Adaptive Depth Sensor Activation for Energy-Efficient Localization
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current devices using sensors for localization, such as Microsoft Hololens and ARKit, maintain all sensors in an active state without considering the need for selective activation and deactivation, leading to unnecessary energy consumption and computational resource utilization.
Innovation Solution
A device that includes a processor connected to a monocular camera and a depth sensor, which determines a benefit level for activating the depth sensor based on image data, activating it when the benefit level satisfies an activation rule, and deactivating the monocular camera when the depth sensor is activated, thereby optimizing energy and computational resources.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If all sensors are kept active for localization, then localization availability is improved, but energy consumption increases
Solution Approach 1:
The system dynamically adjusts sensor activation status based on real-time environmental conditions and localization performance metrics. The depth sensor is selectively activated or deactivated according to whether the monocular camera can achieve sufficient localization accuracy, transforming the static sensor configuration into a dynamic adaptive system that optimizes energy consumption while maintaining localization reliability
Solution Approach 2:
The system changes the operational parameters of sensors based on environmental conditions. By evaluating image data quality, texture density, and localization accuracy metrics, the system adjusts the activation state of the depth sensor, changing parameters such as sensor power state and data acquisition frequency to balance energy consumption with localization performance
2Measurement precision
If depth sensor is activated continuously, then localization accuracy is improved, but computational resource utilization increases
Solution Approach 1:
Instead of continuously activating the depth sensor, the system applies partial action by activating it only when necessary based on localization performance thresholds. The system monitors localization accuracy metrics and activates the depth sensor only when the monocular camera fails to meet minimum accuracy requirements, reducing unnecessary computational resource utilization while maintaining adequate localization precision
Solution Approach 2:
The system implements feedback mechanisms by continuously monitoring localization accuracy from the monocular camera and using this information to control depth sensor activation. When localization error exceeds thresholds or environmental conditions indicate poor monocular performance, the system activates the depth sensor to correct localization drift, creating a closed-loop control system that optimizes computational resource usage
3Use of energy by moving object
If monocular camera is used exclusively, then energy consumption is reduced, but localization performance deteriorates in certain conditions
Solution Approach 1:
The system creates a multi-functional sensor configuration where the monocular camera serves as the primary localization sensor for energy-efficient operation, while the depth sensor acts as a supplementary sensor activated under specific conditions. This universal approach allows the system to function effectively in both low-texture and high-texture environments, adapting to different operational scenarios while maintaining energy efficiency
Data Source
Figure 1
Figure 2
Figure 3
AI summary
A device is disclosed that is configured to perform localization using one or both of a monocular camera (200) and a depth sensor (202) that are transportable with the device. The device includes at least one processor operationally connected to the monocular camera and the depth sensor. The device also includes at least one memory storing program code that is executed by the at least one processor to perform operations to receive image data from the monocular camera. The operations determine a benefit level of activating the depth sensor for localization, based on the image data, and activate the depth sensor for localization based on a determination that the benefit level of activating the depth sensor satisfies an activation rule. Related methods and computer program products are also disclosed.