Autonomous Vehicle Simulation for Manual Driving Progress Comparison
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Autonomous vehicles require effective testing and validation of their control software to ensure safe interaction with other road users, as existing methods lack accurate comparison with manually-driven vehicle behaviors, leading to potential differences in progress and passenger experience.
Innovation Solution
A method involving the retrieval of log data from manually-driven vehicles, generation of path segments, and simulation of autonomous vehicle progress along these segments to determine differences in behavior, allowing for adjustments to the autonomous vehicle software to mimic manually-driven vehicle performance.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If autonomous vehicle software is tested using existing validation methods, then testing coverage is achieved, but accurate comparison with manually-driven vehicle behaviors is lacking
Solution Approach 1:
The patent creates a digital twin or simulation model that copies the behavior of manually-driven vehicles. By retrieving log data from manually-driven vehicles and generating path segments that replicate real driving behavior, the system enables accurate comparison between autonomous and manual driving patterns without physical testing
Solution Approach 2:
The patent introduces simulation software as an intermediary between autonomous vehicle testing and real-world validation. The simulation environment acts as a mediator that can reproduce complex manual driving scenarios and compare autonomous vehicle responses against established manual driving baselines
2Reliability
If autonomous vehicle software is made more cautious to improve safety, then passenger safety increases, but progress along route decreases
Solution Approach 1:
The patent implements dynamic adjustment of autonomous vehicle behavior based on contextual factors. By analyzing simulation data from manually-driven vehicles, the system learns when caution is appropriate and when normal progress should resume, allowing the vehicle to dynamically adapt its safety parameters rather than maintaining fixed conservative settings
Solution Approach 2:
The patent adjusts software parameters such as buffer distances and discomfort thresholds based on simulation results. By changing these parameters dynamically according to learned manual driving patterns, the system optimizes the balance between safety and progress, allowing the vehicle to be cautious when necessary and efficient when safe
3Reliability
If simulation testing is implemented to compare autonomous and manual vehicle behavior, then software validation improves, but computational resources and time increase
Solution Approach 1:
The patent performs preliminary actions by pre-processing log data from manually-driven vehicles into structured path segments before running simulations. This preparation work is done once and reused across multiple simulation scenarios, reducing the overall time required for comprehensive validation
Solution Approach 2:
The patent divides the testing process into manageable segments by breaking down routes into path segments and analyzing them individually. This segmentation allows for parallel processing and focused validation of specific driving scenarios, reducing total testing time while maintaining comprehensive coverage
Data Source
AI summary
A simulation may be used to determine a difference between progress of a manually-driven vehicle and progress of a simulated autonomous vehicle. The method includes retrieving log data collected for the manually-driven vehicle driving along a route, generating a plurality of path segments for a portion of the route. The plurality of path segments corresponds to points in a lane that the manually-driven vehicle traveled through on the portion of the route. The method also includes running, using a software of the autonomous vehicle, a simulation of the autonomous vehicle driving along the plurality of path segments, extracting metrics from the log data and the simulation, and determining the difference between a first progress of the manually-driven vehicle and a second progress of the simulated autonomous vehicle based on the metrics.