Autonomous Vehicle Prepositioning Circuits for Lower-Latency Coverage

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Conventional transportation matching systems face challenges with flexibility and efficiency, particularly in balancing computing device imbalances and ensuring effective network coverage, leading to increased latency, reduced responsiveness, and inefficient resource utilization.

Innovation Solution

The system dynamically generates and modifies autonomous vehicle pre-matching circuits defined by waypoints and transmits prepositioning instructions to improve network coverage. It uses a prediction model to determine predicted requester devices, divides the service area into subregions, and optimizes vehicle assignments based on real-time data and vehicle locations.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Reliability

If conventional transportation matching systems match requesting devices with provider devices, then transportation coordination is achieved, but network coverage and responsiveness are reduced due to computing device imbalances

Engineering Contradiction:

Improvenetwork coverageVSAvoidlatency

Core Design Contradiction:

ReliabilityVSLoss of time

Solution Approach 1:

The system performs preliminary actions by pre-positioning autonomous vehicles in strategic locations before transportation requests are made. The pre-positioning system proactively moves vehicles to high-demand areas based on predictive analytics, so when requests arrive, vehicles are already nearby and ready to serve, eliminating waiting time and improving network coverage.

Inventive Principle:

Principle #10Preliminary action

Solution Approach 2:

The system implements dynamic pre-positioning where autonomous vehicles are continuously redistributed based on real-time demand patterns, time of day, day of week, and predicted future requests. This dynamic adjustment optimizes vehicle distribution across the service area, improving network coverage and responsiveness without static assignments.

Inventive Principle:

Principle #15Dynamics

2Adaptability or versatility

If conventional systems coordinate transportation through digital transmissions, then matching is achieved, but flexibility and efficiency are reduced due to computing device imbalances

Engineering Contradiction:

Improveflexibility of operationVSAvoidefficiency of implementing computing devices

Core Design Contradiction:

Adaptability or versatilityVSProductivity

Solution Approach 1:

The pre-positioning system operates autonomously using predictive models and optimization algorithms to self-manage vehicle distribution without requiring constant human intervention or complex real-time coordination for each vehicle assignment. The system learns from historical data and automatically adjusts pre-positioning strategies, improving both flexibility and computational efficiency.

Inventive Principle:

Principle #25Self-service

Solution Approach 2:

The system replaces traditional mechanical matching approaches (real-time request-response coordination) with a predictive information-based system that uses machine learning models to anticipate demand and proactively position vehicles. This substitution of predictive analytics for reactive coordination improves operational flexibility and reduces computational burden.

Inventive Principle:

Principle #28Mechanics substitution (Replace mechanical system)

3Reliability

If autonomous vehicles are positioned statically, then network coverage is maintained, but responsiveness to changing conditions deteriorates

Engineering Contradiction:

Improvenetwork coverageVSAvoidresponsiveness

Core Design Contradiction:

ReliabilityVSSpeed

Solution Approach 1:

Inventive Principle:

Principle #15Dynamics

Solution Approach 2:

The system uses feedback loops where actual transportation requests, vehicle locations, and demand patterns are continuously monitored and fed back into the predictive models. This feedback enables the system to learn from real-world outcomes and continuously refine pre-positioning strategies, maintaining both coverage and responsiveness to changing conditions.

Inventive Principle:

Principle #23Feedback

Data Source

PatentUS12271191B2Generating and transmitting autonomous vehicle prepositioning instructions to improve network coverage

Publication Date: 2025.04.08 LYFT INC

AI summary

The present disclosure relates to systems, non-transitory computer-readable media, and methods for generating and transmitting autonomous vehicle prepositioning instructions to improve network coverage. In particular, in one or more embodiments, the disclosed systems subdivide a geographic transportation service area into subregions, generate a set of waypoints and circuits for the subregions. Moreover, in one or more embodiments, the disclosed systems utilize an optimization model to assign autonomous vehicles to the set of waypoints and circuits and transmit digital prepositioning instructions to the autonomous vehicles to traverse the waypoints and circuits.