Autonomous Vehicle Obstacle Perception Calibration via Vertical Acceleration
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Autonomous driving vehicles face challenges in accurately perceiving obstacles due to the complexity of their surroundings and limitations of perception sensors like LIDAR and cameras, leading to uncertainties in prediction, planning, and control modules.
Innovation Solution
The use of additional sensors such as IMU, GPS, tire pressure sensors, and dynamic suspension system sensors to measure vertical acceleration, which is used as an input for auto-correction in the obstacle perception system, improving the accuracy of obstacle detection and shape determination by compensating for sensor inaccuracies.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If additional sensors (IMU, GPS, tire pressure sensors, dynamic suspension system sensors) are used to measure vertical acceleration for auto-correction, then measurement precision of obstacle perception is improved, but device complexity increases
Solution Approach 1:
The patent combines multiple existing vehicle sensors (IMU, GPS, tire pressure sensors, dynamic suspension system sensors) into an integrated obstacle perception calibration system. These sensors are merged to collectively measure vertical acceleration, which is then used to calibrate and correct obstacle perception data from primary perception sensors, thereby improving measurement precision while utilizing already-present hardware components.
2Reliability
If vertical acceleration measurement is used to correct obstacle perception, then reliability of obstacle detection is improved, but loss of time for calibration processing increases
Solution Approach 1:
The system performs preliminary calibration by continuously measuring vertical acceleration through the integrated sensor system and using this data to pre-correct obstacle perception parameters before they are used in navigation decisions. This preliminary action ensures that obstacle detection reliability is maintained without requiring time-consuming post-processing calibration, as the correction is applied in real-time alongside primary perception data.
Data Source
AI summary
In one embodiment, an autonomous driving system of an autonomous driving vehicle perceives a driving environment surrounding the autonomous driving vehicle traveling along a path, including perceiving an obstacle in the driving environment. The system detects a vertical acceleration of the autonomous driving vehicle based on sensor data obtained from a sensor on the autonomous driving vehicle. The system further calibrates the perceived obstacle based on the vertical acceleration of the autonomous driving vehicle. The system then controls the autonomous driving vehicle to navigate through the driving environment in view of the calibrated perceived obstacle.