In-Motion Sensor Calibration Using Road-Derived Targets
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Traditional autonomous vehicle sensor calibration processes require the vehicle to be stationary and surrounded by calibration targets, limiting the ability to maintain accurate calibration while the vehicle is in motion or on the road.
Innovation Solution
The system dynamically detects and corrects sensor calibration by generating a calibration target from real-time sensor data, such as lane lines, while the vehicle is in motion, allowing for continuous monitoring and adjustment of sensor alignment.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If traditional calibration process is used with vehicle stationary on rotating substrate, then sensor calibration accuracy is improved, but vehicle operational time is reduced and calibration frequency increases
Solution Approach 1:
The calibration system transitions from a static process (vehicle stationary on rotating substrate) to a dynamic process (vehicle moving on road). The system performs calibration while the vehicle is in motion by using road features such as lane markings as calibration targets, eliminating the need to stop the vehicle for calibration.
Solution Approach 2:
The vehicle performs calibration autonomously using its own sensors and environmental features (road markings, signs, etc.) as calibration targets. The system self-calibrates by detecting calibration targets in the environment and computing sensor parameters without external intervention or specialized calibration equipment.
2Measurement precision
If traditional calibration process is used with rotating substrate and calibration targets, then sensor calibration is achieved, but device complexity and infrastructure requirements increase
Solution Approach 1:
The system extracts calibration functionality from a specialized controlled environment (calibration room with rotating substrate and targets) and integrates it into the vehicle's normal operational environment. The calibration process is decoupled from specialized infrastructure and performed using everyday road features.
Solution Approach 2:
The vehicle's sensors serve dual purposes: they capture data for both navigation/operation and calibration. The same cameras and lidars used for autonomous driving also detect calibration targets and compute sensor parameters, eliminating the need for dedicated calibration equipment.
3Reliability
If continuous monitoring of sensor calibration is performed, then calibration accuracy is maintained, but computational load and processing requirements increase
Solution Approach 1:
Instead of continuous calibration processing, the system performs calibration monitoring periodically or event-driven. The system can trigger calibration when specific conditions are met, such as detecting calibration targets in the environment, rather than continuously processing calibration data at all times.
Data Source
AI summary
Provided are systems and methods for detecting a vehicle with sensors that are not calibrated properly and calibrating such sensor in real-time. In one example, a method may include iteratively capturing sensor data of a road while the vehicle is travelling on the road; monitoring a calibration of the sensors of the vehicle based on the sensor data, determining that the sensors of the vehicle are not calibrated properly based on the monitoring, generating a calibration target of an object on the road based on the sensor data, and adjusting a calibration parameter of the one or more sensors of the vehicle based on the generated calibration target.