Load Handling Vehicle Localization Using Synchronized Image and Range Sensing
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Localization of load handling vehicles in uncertain or uncontrolled environments is challenging, particularly in navigating safely to a load target with potential large uncertainties in target position, which affects the guidance and operation of semi-autonomous and autonomous load handling systems.
Innovation Solution
A controller system that generates a spatial map of the surroundings using sensor data from multiple systems, synchronizing point clouds and images to accurately localize the vehicle and load target, plan trajectories, and update positions and paths in real-time, even in the presence of uncertainties or sensor failures.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Extent of automation
If a load handling vehicle operates in an uncertain or uncontrolled environment, then the vehicle can perform autonomous or semi-autonomous operations, but the localization accuracy deteriorates due to large uncertainties in target position
Solution Approach 1:
The patent combines data from multiple sensor systems (LIDAR, cameras, GPS, inertial sensors) to create a unified localization solution. By merging information from these different sources, the system achieves reliable localization in uncertain environments where individual sensors would be insufficient, thus enabling autonomous operation while maintaining acceptable localization accuracy.
Solution Approach 2:
The patent introduces a spatial map as an intermediary representation that mediates between sensor data and vehicle localization. The spatial map serves as a reference framework that allows the system to determine vehicle position and target position relative to a common coordinate system, improving localization accuracy in uncontrolled environments.
2Measurement precision
If multiple sensor systems are used to improve localization accuracy, then measurement precision improves, but device complexity increases
Solution Approach 1:
The spatial map serves multiple functions: it stores environmental geometry, provides a reference coordinate system for localization, enables target identification, and supports path planning. This multi-functionality reduces the need for separate specialized systems, thereby managing complexity while maintaining high localization accuracy.
Solution Approach 2:
The system continuously updates the spatial map and vehicle localization based on incoming sensor data, creating a feedback loop that refines localization accuracy over time. This iterative process allows the system to adapt to environmental uncertainties and improve measurement precision without requiring overly complex hardware.
3Productivity
If real-time localization and path planning are performed, then productivity improves, but computational requirements and processing time increase
Solution Approach 1:
The system performs preliminary actions by continuously building and updating the spatial map as the vehicle moves, rather than creating it from scratch when needed. This pre-computation of environmental data reduces the processing time required for real-time localization and path planning, thereby improving productivity without excessive computational delays.
Solution Approach 2:
The localization and path planning processes are segmented into discrete computational steps: spatial map updates, vehicle localization calculation, target identification, and trajectory generation. This segmentation allows for optimized processing of each individual task and enables parallel computation where possible, reducing overall processing time while maintaining real-time performance.
Data Source
Figure 1
Figure 2
Figure 3
AI summary
A method for localizing a load handling vehicle and a load target whereby : - a spatial map describing a surrounding of the load handling vehicle is obtained. - First sensor signals are received from a first sensor system for generating point clouds of the surrounding of the load handling vehicle and second sensor signals are received from a second sensor system for generating images of the surrounding of the load handling vehicle. The second sensor signals are synchronized in time with the first sensor signals. The load handling vehicle and the load target are localized in the spatial map based on the first sensor signals and the second sensor signals.