Elevator Depth Sensor Intent Deduction
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Elevator systems often waste energy and delay calls for intended users due to mistakenly sending elevators for individuals who do not actually want to board, as existing systems cannot accurately determine user intent based on proximity alone.
Innovation Solution
A sensor assembly with a depth sensor and controller system that senses multiple cues such as body orientation, head pose, gaze direction, motion history, and vocalizations, and compares these with historical data to deduce user intent, issuing a call signal only when intent to board is confirmed.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Speed
If the elevator system sends elevators based on proximity detection alone, then the system responds quickly to potential users, but it wastes energy and delays calls for actual users by mistakenly serving individuals who do not want to board
Solution Approach 1:
The system continuously monitors multiple cues (body orientation, head pose, gaze direction, motion history, clustering behavior, and vocalizations) and uses this feedback to dynamically adjust elevator call decisions. The controller processes real-time sensor data to confirm user intent before triggering elevator calls, eliminating false calls for individuals merely passing by or waiting for other reasons.
Solution Approach 2:
The system changes the parameters used for detection from simple proximity-based detection to multi-parameter analysis including body orientation angles, head pose coordinates, gaze direction vectors, motion history trajectories, clustering density metrics, and vocalization presence. This parameter transformation enables accurate distinction between users intending to board and those merely in the vicinity.
2Measurement precision
If the system uses multiple cues and historical data comparison to deduce user intent, then call accuracy improves, but device complexity increases
Solution Approach 1:
The sensor assembly integrates multiple sensing functions into a single unified device that simultaneously captures body orientation, head pose, gaze direction, motion history, clustering behavior, and vocalizations. This multi-functional sensor assembly eliminates the need for separate sensors for each cue type, reducing overall system complexity while maintaining high detection accuracy.
Solution Approach 2:
The controller serves as an intermediary that receives raw data from the sensor assembly, compares it with historical data patterns, and deduces user intent. This intermediary processing layer simplifies the system architecture by centralizing the complex analysis function in the controller rather than requiring complex processing in the sensor assembly itself.
3Measurement precision
If the system monitors multiple individual cues and group behavior, then call assignment accuracy improves, but processing time and computational load increase
Solution Approach 1:
The system pre-processes and stores historical data patterns for quick comparison during real-time operation. By having reference data prepared in advance, the controller can rapidly match current sensor readings against known patterns, significantly reducing processing time while maintaining high accuracy in call assignment decisions.
Data Source
AI summary
An elevator system is provided and includes a sensor assembly and a controller. The sensor assembly is disposable in or proximate to an elevator lobby and is configured to deduce an intent of an individual in the elevator lobby to board one of one or more elevators and to issue a call signal in response to deducing the intent of the individual to board the one of the elevators. The controller is configured to receive the call signal issued by the sensor assembly and to assign one or more of the elevators to serve the call signal at the elevator lobby.