Steering Torque Intent Detection for Earlier Evasive Maneuvers
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Conventional threat avoidance steering systems in vehicles are reactive and may be delayed, leading to potential collisions due to inadequate detection of driver-initiated collision avoidance steering, especially in curved maneuvers.
Innovation Solution
A vehicle system that proactively detects driver intent through monitoring torque and vehicle states, using a probabilistic approach and mathematical modeling to predict evasive steering maneuvers, enabling faster and accurate detection of driver intent.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Speed
If conventional dynamics-based systems are used for threat avoidance steering, then the system structure is simpler, but the detection speed is slower and collision avoidance is delayed
Solution Approach 1:
The system performs preliminary action by proactively detecting driver intent before the evasive maneuver is fully executed. The probabilistic model continuously assesses torque and torque rate data to predict upcoming steering actions, enabling the threat avoidance system to activate assistive steering earlier than conventional reactive systems that wait for dynamic changes to occur.
Solution Approach 2:
The patent replaces conventional mechanics-based detection (relying on vehicle dynamic responses) with a probabilistic computational model. Instead of waiting for physical vehicle responses to trigger detection, the system uses mathematical modeling of driver torque patterns to predict intent, substituting mechanical reaction-based detection with computational prediction.
2Measurement precision
If proactive driver intent detection is implemented using probabilistic modeling, then collision avoidance accuracy is improved, but the computational complexity increases
Solution Approach 1:
The system changes parameters by using probabilistic thresholds and confidence levels to determine driver intent. Instead of relying on fixed dynamic thresholds, the model calculates probabilities based on torque and torque rate patterns, allowing for more nuanced and accurate detection of driver intent while managing computational complexity through statistical methods.
Solution Approach 2:
The probabilistic model continuously learns and adapts to individual driver behavior patterns, effectively serving itself by improving detection accuracy over time without requiring external recalibration. The system uses historical torque data to refine its understanding of each driver's steering characteristics, enhancing precision while maintaining automated operation.
3Loss of time
If the system waits for vehicle dynamic changes to activate assisted steering, then the control logic is simpler, but the response time is delayed causing potential collisions
Solution Approach 1:
The system performs preliminary action by detecting driver intent before the evasive maneuver is fully executed. The probabilistic model continuously assesses torque and torque rate data to predict upcoming steering actions, enabling the threat avoidance system to activate assistive steering earlier than conventional reactive systems that wait for dynamic changes to occur.
Solution Approach 2:
The system implements continuous feedback by monitoring torque and torque rate data in real-time and adjusting the probabilistic assessment of driver intent accordingly. This feedback loop allows the system to dynamically update its prediction of driver intent and activate threat avoidance steering at the optimal moment, balancing early activation with accurate timing.
Data Source
AI summary
A vehicle system includes a control module configured to receive data from a sensor indicative of a torque applied to the steering wheel, calculate a torque rate based on the applied torque, calculate a left evasive steering probability of the driver intending to steer the vehicle to the left and a right evasive steering probability of the driver intending to steer the vehicle to the right based on the torque, the torque rate, and a modeled relationship between the torque and the torque rate, compare the left evasive steering probability and the right evasive steering probability to determine a directional steering intent of the driver, and transmit a signal to a threat avoidance steering control module for controlling the vehicle. Other example vehicle systems and methods for predicting driver intent in evasive steering maneuvers are also disclosed.