Autonomous Vehicle Stop Selection Using Passenger Dwell Time
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Autonomous vehicles face challenges in determining safe and appropriate locations to pick up or drop off passengers due to the lack of human interaction and communication, which complicates the estimation of stop time and selection of suitable stopping places.
Innovation Solution
The system estimates the time required for a passenger to enter or exit the vehicle based on various factors, including whether the passenger is entering or exiting, the presence of packages, historical data, and traffic conditions. It then identifies suitable stopping places by comparing the estimated time with threshold times associated with different locations, and conducts a cost analysis to determine the best stopping location.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Ease of operation
If the vehicle stops at the exact requested location, then passenger convenience is improved, but safety may be compromised due to inability to assess pedestrian awareness and communication
Solution Approach 1:
The system performs preliminary actions by estimating the time required for passenger entry/exit before finalizing the stopping decision. This advance calculation allows the vehicle to assess whether the requested location is suitable, balancing convenience with safety requirements by identifying potential issues before committing to a stop.
2Reliability
If the vehicle waits for an extended period for passenger entry/exit, then passenger safety is improved, but traffic flow is disrupted
Solution Approach 1:
The system dynamically changes the time parameter by calculating an estimated waiting period based on multiple factors including passenger type, location characteristics, and environmental conditions. This parameter adjustment allows the vehicle to optimize the balance between safety (adequate waiting time) and traffic efficiency (minimizing disruption).
Solution Approach 2:
The system autonomously determines the appropriate waiting time without requiring manual input or external intervention. By self-calculating the estimated time based on available data, the vehicle independently resolves the conflict between safety requirements and traffic flow considerations.
3Measurement precision
If the vehicle collects and processes multiple factors for time estimation, then accuracy of stopping decision is improved, but computational complexity increases
Solution Approach 1:
The system segments the time estimation process into distinct components: base time estimation, factor-based adjustments, and threshold comparisons. Each factor (passenger type, packages, location characteristics) is processed as a separate element that contributes to the overall estimate, making the complex calculation more manageable and systematic.
4Reliability
If the vehicle selects from multiple possible stopping places, then passenger safety is improved, but decision-making time increases
Solution Approach 1:
The system changes the evaluation parameter by comparing estimated times against pre-established threshold values for each candidate location. This parameter transformation converts a complex multi-criteria decision problem into a series of simpler threshold-based comparisons, reducing decision-making time while maintaining safety considerations.
Data Source
Figure 1
Figure 2A
Figure 2B
AI summary
Aspects of the disclosure provide for stopping a vehicle 100 to pick up or drop off a passenger at a location. An example methods includes maneuvering a vehicle towards the location 680. An amount of time for the passenger to enter or exit a vehicle is estimated. Once the vehicle is a predetermine distance from the location, a set of possible places to stop the vehicle are determined. For each place of the set of possible places, a corresponding threshold value is determined. For each place of the set of possible places, the estimated amount of time is compared to the corresponding threshold value. A particular one of the set of possible places is identified based on the comparisons and the vehicle at the particular one to allow the passenger to enter or exit the vehicle.