Collaborative Sensor Calibration for Moving Autonomous Vehicles
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current autonomous driving technologies do not adequately address the unique challenges of sensor calibration and truck-trailer configuration awareness, particularly in scenarios where real-time recalibration and precise positioning are crucial for safe navigation, especially in trucks and truck fleets where traditional methods fail to ensure accurate obstacle avoidance and lane maintenance.
Innovation Solution
A method and system for collaborative sensor calibration on-the-fly using assisting vehicles or landmarks, allowing for dynamic recalibration of sensors while in motion, and fiducial marker-based estimation to monitor and control truck-trailer configurations, ensuring accurate sensor data and safe vehicle control.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If traditional sensor calibration methods are used, then calibration accuracy is improved, but the vehicle must stop and calibration time increases
Solution Approach 1:
The patent enables dynamic sensor calibration by allowing the ego vehicle to move during the calibration process rather than requiring it to stop. The calibration is performed while the vehicle is in motion, with the assisting vehicle dynamically adjusting its position to maintain the required geometric relationship for calibration.
Solution Approach 2:
The patent introduces an assisting vehicle as an intermediary object that facilitates the calibration process. This assisting vehicle serves as a movable reference target that can be positioned optimally to enable calibration while the ego vehicle is moving, thus mediating between the need for accuracy and the need to maintain motion.
2Productivity
If the ego vehicle moves during calibration, then productivity is improved, but calibration reliability deteriorates
Solution Approach 1:
The assisting vehicle acts as a stable intermediary reference that remains controllable even while the ego vehicle moves. This mediator provides a reliable calibration target that compensates for the motion of the ego vehicle, maintaining calibration reliability despite the vehicle's movement.
Solution Approach 2:
The system uses real-time feedback by continuously monitoring the relative positions and orientations of the ego vehicle and assisting vehicle. This feedback allows for dynamic adjustments to maintain the geometric relationships required for accurate calibration while the ego vehicle is in motion.
3Adaptability or versatility
If collaborative calibration with assisting vehicles is implemented, then calibration flexibility is improved, but system complexity increases
Solution Approach 1:
The assisting vehicle is designed with multi-functionality, serving both as a calibration target and as a communicative partner in the calibration process. It can display calibration patterns and communicate its position and status, consolidating multiple functions into a single system component to manage complexity.
Solution Approach 2:
The system enables self-service calibration by allowing vehicles to perform calibration autonomously without requiring external equipment or manual intervention. The assisting vehicle and ego vehicle cooperate autonomously to complete the calibration process, reducing the need for external calibration equipment and simplifying the overall system.
Data Source
AI summary
The present teaching relates to method, system, medium, and implementations for sensor calibration. A request is received from an ego vehicle in motion for assistance in collaborative calibration, when the ego vehicle determines that a sensor deployed thereon needs to be calibrated. The request includes at least one of a first position of the ego vehicle and a first configuration of the sensor with respect to the ego vehicle. An assisting vehicle is identified based on the first position, the first configuration, and a second position associated with the assisting vehicle and an assistance plan is generated in response to the request indicative of the assisting vehicle to travel to the ego vehicle to facilitate the calibration of the sensor by collaborating with the moving ego vehicle. Such generated assistance plan is then sent out to initiate the collaborative calibration.