Mining Vehicle Sensor Fusion for Sparse Obstacle Detection
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Obstacle detection in underground mining environments is challenging due to constantly varying circumstances, leading to sparse measurement data that makes it difficult to detect obstacles such as potholes or voids effectively.
Innovation Solution
An apparatus and method for combining measurement data from different time instances by transforming it into a common coordinate frame based on the vehicle's transition, thereby increasing data density and accuracy for obstacle detection systems.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If measurement data is collected at different time instances separately, then the obstacle detection system can process current data, but the data density remains sparse and obstacle detection accuracy deteriorates
Solution Approach 1:
The patent combines measurement data from multiple time instances into a single integrated data set. By merging historical measurement data with current measurement data, the system increases data density and improves obstacle detection accuracy. The combining module integrates these data sets while accounting for vehicle transitions to create a comprehensive view of the environment.
Solution Approach 2:
The system performs preliminary processing of measurement data by transforming historical data into the coordinate frame of current data before combining. This preliminary transformation action ensures that data from different time instances can be properly integrated, preparing the data for effective combination and analysis in the obstacle detection system.
2Quantity of substance
If measurement data from different time instances is combined without coordinate transformation, then data quantity increases, but measurement precision deteriorates due to coordinate frame mismatches
Solution Approach 1:
The patent introduces a coordinate transformation process as an intermediary step between data collection and data combination. The determining module calculates vehicle transitions (position and orientation changes) that serve as intermediary parameters. These transformations act as mediators that align historical data with the current coordinate frame, enabling accurate integration of data from different time instances without coordinate mismatches.
3Reliability
If the obstacle detection system processes only current measurement data, then processing complexity remains low, but detection reliability deteriorates in constantly varying environments
Solution Approach 1:
The system dynamically adapts to changing environmental conditions by incorporating historical measurement data that captures the evolving environment. The determining module calculates vehicle transitions to account for dynamic changes in position and orientation. This dynamic approach allows the system to maintain reliable obstacle detection in constantly varying mining environments by considering both historical context and current conditions.
Data Source
AI summary
An apparatus, method and computer program product for: receiving a first set of measurement data relating to an environment of the mobile mining vehicle at a first time instance, receiving a second set of measurement data relating to the environment of the mobile mining vehicle at a second time instance, determining a transition of the mobile mining vehicle between the first time instance and the second time instance, forming a combined set of measurement data by transforming the first set of measurement data to a coordinate frame of the second set of measurement data based on the transition of the mobile mining vehicle, and providing the combined set of measurement data to an obstacle detection system of the mobile mining vehicle.