Autonomous Fleet Simulation Using Real-Time Sensor Feedback

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Traditional transportation services are inefficient due to human operators' lack of knowledge about demand areas and preferences for familiar regions, leading to sub-optimal vehicle distribution, and the challenge of automating activities previously performed by human drivers in autonomous vehicles.

Innovation Solution

An autonomous fleet simulation system that models and optimizes the behavior of autonomous vehicles based on real-time data, infrastructure placement, and vehicle status to determine optimal routes, service locations, and vehicle activities, ensuring efficient operation across a geographic region.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Adaptability or versatility

If human operators provide transportation services, then they can operate vehicles with flexibility and decision-making capability, but they cannot efficiently identify high demand areas and optimize vehicle distribution

Engineering Contradiction:

Improvevehicle distribution efficiencyVSAvoiddemand area knowledge

Core Design Contradiction:

Adaptability or versatilityVSLoss of information

Solution Approach 1:

The system performs preliminary actions by collecting and analyzing demand data, identifying high-demand areas in advance, and pre-positioning autonomous vehicles in those areas before demand occurs. This allows the fleet to proactively respond to demand patterns rather than reactively searching for riders.

Inventive Principle:

Principle #10Preliminary action

Solution Approach 2:

The system implements continuous feedback loops where sensor data from autonomous vehicles, ride request data, and demand patterns are constantly monitored and analyzed. This feedback enables dynamic adjustment of vehicle positioning and routing decisions to optimize distribution across the fleet.

Inventive Principle:

Principle #23Feedback

2Productivity

If autonomous vehicles are deployed to replace human operators, then operational efficiency and demand optimization improve, but the complexity of automating driver activities increases

Engineering Contradiction:

Improveoperational efficiencyVSAvoidautomation system complexity

Core Design Contradiction:

ProductivityVSDevice complexity

Solution Approach 1:

The autonomous vehicle system is designed as a multi-functional platform that integrates navigation, sensor processing, ride matching, demand prediction, and fleet coordination capabilities into a single unified system. This universal approach consolidates multiple functions that would otherwise require separate systems.

Inventive Principle:

Principle #6Universality (Multi-functionality)

Solution Approach 2:

The system employs intermediary components such as centralized fleet management servers and communication protocols that mediate between individual autonomous vehicles and the overall fleet optimization goals. These intermediaries simplify the complexity by providing a layered architecture rather than requiring direct peer-to-peer coordination between all vehicles.

Inventive Principle:

Principle #24Intermediary (Mediator)

3Extent of automation

If autonomous vehicles operate independently without centralized coordination, then vehicle autonomy and operational flexibility are maintained, but fleet-wide optimization and resource distribution deteriorate

Engineering Contradiction:

Improvevehicle autonomyVSAvoidfleet distribution optimization

Core Design Contradiction:

Extent of automationVSAdaptability or versatility

Solution Approach 1:

The system merges the decision-making capabilities of individual autonomous vehicles with centralized fleet coordination. Each vehicle maintains its autonomous navigation and sensor processing, while simultaneously integrating with the fleet management system that optimizes overall distribution based on aggregated demand data from all vehicles.

Inventive Principle:

Principle #5Merging (Combining)

Solution Approach 2:

The system adds a temporal and informational dimension to autonomous operation by implementing continuous data exchange between vehicles and the fleet management system. This allows vehicles to operate autonomously in real-time while being guided by fleet-wide optimization strategies that consider demand patterns across the entire service area.

Inventive Principle:

Principle #17Another dimension (Dimensionality change)

Data Source

PatentUS11663915B2Dynamic modeling and simulation of an autonomous vehicle fleet using real-time autonomous vehicle sensor input

Publication Date: 2023.05.30 LYFT INC

AI summary

Embodiments provide techniques for autonomous vehicle fleet modeling and simulation, such as within a dynamic transportation matching system utilizing one or more vehicle types such as non-autonomous vehicles and autonomous vehicles. An autonomous fleet simulation model may be generated based on real-world parameters of an autonomous vehicle fleet, and the parameters may be modified in a simulation in order to determine optimized values that may be applied to the real-world autonomous vehicle fleet.