Autonomous Vehicle Prediction of Continuing Lane Driving
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Autonomous vehicles face challenges in predicting and responding to atypical behaviors of other road users, such as jaywalking pedestrians or vehicles running red lights, which can lead to unsafe driving operations.
Innovation Solution
The use of machine learning models to identify and predict continuing lane driving behaviors by analyzing sensor data and map information, allowing the vehicle to adjust its operation accordingly.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If traditional detection and prediction methods are used for road users, then the system operates with standard processing capabilities, but the precision and recall of behavior predictions deteriorate when facing atypical behaviors
Solution Approach 1:
The system changes the parameters of behavior prediction by incorporating continuing lane driving behavior as a specific prediction category. The machine learning model is trained to predict not only standard behaviors (turning, stopping) but also atypical continuing lane behaviors, thereby improving prediction precision for diverse road user actions while maintaining adaptability through parameter expansion in the prediction space.
2Reliability
If the vehicle responds rapidly to detected objects by braking, then collision avoidance is improved, but sudden changes in acceleration occur causing discomfort and potential safety issues
Solution Approach 1:
The system performs preliminary action by predicting continuing lane driving behavior in advance, allowing the autonomous vehicle to plan alternative driving operations before the situation becomes critical. By identifying that a road user may continue straight instead of turning, the system can gradually adjust its trajectory and speed, avoiding sudden braking while still ensuring collision avoidance through proactive motion planning.
3Adaptability or versatility
If the system plans for alternative driving operations to handle rule-violating road users, then adaptability to atypical behaviors is improved, but the complexity of prediction and planning increases
Solution Approach 1:
The system applies segmentation by separating the behavior prediction task into distinct categories: standard behaviors (turning, stopping, proceeding) and continuing lane driving behavior. The machine learning model processes these segmented behavior types independently, allowing the system to handle atypical behaviors adaptably while managing complexity through modular prediction architecture rather than a monolithic complex model.
Data Source
AI summary
The technology relates to controlling a vehicle in an autonomous driving mode in accordance with behavior predictions for other road users in the vehicle's vicinity. In particular, the vehicle's onboard computing system may predict whether another road user will perform a “continuing” lane driving operation, such as going straight in a turn-only lane. Sensor data from detected/observed objects in the vehicle's nearby environment may be evaluated in view of one or more possible behaviors for different types of objects. In addition, roadway features, in particular whether lane segments are connected in a roadgraph, are also evaluated to determine probabilities of whether other road users may make an improper continuing lane driving operation. This is used to generate more accurate behavior predictions, which the vehicle can use to take alternative (e.g., corrective) driving actions.