Time-Warping Autonomous Driving Simulation Playback Speed
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Autonomous vehicles face challenges in simulating autonomous driving scenarios due to position drift between recorded and simulation vehicles, leading to imperfect perception and potential decision-making errors, especially when using different decision-making algorithms or motion models.
Innovation Solution
The method involves receiving recorded driving data from a recorded autonomous vehicle, excluding decision-making data to obtain simulation data, and adjusting the playback speed of the simulation data to synchronize positions between the recorded and simulation vehicles, allowing the simulation vehicle to execute decision-making algorithms using the same data as the recorded vehicle.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If playback speed is adjusted to synchronize positions between recorded and simulation vehicles, then position synchronization accuracy is improved, but decision-making timing accuracy deteriorates
Solution Approach 1:
The system dynamically adjusts the playback speed of recorded driving data based on the position difference between the recorded vehicle and simulation vehicle. When the simulation vehicle lags behind, playback speed increases to catch up; when ahead, playback speed decreases. This dynamic adjustment resolves the contradiction by making the system adaptable to varying position synchronization needs while maintaining decision-making timing through corresponding algorithm execution timing.
2Reliability
If different decision-making algorithms are used between recorded and simulation vehicles, then algorithm robustness is improved, but position synchronization accuracy deteriorates
Solution Approach 1:
The system uses the same decision-making algorithm in both the recorded vehicle and simulation vehicle to ensure identical decision-making behavior. This copying approach eliminates discrepancies caused by algorithm differences, thereby maintaining position synchronization accuracy while still allowing robustness evaluation through playback speed adjustment based on position differences.
3Measurement precision
If decision-making data is excluded from simulation data, then simulation accuracy is improved, but data completeness deteriorates
Solution Approach 1:
The system extracts and excludes decision-making data from the simulation data set, using only sensing data and movement data for simulation purposes. This extraction resolves the contradiction by removing potentially biased decision-making information that could compromise simulation accuracy, while the excluded decision-making data is preserved separately for reference and analysis, thus maintaining overall data completeness.
Data Source
AI summary
Autonomous driving simulation using recorded driving data is disclosed. A method of simulating autonomous driving includes receiving recorded driving data from a recorded autonomous vehicle (AV), the recorded driving data includes decision-making data generated using a first decision-making algorithm, sensing data, and movement data including positions of the recorded AV; obtaining simulation data from the recorded driving data by excluding the decision-making data from the recorded driving data; and simulating, by a simulation AV, a second decision-making algorithm using the simulation data. The simulating the second decision-making algorithm includes determining a first position of the simulation AV at a first time and adjusting a playback speed of the simulation data based on a difference between the first position and a second position of the positions of the recorded AV at the first time.