Autonomous Vehicle Precise Pull-Over Simulation
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Autonomous vehicles face challenges in identifying precise stopping locations that minimize traffic disruption, especially in crowded city environments, as existing systems lack effective methods to optimize stopping positions and passenger behavior simulations.
Innovation Solution
The system utilizes vehicle sensors and mechanical simulations to identify suitable stopping positions by generating high-definition models of surroundings, simulating vehicle and passenger movements, and determining scores for different plans to select the most optimal stopping location, which includes activating a high-definition perception system and onboard computer to process sensor data and generate simulations.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Ease of operation
If the autonomous vehicle stops in a moving traffic lane for pick-up and drop-off, then passenger service is provided, but traffic disruption and driver aggravation increase
Solution Approach 1:
The system performs preliminary simulation of vehicle stopping positions and passenger behaviors before actual execution. Multiple potential stopping positions are evaluated in advance through simulation to predict traffic disruption and select the optimal position that minimizes harm to surrounding traffic while still providing passenger service.
Solution Approach 2:
The system creates virtual copies of the vehicle, passengers, and surrounding environment in a simulation model. This digital twin allows the system to test different stopping scenarios and passenger behaviors without affecting real traffic, enabling selection of the best stopping position based on simulated outcomes.
2Productivity
If the vehicle stops precisely to minimize traffic disruption, then traffic flow is maintained, but passenger safety and comfort during entry/exit may be compromised
Solution Approach 1:
The system uses virtual copies of passengers with simulated physical characteristics and behaviors to test entry and exit scenarios. This allows evaluation of safety metrics for different stopping positions without risking actual passenger safety, enabling selection of positions that optimize both traffic flow and passenger safety.
Solution Approach 2:
Passenger safety is evaluated in advance through simulation before the vehicle actually stops. The system predicts potential safety issues for each candidate stopping position and selects only those positions that meet safety thresholds, ensuring safety is not compromised while maintaining traffic flow.
3Measurement precision
If multiple stopping positions are evaluated with detailed simulations, then the optimal position is identified, but computational time and processing resources increase
Solution Approach 1:
The system evaluates multiple stopping positions with simulations, but limits the number of positions and simulation iterations to a manageable subset. This partial evaluation approach provides sufficiently precise optimization without requiring exhaustive analysis of all possible positions, reducing computational time while maintaining acceptable precision.
Solution Approach 2:
The system performs preliminary filtering of candidate stopping positions based on basic criteria before conducting detailed simulations. This preliminary action reduces the number of positions requiring full simulation analysis, significantly reducing computational time while still identifying the optimal position among the most promising candidates.
Data Source
AI summary
Systems and methods for identifying a precise stopping location using vehicle sensors and mechanical simulation. In particular, systems and methods are provided for using vehicle sensor information to understand vehicle surroundings, identifying an appropriate stopping position that either does not disrupt traffic (or minimally disrupts traffic), and identifying a path to the stopping position. Additionally, the suitability of the stopping position is determined by performing a simulation of the vehicle movement to the stopping position as well as a simulation of passenger behavior during vehicle exit. In some examples, the simulation is performed using a short-range relative map of the vehicle surroundings rather than using the driving map. Additionally, the simulation can be performed using heuristic or data-driven models