Vehicle Handover Control Using Traffic and Link Quality Prediction
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing systems face challenges in safely and seamlessly transitioning control from remote driving mode to automated driving mode, particularly when connectivity to a remote control center becomes insufficient, and in selecting an appropriate level of automation during this transition.
Innovation Solution
A method that determines automated driving preferences from vehicle behavior, predicts future traffic situations, and assesses communication quality to decide on a safe and seamless handover duration, allowing the vehicle to take over control based on predefined conditions and driver adaptation when necessary.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If the vehicle switches from remote driving mode to automated driving mode when connectivity becomes insufficient, then control handover can be achieved, but the transition may be unsafe or non-seamless without proper prediction and assessment
Solution Approach 1:
The system performs preliminary actions by determining automated driving preferences from historical driving behavior, predicting future traffic situations ahead of time, and assessing communication quality in advance. This allows the vehicle to prepare for mode switching before connectivity actually becomes insufficient, ensuring safer and more seamless transitions by having all necessary information ready beforehand.
Solution Approach 2:
The system dynamically adapts the level of automation during the transition process. Instead of a fixed switching protocol, the vehicle can adjust between different levels of automation (from fully remote to fully automated) based on real-time assessment of traffic situation complexity, communication quality, and predicted handover duration, making the transition more flexible and safer.
2Reliability
If the system predicts future traffic situations and assesses multiple parameters to determine safe handover conditions, then the transition safety is improved, but the computational complexity and time required for decision-making increases
Solution Approach 1:
The system determines automated driving preferences in advance by analyzing historical driving behavior data. This preliminary processing of driver preferences allows the system to have pre-computed information ready when a mode switch is needed, reducing the real-time computational burden and decision-making time while maintaining high safety standards.
Solution Approach 2:
The system predicts future traffic situations and assesses communication quality rapidly to quickly determine whether handover conditions are met. By using predictive models and real-time assessment algorithms, the system can fast-track the decision-making process, reducing the time loss associated with complex evaluations while ensuring safety criteria are met.
3Reliability
If the vehicle waits for ideal conditions to switch to automated driving mode, then the transition can be safer, but the remote operation interval may expire before handover is complete
Solution Approach 1:
The system assesses communication quality and determines predicted remote operation intervals in advance. By having this information ready before the interval expires, the vehicle can make informed decisions about when to initiate handover, ensuring that the transition begins with sufficient time buffer while still meeting safety requirements.
Solution Approach 2:
The system dynamically adjusts the timing of mode switching based on real-time conditions. Instead of waiting passively for ideal conditions or switching rigidly at a predetermined time, the vehicle continuously monitors traffic situation complexity, communication quality, and predicted handover duration to determine the optimal moment for transition, balancing safety with the constraint of the remote operation interval.
4Reliability
If the system uses predefined conditions and driver adaptation to determine handover timing, then the transition can be more personalized and safe, but the system complexity increases
Solution Approach 1:
The system determines automated driving preferences by analyzing the driver's own historical driving behavior data. This self-service approach allows the system to automatically learn and adapt to individual driver patterns without requiring complex external configuration or manual input, making the personalized handover decisions more efficient while maintaining safety.
Solution Approach 2:
The system uses feedback from historical driving behavior to continuously refine automated driving preferences. By analyzing past driving patterns and outcomes, the system learns what conditions and timing work best for each driver, improving the safety and suitability of handover decisions over time while the learning process automates what would otherwise require complex manual calibration.
Data Source
AI summary
A transportation vehicle, infrastructure component, apparatus, computer program, and method for a transportation vehicle configured to be remotely operated by a remote driver in a remote driving mode and to be operated at least partially automatically in an automated driving mode. The method includes determining automated driving preferences of the transportation vehicle from driving behavior of the transportation vehicle, predicting information on a future traffic situation for switching from the remote driving mode to the automated driving mode, determining a predicted quality of service (pQoS) of a communication link to obtain a remote operation interval for which the transportation vehicle is at least operable in the remote driving mode, obtaining a handover duration for taking over control by the transportation vehicle for switching from the remote driving mode to the automated driving mode, and deciding for or against switching from the remote driving mode to the automated driving mode.