Hybrid Laser Stereo Sensor Fusion for AGV Obstacle Detection
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current obstacle detection systems for autonomous guided vehicles (AGVs) face challenges with planar LIDAR sensors, which fail to detect overhanging obstacles and have high costs and poor performance, while stereo sensors struggle with short-range object detection due to limited field of view.
Innovation Solution
Combining laser sensors and stereo sensors on AGVs, where laser sensors detect objects within a short range and stereo sensors cover a wider area beyond their range, with overlapping regions for comprehensive obstacle detection, enabling effective navigation instructions for the AGV.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Length of stationary object
If planar LIDAR sensors are used for obstacle detection, then detection range is extended, but detection accuracy deteriorates due to failure to detect overhanging obstacles and high costs
Solution Approach 1:
The patent combines planar LIDAR sensors with stereo sensors to create a hybrid detection system. The LIDAR provides long-range detection while stereo sensors detect overhanging obstacles at closer ranges, merging the advantages of both sensor types to achieve both extended range and improved accuracy.
Solution Approach 2:
The detection space is segmented into different zones: long-range detection handled by LIDAR and short-range overhanging obstacle detection handled by stereo sensors. This segmentation allows each sensor type to operate in its optimal detection zone, resolving the contradiction between range and accuracy.
2Reliability
If stereo sensors are used for obstacle detection, then cost is reduced and performance is improved, but detection capability deteriorates at short ranges due to limited field of view
Solution Approach 1:
The system merges stereo sensors with complementary laser sensors to overcome the limited field of view of stereo sensors alone. The laser sensors provide additional coverage in areas where stereo sensors have blind spots, particularly at short ranges, while maintaining the cost-effectiveness of stereo technology.
Solution Approach 2:
Laser sensors act as intermediaries that bridge the gap in detection capability between stereo sensors and more expensive LIDAR systems, providing the additional short-range and blind-spot coverage needed without fully adopting expensive LIDAR technology.
3Device complexity
If single sensor systems are used, then device complexity is reduced, but obstacle detection capability deteriorates due to inability to cover both short-range and long-range areas
Solution Approach 1:
The patent merges complementary sensor types (stereo and laser) into an integrated detection system. This combination allows the system to cover both short-range and long-range detection needs with improved accuracy while maintaining manageable complexity through unified processing architecture.
Solution Approach 2:
The combined sensor system provides multi-functional detection capabilities, handling both near-field and far-field obstacles with a single integrated system rather than requiring separate specialized systems, thus improving detection capability without proportionally increasing complexity.
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 combined system enhances obstacle detection capabilities, ensuring safe navigation by covering both short-range and long-range areas with improved accuracy and cost-effectiveness compared to single-sensor systems.
Implementation Method 1
laser sensors detect objects within a short range
Implementation Method 2
stereo sensors cover a wider area beyond their range
Data Source
AI summary
An example system includes one or more laser sensors on a robotic device, where the one or more laser sensors are configured to produce laser sensor data indicative of a first area within a first distance in front of the robotic device. The system further includes one or more stereo sensors on the robotic device, where the stereo sensors on the robotic device are configured to produce stereo sensor data indicative of a second area past a second distance in front of the robotic device. The system also includes a controller configured to receive the laser sensor data, receive the stereo sensor data, detect one or more objects in front of the robotic device based on at least one of the laser sensor data and the stereo sensor data, and provide instructions for the robotic device to navigate based on the one or more detected objects.