the desired upper speed bound before it is needed for control decisions. This advance computation allows the system to adapt to changing conditions more efficiently, as the adaptive parameters are prepared in advance rather than computed in real-time during critical control moments.
4Reliability
If the system anticipates potential changes in traffic by analyzing adjacent lane speeds, then the safety is improved, but the likelihood of sudden braking or acceleration increases without proper smoothing
Solution Approach 1:
The system applies beforehand cushioning by using smoothing functions to gradually adjust the desired upper speed bound rather than making abrupt changes. This cushioning effect prevents sudden braking or acceleration by interpolating speed adjustments over time, maintaining safety through anticipatory speed management while ensuring comfortable and smooth navigation transitions.
Data Source
AI summary
Methods, systems, and non-transitory computer-readable media are configured to perform operations comprising determining first speeds of first objects in a first lane and second speeds of second objects in a second lane; determining a first speed of traffic for the first lane based on the first speeds and a second speed of traffic for the second lane based on the second speeds; and generating a speed limit for a third lane based on the first speed of traffic and the second speed of traffic.