Robot Map Creation Using Object Mobility Classification
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Robots operating in dynamic environments like airports and train stations face challenges in distinguishing between fixed and moving objects, which hinders their ability to create accurate maps and perform functions effectively due to continuous changes in the space.
Innovation Solution
A robot equipped with a LiDAR sensor and a control unit that calculates the mobility of sensed objects, storing information about fixed objects in a map storage unit and moving objects in a separate storage unit, allowing the robot to differentiate and manage the two types of objects based on their mobility values.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Loss of information
If the robot accumulates information on all sensed objects in a dynamic environment, then the map completeness is improved, but the difficulty of distinguishing fixed objects from moving objects increases
Solution Approach 1:
The patent applies the dynamics principle by introducing a mobility value that can change over time. Objects are initially classified as moving when first detected, and their mobility value is updated continuously based on whether they are detected in subsequent frames. This dynamic classification allows the system to adapt to objects that may transition from moving to fixed state, resolving the contradiction by providing a mechanism to distinguish object types based on temporal behavior patterns.
Solution Approach 2:
The patent uses parameter changes by modifying the mobility value parameter based on detection history. When an object is first sensed, it is assigned a mobility value indicating it is moving. If the object is not detected in subsequent sensing operations, the mobility value is updated to indicate a fixed object. This parameter transformation enables automatic differentiation between fixed and moving objects, improving classification accuracy while maintaining complete object information in the map.
2Measurement precision
If the robot stores separate information for fixed and moving objects, then the map accuracy is improved, but the device complexity increases
Solution Approach 1:
The patent applies the merging principle by integrating fixed object information and moving object information into a single unified map data structure. Instead of maintaining completely separate storage systems, the patent uses a common map where each object is represented with associated mobility information. This approach maintains map accuracy by preserving distinctions between fixed and moving objects while reducing overall system complexity through unified data management.
Solution Approach 2:
The patent implements universality by creating a multi-functional map structure that can handle both fixed and moving objects using the same basic data framework. The map serves multiple purposes: storing object positions, maintaining mobility information, and supporting navigation for both static and dynamic environments. This universal structure eliminates the need for separate specialized storage systems, thereby reducing device complexity while maintaining high map accuracy.
3Measurement precision
If the robot continuously senses objects to update mobility information, then the mobility detection accuracy is improved, but the energy consumption increases
Solution Approach 1:
The patent applies periodic action by implementing continuous sensing operations at regular intervals to update mobility information. The sensing unit periodically detects objects and updates their mobility values based on whether they are detected in the current sensing cycle. This periodic sensing approach maintains high mobility detection accuracy by continuously monitoring object positions while managing energy consumption through structured, interval-based operation rather than constant active sensing.
Solution Approach 2:
The patent implements self-service by designing the sensing system to automatically update mobility information based on detection results without requiring additional processing or intervention. When an object is detected, the system automatically updates its mobility value; when not detected, the object is reclassified as fixed. This self-updating mechanism maintains high detection accuracy while minimizing energy consumption by eliminating redundant processing steps and allowing the system to operate autonomously based on sensor feedback.
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
Enables the robot to create accurate maps by distinguishing between fixed and moving objects, allowing it to navigate and perform functions without obstruction, even in high-traffic areas by accurately identifying and managing dynamic obstacles.
Implementation Method 1
a sensing unit that senses a first object located outside the robot
Data Source
AI summary
The present disclosure relates to creating a map by identifying a moving object, and a robot implementing the method, and the method comprises, by a sensing unit of a robot, sensing a first object located outside the robot, by a control unit of the robot, calculating mobility of the sensed first object, and storing sensed information and sensed time information of the first object in a map, as a fixed object, when the mobility of the first object calculated by the control unit of the robot is lower than a preset reference.