Predictive Vehicle Motion Control for Stability Limit Avoidance
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current automated driving systems, such as ESP and LKA, are ineffective in anticipating and preventing vehicle stability limit violations, especially in fully automated driving modes, as they lack the ability to predict future states and react proactively to situations like sharp bends with excessive speed, leading to potential overspeeding or loss of control.
Innovation Solution
A device that integrates a prediction model using on-board sensors and road marking detection to anticipate future vehicle states, determining if driving limits will be exceeded, and triggering anticipatory corrective actions like braking or steering adjustments before reaching stability limits.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If automated driving systems use reactive control based on current vehicle state and detected road curvature, then the system can maintain basic lane keeping functionality, but the system cannot anticipate future stability limit violations and react proactively to prevent them
Solution Approach 1:
The prediction model calculates future vehicle states at multiple time steps ahead (e.g., t+1, t+2, ..., t+N) to anticipate stability limit violations before they occur. This preliminary calculation of future states enables the system to take preventive action in advance, rather than reacting only when limits are approached or exceeded.
Solution Approach 2:
The system applies corrective control actions (braking, steering adjustments) before the vehicle reaches stability limits by predicting future violations. The ESP system intervenes anticipatorily with counteracting forces to prevent the predicted unstable state from occurring, rather than reacting after the violation has begun.
2Reliability
If the ESP system intervenes automatically to keep the vehicle on the desired trajectory, then the vehicle can be stabilized during critical situations, but the system degrades in performance on fully automated vehicles without speed information and maximum speed thresholds
Solution Approach 1:
The prediction model acts as an intermediary between the current vehicle state and the ESP control system. It processes sensor data and road curvature information to generate predicted future states, which then inform the ESP system's control decisions. This intermediary layer enables the system to function effectively in fully automated mode by providing anticipatory guidance without requiring direct driver input or maximum speed threshold parameters.
Solution Approach 2:
The system implements a feedback loop where predicted future states are continuously compared against stability limits, and corrective actions are applied based on these predictions. The prediction model receives input from sensors and control actuators, and its outputs feed back to the ESP system to adjust control commands, creating a closed-loop anticipatory control mechanism.
Data Source
Figure 1~2
Figure 3A~3B
Figure 4~5
AI summary
Device for controlling the movement of a motor vehicle, comprising a longitudinal controller (12) and a lateral controller (13) which are capable of generating, from first information relating to the road layout and second information relating to the dynamic behaviour of the vehicle, control commands intended for actuators for controlling the longitudinal and lateral movement of the vehicle, characterised in that it comprises a prediction model (16) which is supplied with the first and second information and is capable of determining future states of the vehicle for future positions of the vehicle over a plurality of iterations defining a future road portion, the model being connected to a module (19) for determining whether driving limit values are violated, which module is capable of determining, for each future state, whether one of the state variables defining the future state reaches or exceeds a driving limit value, and of deducing a future risk situation.