Remote Driving Control with Predicted Network Quality Adaptation
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Remote driving technologies face safety risks due to sudden changes in network quality, which can lead to network lags and compromised vehicle control, especially when high bandwidth and low delay requirements are not met.
Innovation Solution
A method that predicts network quality changes in the future, allowing the remote driving system to adjust vehicle parameters before the change occurs, thereby maintaining safe traveling conditions by adjusting data quality and transmission parameters based on predicted network conditions.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If remote driving transmits collected scene information around the vehicle to a cloud driving cabin with high bandwidth and low delay requirements, then the remote driving control can be achieved, but the network quality sudden changes can cause network lags and reduce safety
Solution Approach 1:
The system performs preliminary actions by predicting future network quality changes before they actually occur. The prediction module forecasts network quality at future time points, and the system proactively adjusts transmission parameters in advance, allowing the remote driving control to adapt to upcoming network conditions rather than reacting to changes after they happen. This preliminary action prevents network lags by preparing the system ahead of time.
Solution Approach 2:
The system dynamically adjusts transmission parameters based on predicted network quality. The traveling parameter adjustment module continuously modifies transmission bitrate, resolution, and other parameters according to the predicted network conditions at different time points. This dynamic adaptation allows the system to optimize performance for upcoming network states, maintaining reliability despite network fluctuations.
2Reliability
If the remote driving system adjusts traveling parameters in real-time based on current network quality, then network lags can be reduced, but the system cannot anticipate sudden network quality changes
Solution Approach 1:
The prediction module performs preliminary actions by forecasting network quality at future time points before the actual changes occur. By predicting network quality trends in advance, the system can adjust transmission parameters proactively rather than reactively, eliminating the time loss associated with waiting for network changes to manifest before responding.
Solution Approach 2:
The system applies beforehand cushioning by preparing for anticipated network quality degradation. The prediction module identifies potential network issues in advance, and the adjustment module pre-adjusts transmission parameters to compensate for upcoming network conditions. This cushioning approach creates a buffer that protects against network lags before they can impact remote driving control.
3Measurement precision
If high bandwidth is used for transmitting scene information, then remote driving control quality is improved, but network resource consumption increases and vulnerability to network quality changes increases
Solution Approach 1:
The system dynamically adjusts transmission parameters including bitrate, resolution, and frame rate based on predicted network quality. The traveling parameter adjustment module continuously optimizes these parameters to match upcoming network conditions, allowing the system to maintain high scene information quality when network conditions permit while adapting to lower quality when network resources are constrained. This dynamic approach improves both measurement precision and adaptability.
Solution Approach 2:
The system changes transmission parameters such as video resolution, bitrate, and frame rate based on predicted network quality. By adjusting these parameters proactively, the system can optimize scene information transmission quality for current and future network conditions while reducing vulnerability to network quality changes. Parameter changes allow the system to balance quality and resource consumption adaptively.
Data Source
AI summary
This application provides a remote driving control method performed by an electronic device mounted on a vehicle, and is applicable to the field of intelligent transportation. The remote driving control method includes: obtaining prediction information of a first area, the prediction information indicating network quality of the first area at a first time when the vehicle is scheduled to travel in the first area at the first time; determining, based on the prediction information, a control policy of the remote driving vehicle at the first time; adjusting a traveling parameter of the vehicle based on the control policy before the first time; and controlling the vehicle to travel in the first area at the first time through remote driving in accordance with the adjusted traveling parameter.