Vehicle Routing for Targeted Scenario Capture and Evaluation

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Conventional approaches for testing vehicle responses to targeted scenarios are inefficient and ineffective, particularly for rare or dynamic scenarios, as they rely on human drivers to locate and recreate specific conditions, which is time-consuming and challenging due to the dynamic nature of real-world environments.

Innovation Solution

A system and method that determine a mission for a vehicle to encounter a targeted scenario, route the vehicle to a location likely to encounter that scenario based on historical sensor data, and evaluate the encounter using machine learning models to assess whether the scenario was successfully encountered, allowing for efficient rerouting if not met.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Ease of manufacture

If human drivers are used to locate and recreate specific scenarios for testing, then the testing process can be performed with simple equipment, but the time and effort required increases significantly

Engineering Contradiction:

Improvetesting process simplicityVSAvoidtime to locate and recreate scenarios

Core Design Contradiction:

Ease of manufactureVSLoss of time

Solution Approach 1:

The system enables autonomous vehicles to independently locate and encounter targeted scenarios without human intervention. The vehicle's computing system automatically processes sensor data, identifies scenario locations based on historical data, navigates to those locations, and evaluates encounters, making the testing process self-service and eliminating the time-consuming manual search and recreation process

Inventive Principle:

Principle #25Self-service

Solution Approach 2:

The patent replaces the mechanical approach of human drivers manually locating and recreating scenarios with an automated computing system that uses sensor data processing, historical data analysis, and autonomous navigation to identify and encounter scenarios, substituting human mechanical effort with electronic and computational systems

Inventive Principle:

Principle #28Mechanics substitution (Replace mechanical system)

2Ease of manufacture

If conventional methods are used to test vehicle responses to rare scenarios, then the testing approach is simple to implement, but the effectiveness decreases for rare or dynamic scenarios

Engineering Contradiction:

Improvetesting approach simplicityVSAvoidtesting effectiveness for rare scenarios

Core Design Contradiction:

Ease of manufactureVSReliability

Solution Approach 1:

The system performs preliminary actions by collecting and analyzing historical sensor data before actual testing occurs. The computing system identifies locations where rare scenarios have previously occurred and stores this information, enabling the vehicle to proactively navigate to these locations and encounter the rare scenarios during designated testing missions rather than relying on chance encounters

Inventive Principle:

Principle #10Preliminary action

Solution Approach 2:

The patent introduces historical sensor data as an intermediary between the testing objective and the actual scenario encounter. This intermediary data layer guides the vehicle to locations where targeted scenarios are likely to occur, increasing the probability of encountering rare scenarios while maintaining a systematic and reproducible testing approach

Inventive Principle:

Principle #24Intermediary (Mediator)

3Reliability

If vehicles navigate to locations based on historical scenario data, then the likelihood of encountering targeted scenarios increases, but the routing complexity increases

Engineering Contradiction:

Improvelikelihood of encountering targeted scenarioVSAvoidrouting system complexity

Core Design Contradiction:

ReliabilityVSDevice complexity

Solution Approach 1:

The computing system performs multiple functions using the same historical data: it identifies scenario locations, determines routing paths, evaluates encounters, and updates the historical database. This multi-functionality reduces the need for separate specialized systems for each task, managing complexity through integrated processing while maintaining high reliability in scenario encounter rates

Inventive Principle:

Principle #6Universality (Multi-functionality)

4Device complexity

If manual evaluation of sensor data is used to determine scenario encounters, then the system complexity remains low, but the accuracy and efficiency of scenario detection decreases

Engineering Contradiction:

Improveevaluation system complexityVSAvoidscenario detection accuracy

Core Design Contradiction:

Device complexityVSMeasurement precision

Solution Approach 1:

The patent replaces manual evaluation of sensor data with automated computing systems that process sensor data to determine whether targeted scenarios were encountered. This substitution of human manual analysis with electronic data processing significantly improves detection accuracy and efficiency while managing complexity through algorithmic automation

Inventive Principle:

Principle #28Mechanics substitution (Replace mechanical system)

Data Source

PatentUS11928557B2Systems and methods for routing vehicles to capture and evaluate targeted scenarios

Publication Date: 2024.03.12 LYFT INC

AI summary

Systems, methods, and non-transitory computer-readable media can be configured to determine a targeted scenario and a mission associated with the targeted scenario. A route to a location associated with the mission can be determined based at least in part on a likelihood of encountering the targeted scenario, wherein the likelihood of encountering the targeted scenario is based at least in part on a frequency with which scenarios similar to the targeted scenario were encountered at the location. Whether the targeted scenario was encountered can be determined based on an evaluation of captured sensor data associated with the mission upon passing the location.