Autonomous Vehicle Simulation Coverage Across ODD Road Segments

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Training autonomous vehicles (AVs) to handle every possible driving scenario in real environments is expensive, time-consuming, and unscalable due to the vast number of scenes and scene characteristics they may encounter.

Innovation Solution

The use of simulated tests to train AVs, where the coverage of test scenarios is expanded based on an operational design domain (ODD) coverage, allowing for modifications to road segments, weather conditions, and other environmental factors to create diverse training scenarios.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Productivity

If simulated tests are used to train AVs, then training cost and time are reduced, but test coverage completeness may be compromised

Engineering Contradiction:

Improvetraining efficiencyVSAvoidtest coverage completeness

Core Design Contradiction:

ProductivityVSReliability

Solution Approach 1:

The system transforms physical driving scenarios into simulated environments by changing the state from real-world to virtual, while systematically varying parameters such as weather conditions, road types, and traffic patterns to achieve comprehensive coverage of the operational design domain

Inventive Principle:

Principle #35Parameter changes

Solution Approach 2:

The patent creates virtual copies of real driving environments through simulation, replicating road segments, weather conditions, and traffic scenarios to provide extensive training data without the costs and limitations of physical testing

Inventive Principle:

Principle #26Copying

2Adaptability or versatility

If real-world training scenarios are expanded to cover all driving conditions, then training comprehensiveness is improved, but cost and time requirements increase significantly

Engineering Contradiction:

Improvetraining comprehensivenessVSAvoidtraining efficiency

Core Design Contradiction:

Adaptability or versatilityVSProductivity

Solution Approach 1:

The simulation platform serves multiple functions simultaneously: it can replicate various weather conditions, road types, and traffic scenarios within a single system, allowing comprehensive training without requiring multiple physical test environments

Inventive Principle:

Principle #6Universality (Multi-functionality)

Solution Approach 2:

The patent adds the dimension of virtual simulation to the training process, transitioning from single-dimensional real-world testing to multi-dimensional training that includes various simulated conditions that can be systematically varied and controlled

Inventive Principle:

Principle #17Another dimension (Dimensionality change)

Data Source

PatentUS12272188B2Determining a coverage of autonomous vehicle simulation tests

Publication Date: 2025.04.08 GM CRUISE HOLDINGS LLC

AI summary

Systems and techniques are provided for expanding a scope of coverage of test scenarios for training an autonomous vehicle (AV). An example method can include identifying a maneuver of an AV; receiving, from a test repository, a plurality of tests that includes the maneuver; identifying one or more segments on a map of an operational design domain (ODD) that include a driving environment for the maneuver; determining a similarity between a driving scene of each of the plurality of tests and the one or more segments on the map of the ODD; and determining a degree of test coverage for each of the one or more segments for the maneuver based on the determined similarity.