Robot Presence Probability Mapping for Early User Detection
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Robots equipped with sensing devices struggle to autonomously move to a position where they can capture users effectively, such as at the entrance when users return home, due to inefficiencies in obstacle detection and route planning, leading to delayed interactions.
Innovation Solution
The creation of an existence probability map using a combination of sensing devices, intelligence, and a drive system allows a robot to determine optimal positions and times to interact with users by learning their life patterns and adjusting its movement accordingly, enabling early detection and greeting of users.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If the robot sequentially searches for obstacles around the robot and finds an obstacle, then the robot creates a new obstacle occupancy probability table, but the efficiency of the research is poor and calculation of the walking route takes time, causing the walking motion to be delayed
Solution Approach 1:
The robot performs preliminary actions by proactively moving to predetermined arrangement positions and capturing images of users in advance. The image recognition unit continuously recognizes users and updates existence probability maps before interactions are needed, so that when the robot needs to interact with a user, the information is already prepared. This eliminates the need for sequential obstacle-searching behavior and enables immediate response to users.
2Device complexity
If the robot is located at a predetermined arrangement position, then the robot structure is simple, but the user cannot be imaged and captured unless the user approaches a sensable position, causing delayed user detection
Solution Approach 1:
The robot dynamically changes its position based on learned user patterns and predicted user locations. Instead of remaining static at predetermined positions, the robot moves to arrangement positions that maximize the probability of capturing users, such as moving to the entrance when a user is expected to return home. This dynamic positioning enables early user detection while maintaining relatively simple system architecture.
Solution Approach 2:
The system adds the time dimension to the spatial positioning problem by creating existence probability maps that evolve over time based on user life patterns. The robot doesn't just consider spatial arrangement positions but also temporal patterns of user behavior, selecting positions and times that optimize user capture probability. This transforms the problem from a static spatial issue to a spatio-temporal optimization problem.
Data Source
Figure 1
Figure 2
Figure 3
AI summary
An agent includes a sensing device configured to sense an opject in a real space, an existence probability map creation means configured to define the real space as a group of voxels, and create, every predetermined time, an existence probability map on which information of an existence probability of the object is recorded for each of the voxels, and an arrangeable position storage unit configured to store information of an arrangeable position.