Autonomous Vehicle Collision Mitigation via Focused Sensor Steering
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Autonomous vehicle collision mitigation systems face challenges in accurately identifying potential collisions and efficiently controlling the vehicle to avoid them, particularly due to reliance on a single set of sensors and lack of redundancy in data sources.
Innovation Solution
A computer-implemented method and system that utilizes motion plan data to determine a region of interest in the surrounding environment, independent of the autonomy system, to identify potential collisions and control the vehicle by steering sensors to focus on high-risk areas, thereby reducing false positives and improving accuracy through data from separate sensors.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Device complexity
If a single set of sensors is used for collision detection, then the system complexity is reduced, but the reliability and accuracy of collision mitigation deteriorates due to lack of redundancy
Solution Approach 1:
The patent divides the sensor system into two independent segments: first sensors associated with the autonomy system and second sensors associated with the collision mitigation system. This segmentation allows each sensor set to perform specialized functions, with the second sensors providing independent verification and detection capabilities, thereby improving reliability without significantly increasing overall system complexity.
Solution Approach 2:
The collision mitigation system employs sensors with detection parameters specifically optimized for collision detection rather than general autonomy navigation. This local quality optimization ensures that the second sensors are tailored for their specific collision mitigation function, improving detection accuracy and reliability for the critical safety task.
2Area of stationary object
If sensors are directed to monitor the entire surrounding environment, then coverage is maximized, but the accuracy of collision detection in critical areas deteriorates due to dispersed attention
Solution Approach 1:
The system dynamically adjusts sensor detection focus based on the vehicle's motion plan, concentrating sensor attention on regions of interest where collisions are most likely to occur. This local quality adjustment allows the sensors to maintain high detection accuracy in critical areas while still providing sufficient coverage of the broader environment through the autonomy system's first sensors.
Solution Approach 2:
The collision mitigation system receives the motion plan from the autonomy system in advance and uses this information to pre-position sensor attention on upcoming regions of interest. By performing this preliminary orientation based on the planned trajectory, the system ensures that sensors are already focused on critical areas when the vehicle approaches potential collision zones, improving detection accuracy without requiring continuous pan-scanning of the entire environment.
Data Source
AI summary
Systems and methods for controlling an autonomous vehicle are provided. In one example embodiment, a computer-implemented method includes obtaining, from an autonomy system, data indicative of a planned trajectory of the autonomous vehicle through a surrounding environment. The method includes determining a region of interest in the surrounding environment based at least in part on the planned trajectory. The method includes controlling one or more first sensors to obtain data indicative of the region of interest. The method includes identifying one or more objects in the region of interest, based at least in part on the data obtained by the one or more first sensors. The method includes controlling the autonomous vehicle based at least in part on the one or more objects identified in the region of interest.