Lead Vehicle Prediction for Route-Aware Ego Velocity Control
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing vehicle optimization systems fail to adequately consider the granular effects of surrounding vehicles, particularly lead vehicles, and ego vehicle driver behavior, which limits the optimization of fuel consumption, emissions, and vehicle performance.
Innovation Solution
A predictive model that includes a velocity profile generator and cruise controller to estimate lead vehicle and ego vehicle behavior, using navigation data and vehicle measurements to adjust velocity setpoints and generate optimized velocity profiles for powertrain control.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Use of energy by moving object
If complex analyses are performed to determine optimal velocities for fuel consumption and emissions reduction, then energy efficiency is improved, but computational complexity and processing time increase
Solution Approach 1:
The system performs preliminary actions by obtaining preview information from the navigation system about upcoming route conditions before making velocity decisions. This allows the controller to pre-calculate optimal velocity profiles based on known future conditions (road grade, curvature, speed limits) rather than reacting in real-time, reducing computational complexity during actual vehicle operation while maintaining fuel efficiency optimization
Solution Approach 2:
The system dynamically adjusts velocity setpoints based on predicted lead vehicle behavior and upcoming route conditions. The controller continuously updates the ego vehicle's velocity profile by comparing predicted lead vehicle velocity with route constraints, allowing adaptive optimization of fuel consumption without requiring complex real-time calculations for every parameter change
2Measurement precision
If lead vehicle behavior is modeled using data from the lead vehicle itself, then prediction accuracy is improved, but data acquisition complexity and communication requirements increase
Solution Approach 1:
The system creates a behavioral model of the lead vehicle by copying and analyzing its observed velocity patterns and response characteristics. Instead of requiring direct communication with the lead vehicle, the ego vehicle's controller constructs a predictive model based on observed lead vehicle behavior, enabling accurate predictions without complex inter-vehicle communication systems
Solution Approach 2:
The navigation system's preview information acts as an intermediary that provides route context (speed limits, road grade, curvature) which helps interpret lead vehicle behavior. This intermediary data allows the controller to distinguish between lead vehicle actions caused by road conditions versus intentional behavior, improving prediction accuracy without requiring direct lead vehicle data transmission
3Productivity
If ego vehicle velocity is optimized without considering lead vehicle constraints, then velocity optimization flexibility is improved, but safety and following distance compliance deteriorate
Solution Approach 1:
The controller applies preliminary anti-action by predicting lead vehicle velocity and using this prediction to constrain the ego vehicle's velocity profile in advance. Before optimizing for fuel efficiency or speed, the system pre-calculates velocity limits based on predicted lead vehicle behavior and route conditions, ensuring that safety constraints are built into the optimization from the start rather than being applied as post-processing corrections
Solution Approach 2:
The system uses feedback by continuously comparing the ego vehicle's predicted velocity profile against the predicted lead vehicle velocity and actual following distance. The controller adjusts the velocity setpoint based on this feedback, reducing speed when the lead vehicle is slowing or maintaining larger distances, thereby maintaining safety compliance while still allowing velocity optimization when conditions permit
Data Source
AI summary
Methods and systems for predicting velocities of both a lead vehicle and an ego vehicle along a travel route. The ego vehicle generates a velocity profile for the ego vehicle and a velocity prediction for the lead vehicle, and uses the ego vehicle velocity profile and the lead vehicle velocity prediction to estimate position and velocity of the ego vehicle in the travel route. Preview information from a navigation system is used and may include velocity limitations for the travel route derived from the travel route characteristics. Driver actions are used when generating the ego vehicle velocity profile by calculating a virtual velocity setpoint for the ego vehicle.