Autonomous Vehicle Pose Estimation Using Transmission Sensor Data
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Autonomous vehicles face challenges in accurately determining their pose within their surroundings, especially in adverse conditions where primary sensors fail, leading to potential loss of control and safety issues.
Innovation Solution
The method involves generating pose instances using transmission sensor data, which can be used to control the vehicle, even in the absence of primary sensors, by processing data from transmission sensors, steering sensors, and IMU sensors, and utilizing a transmission model to determine steering angles and vehicle properties, allowing for continuous operation or controlled stops as needed.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If primary sensors are used for pose determination, then measurement precision is improved, but reliability deteriorates when sensors fail in adverse conditions
Solution Approach 1:
The system implements a backup pose determination method using transmission sensor data that can be activated before primary sensors fail. By pre-configuring alternative sensing pathways through the transmission system, the vehicle maintains pose determination capability even when primary sensors fail in adverse conditions, thus cushioning against the reliability deterioration.
Solution Approach 2:
The transmission system serves as an intermediary element for pose determination. Instead of relying solely on primary sensors that may fail, the system uses transmission sensor data (rotational speed, gear position) as an intermediate measurement source to infer vehicle pose, providing a redundant pathway that improves reliability without sacrificing measurement precision.
2Reliability
If transmission sensor data is used for pose determination, then reliability is improved during sensor failure, but device complexity increases
Solution Approach 1:
The transmission system, which already exists for power delivery, is given the additional function of pose determination. By utilizing existing transmission sensors (rotational speed sensors, gear position sensors) for dual purposes - both power transmission monitoring and pose determination - the system improves reliability without adding dedicated backup sensor systems, thus avoiding excessive complexity.
Solution Approach 2:
The transmission system serves itself by providing pose determination data from its own sensors. The rotational speed and gear position information, originally collected for powertrain control, are repurposed to determine vehicle pose, allowing the system to improve reliability using its existing components rather than requiring separate backup sensing systems.
3Measurement precision
If multiple sensor data sources are integrated for pose generation, then measurement precision is improved, but difficulty of detecting and measuring increases
Solution Approach 1:
The pose determination process is segmented into distinct functional modules: transmission data processing, IMU data processing, steering data processing, and pose calculation. Each module handles specific sensor data types independently, reducing the complexity of integrating multiple sensor sources by breaking down the overall task into manageable segments that can be processed separately and then combined.
Data Source
AI summary
Systems and methods for using transmission sensor(s) in localization of an autonomous vehicle (“AV”) are described herein. Some implementations receive instance(s) of transmission sensor data generated by transmission sensor(s) of the AV, generate pose instance(s) of a pose of the AV based on the instance(s) of the transmission sensor data, and cause the AV to be controlled based on the pose instance(s). In some of those implementations, the pose instance(s) can be generated based on steering data the AV that indicates steering angle(s) of the autonomous, and that temporally correspond to the instance(s) of the transmission sensor data. In various implementations, the pose instance(s) may only be generated or utilized based on the instance(s) of the transmission sensor data (and optionally the steering data) in response to detecting an adverse event at the AV.