Pickup Drop-off Zone Selection for Autonomous Vehicles
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Autonomous vehicles face challenges in identifying and navigating to safe and efficient pickup/drop-off zones, as well as guiding passengers to these zones, due to uncertainties in zone availability and walking distances, which affect passenger convenience and safety.
Innovation Solution
A PDZ/Walking Point Calculation system that uses probabilistic models and machine learning algorithms to estimate the availability of pickup/drop-off zones based on historical data and real-time information, and communicates with the vehicle autonomy system to optimize routes and guide both the vehicle and passengers to the most suitable zones.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Ease of operation
If the vehicle is guided to PDZs close to the passenger's location, then passenger convenience is improved, but the challenge of identifying safe and efficient PDZs increases
Solution Approach 1:
The system performs preliminary calculations of walking points and PDZ availability before the vehicle arrives. The server computes optimal PDZs and walking routes in advance based on historical data and real-time conditions, so that when the vehicle approaches, the passenger already has guidance information ready, resolving the contradiction between convenience and identification difficulty
Solution Approach 2:
A server acts as an intermediary between the passenger mobile device and the vehicle autonomy system. The server consolidates complex data processing for PDZ identification and walking point calculation, providing simplified guidance information to both the vehicle and passenger, thus resolving the difficulty of detecting and measuring safe PDZs while maintaining passenger convenience
2Reliability
If passengers need to be guided to PDZ for pickup, then passenger safety is improved, but the complexity of the guidance system increases
Solution Approach 1:
The guidance system is segmented into distinct functional components: a server for centralized calculations, a vehicle autonomy system for vehicle guidance, and a passenger mobile device for passenger guidance. This segmentation distributes complexity across multiple simple components rather than one complex system, improving safety through coordinated specialization while managing overall system complexity
Solution Approach 2:
The server serves as an intermediary that handles the complex calculations of walking points and PDZ availability, while the vehicle autonomy system and passenger mobile device receive simplified guidance information. This intermediary approach improves passenger safety through accurate calculations while keeping the actual guidance devices relatively simple
3Productivity
If probabilistic models and machine learning algorithms are used to estimate PDZ availability, then route optimization is improved, but the computational complexity increases
Solution Approach 1:
The server acts as an intermediary that performs computationally intensive probabilistic models and machine learning algorithms for PDZ availability estimation. By centralizing these complex calculations on the server rather than in the vehicle or mobile device, the system achieves route optimization efficiency while managing computational complexity in a centralized location with greater processing resources
Data Source
AI summary
Systems and methods are provided for finding an available pickup/drop-off zone (PDZ) for an autonomous vehicle (AV) to use to pick up a passenger. A PDZ is selected that is likely to be available and that is within a reasonable walking distance of a passenger. The AV and the passenger are guided to the available PDZ. In selecting the available PDZ, the system balances the human and vehicle routing by taking into account the distance possible PDZs are from the passenger, the likelihood the respective PDZs will be available, the passenger's desire/ability to walk to the respective PDZs (e.g., due to physical limitations, weather, etc.), the driving time of the AV to the respective PDZs, the walking time of the passenger to the respective PDZs, and the like.