Safe Drivable Area Control Under Dynamic Sensor Coverage Limits

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Autonomous vehicles face challenges in maintaining safe operation under varying environmental conditions due to limitations in sensor performance and perception algorithms, which can lead to reduced effective sensor coverage and increased risk of accidents, especially in adverse weather or obstructed environments.

Innovation Solution

A computer-implemented method dynamically adjusts the effective sensor coverage area by using high-definition maps and multiple sensors to verify object locations, ensuring that critical objects are within the sensor's range, and implements a fail-operational navigation system to safely operate the vehicle by modifying navigation inputs based on safety monitors and sensor performance.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Measurement precision

If AI/machine learning technologies are used to process sensor data, then the autonomous system can perceive the surrounding environment, but the system is slow and does not adapt readily to real-time changes in environmental conditions

Engineering Contradiction:
Improveenvironment perception accuracyVSAvoidreal-time adaptation speed
Core Design Contradiction:
Measurement precisionVSSpeed

Solution Approach 1:

The patent implements dynamic adjustment of sensor coverage areas based on real-time environmental conditions. The system continuously monitors environmental factors (weather, lighting, obstacles) and adapts sensor coverage dynamically rather than using fixed AI models, enabling real-time response to changing conditions while maintaining perception accuracy.

Inventive Principle:
Principle #15Dynamics

Solution Approach 2:

The system incorporates feedback mechanisms where sensor data is continuously processed to update environmental condition assessments, which then feed back into adjusting sensor coverage and navigation decisions. This closed-loop feedback enables rapid adaptation without requiring complete reprocessing by slow AI/machine learning systems.

Inventive Principle:
Principle #23Feedback

2Reliability

If redundant automated driving systems are designed to accomplish fail-operational, then system reliability improves, but device complexity increases

Engineering Contradiction:
Improvefail-operational capabilityVSAvoidsystem architecture complexity
Core Design Contradiction:
ReliabilityVSDevice complexity

Solution Approach 1:

Instead of implementing full redundant automated driving systems, the patent applies partial redundancy by focusing specifically on sensor coverage verification and environmental monitoring functions. This selective approach provides fail-operational capability for critical safety functions without duplicating the entire complex automated driving system.

Inventive Principle:
Principle #16Partial or excessive action

Solution Approach 2:

The patent introduces an intermediary environmental condition monitoring system that acts as a mediator between sensors and the automated driving system. This intermediary layer provides safety verification and fail-operational monitoring without requiring full system redundancy, thereby reducing complexity while maintaining reliability.

Inventive Principle:
Principle #24Intermediary (Mediator)

3Reliability

If sensor coverage is expanded to monitor all areas around the vehicle, then safety monitoring improves, but the system cannot adapt to sensor limitations under adverse environmental conditions

Engineering Contradiction:
Improvesafety monitoring coverageVSAvoidenvironmental condition adaptability
Core Design Contradiction:
ReliabilityVSAdaptability or versatility

Solution Approach 1:

The system dynamically adjusts sensor coverage areas based on real-time environmental conditions and sensor performance verification. Rather than maintaining fixed maximum coverage, the system adapts coverage boundaries to match actual sensor capabilities under current conditions, ensuring reliable monitoring where sensors work effectively while acknowledging limitations in adverse environments.

Inventive Principle:
Principle #15Dynamics

Solution Approach 2:

The patent implements local quality by verifying sensor coverage on a localized basis rather than uniformly across all areas. The system identifies and monitors specific critical zones where sensor performance is verified, allowing high-quality safety monitoring in reliable areas while adapting to limitations in other areas affected by environmental conditions.

Inventive Principle:
Principle #3Local quality

Data Source

PatentUS11402842B2Method to define safe drivable area for automated driving system
Publication Date: 2022.08.02 BAIDU USA LLC
  • US11402842B2 patent drawing
  • US11402842B2 patent drawing
  • US11402842B2 patent drawing

AI summary

Systems and methods are disclosed for dynamically adjusting effective sensor coverage coordinates of a sensor used to assist in navigating an autonomous driving vehicle (ADV) in response to environmental conditions that may affect the ideal operation of the sensor. An ADV includes a navigation system and a safety monitor system that monitors some, or all, of the navigation system, including monitoring: dynamic adjustment of effective sensor coverage coordinates of a sensor and localization of the ADV within a high-definition map. The ADV safety monitor system further determines safety-critical objects surrounding the ADV, determines safe areas to navigate the ADV, and ensures that the ADV navigates only to safe areas. An automated system performance monitor determines whether to pass-through ADV navigation control commands, limit one or more control commands, or perform a fail-operational behavior, based on the ADV safety monitor systems.