Hybrid ADAS Override for Real-Time Emergency Gap Control
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Probabilistic ADAS systems face challenges in ensuring safety during sudden or unintended acceleration due to longer computation times and delayed decision-making, which can lead to uncertainty and increased risk of accidents, especially when relying on cloud-based data transmission.
Innovation Solution
A hybrid adaptive cruise control system that switches from a cloud-based probabilistic controller to a deterministic controller located in the vehicle during unsafe conditions, utilizing a deterministic override algorithm to make real-time decisions and ensure safer driving by overriding the probabilistic system.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Adaptability or versatility
If a cloud-based probabilistic controller is used for adaptive cruise control, then personalized driving preferences and naturalistic vehicle-following styles are maintained, but real-time decision-making capability during emergency situations is reduced due to longer computation and transmission times
Solution Approach 1:
The control system is segmented into two distinct controllers: a cloud-based probabilistic controller for normal driving conditions and a deterministic controller for emergency situations. This segmentation allows each controller to specialize in its respective domain, maintaining personalized driving styles during normal operation while ensuring rapid response during emergencies
Solution Approach 2:
The system dynamically switches between probabilistic and deterministic control modes based on the driving situation. The probabilistic controller handles personalized, adaptive control during normal conditions, while the deterministic controller takes over for real-time emergency responses, creating a dynamic hybrid architecture that adapts to situational requirements
2Adaptability or versatility
If a cloud-based probabilistic controller is used for adaptive cruise control, then personalized driving preferences are maintained, but system reliability during unsafe or uncertain driving conditions is reduced due to computation delays
Solution Approach 1:
The system prepares for potential failures by pre-configuring a deterministic controller as a safety backup. This deterministic controller is ready to immediately take over when unsafe conditions are detected, providing a cushion against the reliability limitations of cloud-based probabilistic control during critical situations
Solution Approach 2:
A hybrid control architecture acts as an intermediary layer between the cloud-based probabilistic controller and the vehicle's deterministic safety systems. This intermediary structure allows the system to leverage the adaptability of probabilistic control while maintaining the reliability guarantees of deterministic control through a structured integration approach
3Reliability
If a deterministic controller is used for all driving conditions, then real-time control and safety are ensured, but personalized driving preferences and naturalistic vehicle-following styles are lost
Solution Approach 1:
Different control qualities are applied to different operational contexts: probabilistic control with personalized characteristics is used for normal driving conditions where adaptability is valued, while deterministic control with guaranteed real-time performance is applied locally to emergency and unsafe conditions where reliability is paramount
4Adaptability or versatility
If cloud-based data transmission is used for probabilistic ADAS, then personalized driving data can be processed, but computation and transmission delays increase response time during emergencies
Solution Approach 1:
The critical real-time control function is extracted from the cloud-based probabilistic system and placed into a local deterministic controller. This extraction removes the time-consuming cloud communication loop from the emergency response path, allowing instantaneous local decision-making while the cloud system continues to handle personalized driving profile updates during normal operation
Data Source
AI summary
A hybrid deterministic override to cloud based probabilistic advanced driver assistance systems. Under default driving conditions, an ego vehicle is controlled by a probabilistic controller in a cloud. An overall gap between the ego vehicle and a leading vehicle is divided into an emergency collision gap and a driver specified gap. The vehicle sensors monitor the overall gap. When the gap between the ego vehicle and the leading vehicle is less than or equal to the emergency collision gap, a deterministic controller of the ego vehicle overrides the cloud based probabilistic controller to control the braking and acceleration of the ego vehicle.


