Autonomous Vehicle Road Grade Prediction Using Sensor Fusion
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Conventional methods for estimating road grade, such as satellite navigation and inertial measurement units, provide inaccurate results, especially in urban environments, affecting the navigation and energy efficiency of autonomous vehicles.
Innovation Solution
Utilizing engine power requirements, LiDAR sensors, and image sensors to estimate road grade by compensating for factors like vehicle load and wind resistance, combined with sensor data to generate digital surface models for accurate road gradient prediction.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Device complexity
If satellite navigation systems (GPS) are used to estimate road grade, then the system is simple to implement, but measurement precision deteriorates in urban environments where signal reception is impaired
Solution Approach 1:
The patent combines multiple measurement approaches (GPS data, IMU data, and engine performance data) to estimate road grade. By merging these different data sources, the system overcomes the limitations of individual methods - GPS provides broad coverage but fails in urban canyons, IMU accumulates errors over time, while engine performance data provides continuous accurate measurements that compensate for the weaknesses of each individual system.
Solution Approach 2:
The patent introduces engine performance parameters (power output, fuel injection amount, throttle position) as an intermediary measurement method. These engine parameters serve as a mediator between direct GPS/IMU measurements and road grade estimation, providing an alternative measurement path that is not affected by satellite signal blockage or sensor drift accumulation.
2Duration of action of moving object
If inertial measurement units (IMU) are used to estimate road grade, then the system provides continuous measurements, but reliability deteriorates due to accumulation of errors and noise over time
Solution Approach 1:
The patent implements a feedback mechanism where engine performance data continuously monitors and corrects the road grade estimates. The engine parameters provide real-time feedback that counteracts the accumulation of errors in IMU measurements, maintaining reliability over extended periods without requiring external reference updates.
Solution Approach 2:
The patent performs preliminary calibration by establishing the relationship between engine performance parameters and road grade under known conditions. This preliminary action creates a reference model that can be applied continuously, allowing the system to maintain accurate measurements over time by comparing current engine performance against the calibrated relationship.
3Measurement precision
If engine power requirements are used to determine road grade, then measurement precision improves, but device complexity increases due to multiple sensors and processing requirements
Solution Approach 1:
The patent leverages the universality of engine performance data, which serves multiple functions: it directly indicates road grade through power requirements, provides information about vehicle load conditions, and helps distinguish between grade-induced power changes and other operational factors. This multi-functional use of engine data maximizes measurement precision without proportionally increasing system complexity.
Solution Approach 2:
The patent transforms engine performance parameters (fuel injection amount, throttle position, power output) into road grade estimates through mathematical relationships. By changing the parameter representation from raw engine data to derived road grade information, the system achieves high measurement precision while using standard engine sensors already present in modern vehicles.
4Measurement precision
If LiDAR and image sensors are used to generate digital surface models, then measurement precision improves for road geometry, but use of energy increases due to additional sensing and processing requirements
Solution Approach 1:
The patent applies partial action by using LiDAR and image sensors only when needed for specific tasks (such as initializing the grade estimation or verifying results) rather than continuously. This selective application provides high measurement precision when required while minimizing energy consumption during normal operation where engine data alone suffices.
Data Source
AI summary
Systems and methods of predicting a grade of a road upon which a vehicle is traveling are disclosed. An autonomous vehicle system can receive sensor data from a sensor measuring a response from at least one mechanical component of the autonomous vehicle as the autonomous vehicle navigates a road; detect a speed of the autonomous vehicle; determine a predicted grade of the road based on the sensor data and the speed; and navigate the autonomous vehicle based on the predicted grade of the road.