Close-In Camera and LiDAR Layout for Vehicle Blind Spot Sensing
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Autonomous vehicles face blind spots and occlusions in their sensor fields of view, which can impact driving decisions and operations, particularly for objects immediately adjacent to the vehicle.
Innovation Solution
An integrated sensor system comprising a lidar sensor and an image sensor, with an overlapping field of view, is used to detect and classify objects within a threshold distance of the vehicle, employing a control system to process lidar and image data for precise vehicle operations.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If sensors are positioned to detect objects in the external environment, then object detection capability is improved, but blind spots and occlusions occur that reduce detection reliability
Solution Approach 1:
The patent combines multiple sensor types (lidar and image sensors) into an integrated sensor system with overlapping fields of view. This merging allows the system to detect objects using both lidar data and image data, where the image sensor provides visual confirmation for objects detected by lidar, thereby eliminating blind spots and occlusions that would otherwise reduce detection reliability
Solution Approach 2:
The image sensor acts as an intermediary that provides additional information about objects detected by the lidar sensor. When lidar detects an object, the image sensor captures visual data that mediates the classification process, allowing the control system to determine whether the object is driveable or non-driveable with higher reliability
2Reliability
If multiple sensors are integrated to reduce blind spots, then detection coverage is improved, but system complexity increases
Solution Approach 1:
The patent integrates multiple sensor types (lidar and image sensors) into a unified sensor system with overlapping fields of view. This merging approach improves detection coverage by eliminating blind spots while managing complexity through integrated housing and coordinated operation controlled by a single control system that processes both lidar and image data together
3Measurement precision
If high resolution imaging is used to classify objects, then classification accuracy is improved, but processing time increases
Solution Approach 1:
The patent applies partial action by using image sensors to capture images of objects for classification purposes. The control system processes image data to classify objects as driveable or non-driveable, applying classification only where needed (for objects detected by lidar) rather than continuously processing all sensor data at high resolution, thus balancing accuracy with processing time constraints
Applied Scientific Principles
This section explains which scientific principles are used to turn an abstract innovation direction into a practical engineering solution.
Function Achieved in This Case
The system effectively classifies objects as driveable or non-driveable, enhancing the vehicle's ability to make informed driving decisions by minimizing blind spots and occlusions, thereby improving safety and operation in autonomous modes.
Implementation Method 1
The lidar sensor has a field of view configured to detect objects in at least a given region of an external environment around the vehicle and within a threshold distance of the vehicle
Implementation Method 2
The image sensor is disposed adjacent to the lidar sensor and arranged along the vehicle to have an overlapping field of view of the region of the external environment within the threshold distance of the vehicle
Data Source
AI summary
The technology relates to an exterior sensor system for a vehicle configured to operate in an autonomous driving mode. The technology includes a close-in sensing (CIS) camera system to address blind spots around the vehicle. The CIS system is used to detect objects within a few meters of the vehicle. Based on object classification, the system is able to make real-time driving decisions. Classification is enhanced by employing cameras in conjunction with lidar sensors. The specific arrangement of multiple sensors in a single sensor housing is also important to object detection and classification. Thus, the positioning of the sensors and support components are selected to avoid occlusion and to otherwise prevent interference between the various sensor housing elements.