Elevator Scheduling With 3D Passenger Group Tracking
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing elevator scheduling systems struggle with inefficiencies due to intentional misuse of interactive input devices and the inability to accurately account for group dynamics, leading to suboptimal allocation of elevator cars and reduced efficiency.
Innovation Solution
Implementing 3D depth sensing and hierarchical agglomerative clustering to detect, track, and group passengers, allowing for intelligent elevator scheduling that adjusts assignments based on actual group dynamics and individual interactions.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If traditional elevator scheduling systems rely on interactive input devices for call requests, then the system can receive explicit user requests, but the system becomes vulnerable to intentional misuse and cannot accurately detect actual group dynamics
Solution Approach 1:
The patent introduces sensors (cameras, depth sensors, RFID readers) as intermediary devices that detect user presence, group formation, and intent without requiring direct interaction with input devices. These sensors mediate between users and the scheduling system, providing reliable data about actual user needs while bypassing the vulnerability of manual input devices to misuse.
Solution Approach 2:
The patent replaces the mechanical interaction system (physical buttons, cards, or mobile device inputs) with optical and electromagnetic sensing systems. Cameras and depth sensors detect user presence and group dynamics automatically, while RFID readers identify users without physical contact, eliminating the need for users to manually interact with vulnerable input devices.
2Productivity
If the system tracks individual users separately, then it can process each user's request independently, but it fails to account for group dynamics and results in suboptimal elevator allocation
Solution Approach 1:
The patent merges individual user tracking with group detection by using sensors to identify when users are physically close to each other and likely traveling together. The system combines individual request data with group composition information, allowing it to allocate elevators based on total group size and destination requirements rather than treating each user as a separate entity.
Solution Approach 2:
The patent creates a multi-functional tracking system that simultaneously performs individual user identification, group formation detection, and intent recognition. The same sensor network that tracks individual users also detects group dynamics by analyzing spatial relationships and movement patterns, eliminating the need for separate group detection mechanisms.
3Measurement precision
If the system uses basic input devices for call requests, then the system is simple to operate, but it cannot accurately determine group sizes and intentions
Solution Approach 1:
The patent adds spatial and temporal dimensions to user detection by using depth sensors and video cameras that capture three-dimensional information and movement over time. Instead of relying solely on two-dimensional input device interactions, the system analyzes user presence, group formation, and movement patterns in 3D space, providing accurate group size and intent detection through dimensional enrichment of the sensing data.
Data Source
Figure 1
Figure 2~3
Figure 4
AI summary
Methods and systems for controlling elevator systems are provided. The methods include receiving inputs from at least one interactive input device (806a, 806b), wherein the inputs include elevator call requests, tracking one or more people (812a, 812b) located within a monitored area (802) using at least one sensor (808a, 808b), assigning elevator assignments to the one or more people based on at least one of the inputs from the at least one interactive input device and a grouping algorithm based on the tracking of the one or more people, and scheduling operation of at least one elevator car (804a-c) based on the elevator assignments.