Cooperative Vehicle Motion Estimation Under V2X Packet Loss
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Automated vehicles face challenges in accurately estimating motion due to communication delays and packet losses in wireless networks, which can lead to suboptimal performance and safety issues in cooperative driving scenarios.
Innovation Solution
A control system that monitors communication links for motion data of target vehicles, estimates their trajectory using models, and adjusts motion estimates based on communication link conditions, allowing the ego vehicle to maintain cooperative adaptive cruise control (CACC) mode even with degraded communication, ensuring more reliable motion control.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Loss of information
If vehicular communications (DSRC, V2X) are used to obtain states of vehicles beyond measurement ranges, then awareness about surrounding environment is improved, but communication delays and packet losses occur reducing CAV application performance
Solution Approach 1:
The system performs preliminary actions by predicting target vehicle motion states in advance using dynamic models before actual communication occurs. This allows the ego vehicle to prepare motion estimates proactively, reducing the impact of communication delays when actual state data is received later.
Solution Approach 2:
A dynamic model acts as an intermediary between the target vehicle's actual state and the ego vehicle's motion estimation. Instead of directly relying on delayed communication data, the system uses this intermediary model to generate accurate motion estimates that bridge the information gap caused by communication delays.
2Loss of time
If time-delay synthesizing and consensus-based CACC mode are used to aggregate delay, then communication delays are reduced, but the compensation may be insufficient under severe packet losses
Solution Approach 1:
The system dynamically adapts its motion estimation approach based on communication conditions. When packet losses occur, the system switches from relying on consensus-based CACC to using its own dynamic model predictions, making the system flexible and adaptive to varying communication reliability rather than using a fixed approach.
Solution Approach 2:
The system incorporates feedback mechanisms where the actual received motion data is compared with model-predicted values. This feedback allows the system to continuously refine its estimates and switch between using model predictions and actual communication data based on their relative reliability, improving robustness against packet losses.
3Reliability
If control system switches to ACC mode to avoid V2X packet losses, then communication reliability is improved, but effectiveness for estimating motion associated with automated driving decreases
Solution Approach 1:
The dynamic model serves as an intermediary that enables the system to maintain CACC mode while being robust to packet losses. The model fills in the gaps when communication data is lost, allowing the system to keep using the more accurate CACC motion estimation rather than degrading to ACC mode.
Solution Approach 2:
The system prepares cushioning measures in advance by maintaining dynamic models that can compensate for packet losses. This beforehand preparation allows the system to absorb communication failures without switching modes, as the models provide a safety buffer that maintains motion estimation accuracy even when V2X data is lost.
Data Source
AI summary
System, methods, and other embodiments described herein relate to a control system to improve estimating motion for an automated vehicle related to cooperative driving. In one embodiment, a method includes monitoring, by an ego vehicle, a communication link for motion data of a target vehicle, used in a model to determine motion, for motion planning by the ego vehicle. The method also includes estimating trajectory of the target vehicle according to a motion estimate by the model when criteria for the communication link are unsatisfied. The method also includes adjusting the motion estimate using a modified model, adapted for speed of the target vehicle, when the criteria for the communication link are satisfied. The method also includes controlling the ego vehicle according to the trajectory and the motion estimate.