AV Pullover Routing Using Crowding-Aware Location Filtering
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Autonomous vehicles (AVs) often cluster at pickup and drop-off locations, leading to slowdowns, increased reliance on remote assistance, and higher risks of vehicle retrieval events due to cautious navigation in tight spaces.
Innovation Solution
Implement a routing system that identifies and adjusts AV destinations to prevent clustering by filtering out crowded pullover locations based on a defined crowding metric, using algorithms to predict potential crowding and adjust routes in real-time.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Productivity
If AVs navigate to the same requested pullover locations, then service demand is met, but clustering occurs causing slowdowns and safety issues
Solution Approach 1:
The system performs preliminary analysis of requested pullover locations against historical and real-time crowding data before dispatching AVs. By predicting potential clustering events in advance and adjusting routes proactively, the system prevents crowding before it occurs, ensuring both service demand is met and navigation safety is maintained
Solution Approach 2:
The route coordination system acts as an intermediary between service demand and AV navigation. It introduces a crowding assessment layer that mediates between the need to fulfill service requests and the need to avoid clustering, using historical data and real-time information to make intelligent routing decisions
2Productivity
If AVs cluster at pullover locations, then service concentration is achieved, but traffic efficiency decreases and remote assistance is required
Solution Approach 1:
The system applies different routing strategies to different locations based on their crowding characteristics. High-crowding locations receive route adjustments to disperse AVs, while low-crowding locations can accept direct routing. This localized quality adjustment maintains service concentration where appropriate while preventing slowdowns in crowded areas
Solution Approach 2:
The system resolves spatial clustering by introducing temporal dimensionality - staggering arrival times at pullover locations even when multiple AVs are dispatched to the same area. By distributing arrivals across different time windows, the system maintains service concentration without causing simultaneous traffic slowdowns
3Reliability
If AVs navigate cautiously in tight spaces, then collision risk is reduced, but navigation speed decreases
Solution Approach 1:
The system applies preliminary anti-action by preventing AVs from entering crowded areas in the first place. Through proactive route adjustment based on crowding predictions, the system eliminates the need for cautious navigation in tight spaces, allowing AVs to maintain higher speeds in open, uncrowded areas while still ensuring collision avoidance
Data Source
AI summary
Disclosed are embodiments for facilitating autonomous vehicle (AV) pullover clustering prevention. In some aspects, an embodiment includes receiving identification of an origin location and a destination location corresponding to a transportation trip request for an AV; determining a set of pullover locations comprising pickup locations for the origin location and drop-off locations for the destination location; for each pullover location of the set of pullover locations: determining an estimated time of arrival (ETA) time window for the AV at the pullover location; determining a number of other AVs expected to be at the pullover location during the ETA time window; and responsive to the number of other AVs expected to be at the pullover location during the ETA time window exceeding an AV pullover crowding metric, removing the pullover location from the set of pullover locations to produce a revised set of pullover locations.