Implicit Free Space Detection Using Unobstructed Sensor Sightlines
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing automated driving systems (ADS) face challenges in accurately and reliably determining free space in front of a vehicle, leading to unnecessary stops or speed reductions due to insufficient sensor data, especially in adverse weather conditions.
Innovation Solution
Implementing an implicit free space detection method that identifies and locates target object types using unobstructed lines of sight between vehicle sensors and object instances, allowing for the determination of free space even in conditions where explicit detection is unreliable.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If explicit object detection methods are used to determine free space, then measurement precision is improved, but reliability deteriorates under adverse weather conditions
Solution Approach 1:
Instead of directly detecting free space by analyzing road surface sections, the patent inverts the approach by detecting objects and then determining free space as the complement. The system detects target objects using multiple sensors and defines free space as areas not occupied by detected objects, thereby improving reliability when direct detection fails under adverse conditions.
Solution Approach 2:
The patent employs multiple sensors (cameras, radar, LIDAR) that can serve multiple functions. These sensors not only detect objects for free space determination but also provide backup detection capabilities under different weather conditions, enhancing the system's reliability through multi-functional sensor utilization.
2Reliability
If sensor data is insufficient for guaranteeing non-presence of objects, then vehicle operation is restricted (stops or reduced speed), but detection range is reduced
Solution Approach 1:
The patent combines data from multiple sensors (camera, radar, LIDAR) to create a comprehensive view of the environment. By merging sensor data, the system achieves reliable object detection over extended ranges, allowing the vehicle to maintain higher speeds without compromising safety, as the combined sensor information compensates for individual sensor limitations.
3Reliability
If more sensors are added to improve free space detection, then reliability is improved, but device complexity increases
Solution Approach 1:
The patent implements a sensor fusion system that processes data from multiple sensors but only activates full multi-sensor operation when needed. During normal conditions, the system may rely on primary sensors, activating additional sensors and full fusion processing only when detection uncertainty arises, thereby maintaining reliability while reducing average system complexity.
Data Source
Figure 1~2
Figure 3~4
Figure 5
AI summary
A method for determining a free space (218, 220, 222, 224, 300, 302, 400) adjacent to a vehicle is disclosed. The vehicle comprises one or more sensors (324) arranged to detect objects adjacent to the vehicle and an apparatus (10) for processing sensor data. The method comprises obtaining (S102) target object data defining one or more target object types to detect, obtaining (S104) the sensor data from the one or more sensors, detecting (S106) one or more instances of the target object types in the sensor data, determining (S108) spatial location data for the one or more instances of the object types, wherein the spatial location data comprises instance location data sets defining positions of the instances, respectively, and determining (S110) the free space implicitly as a space between the vehicle and the instance location data sets by determining (5112) one or more unobstructed line of sights between the sensors of the vehicle and the instance location data sets, and generating (S114) the free space by combining the one or more unobstructed line of sights.