Predictive Sensing Control for Robust Mobile Object Localization
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing methods for estimating the self-location of autonomously behaving mobile objects are prone to accuracy decreases due to disturbances in the environment, such as lost or falsely recognized landmarks, which can be caused by factors like the sun, tunnels, or shadows.
Innovation Solution
An information processing apparatus with an information acquisition unit and a control prediction unit that predicts control for sensing devices based on the object's location, posture, and map information, allowing for anticipation and mitigation of disturbance factors like the sun's position or shadows, thereby improving image capture and self-location estimation accuracy.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If landmark extraction is performed for self-location estimation, then position estimation can be achieved, but accuracy decreases due to disturbance factors like sunlight, shadows, or tunnels causing lost or falsely recognized landmarks
Solution Approach 1:
The system performs preliminary action by predicting the positions of disturbance factors (sun, shadows, tunnels) in advance before image capture. This allows the self-location estimation system to anticipate and compensate for potential landmark recognition errors caused by these disturbances, thereby maintaining accuracy despite environmental challenges.
Solution Approach 2:
The system applies preliminary anti-action by using predicted disturbance factor positions to correct or adjust landmark extraction results. By anticipating where disturbances will occur and pre-calculating their impact, the system can counteract their negative effects on landmark recognition and self-location estimation accuracy.
2Productivity
If control of sensing device is performed based on current location and posture information, then image capture can be executed, but time lag occurs preventing optimal image capture for future positions
Solution Approach 1:
The system performs preliminary action by predicting the mobile object's future location and posture at time T+N, and pre-determining the optimal sensing device control settings for that future state. This allows the control command to be executed in advance, eliminating time lag and ensuring the sensing device is optimally positioned when the predicted moment arrives.
Solution Approach 2:
The system applies dynamics by transitioning from static control based on current state to dynamic predictive control that accounts for future state changes. The control system continuously updates predictions of location, posture, and disturbance factors, adjusting sensing device control in real-time to maintain optimality despite changing conditions.
Data Source
AI summary
There is provided an information processing apparatus that includes an information acquisition unit and a control prediction unit. The information acquisition unit acquires information regarding a location and a posture of a first mobile object that includes a sensing device. The control prediction unit predicts control performed with respect to the sensing device, on the basis of the information regarding the location and the posture and map information, the information regarding the location and the posture being acquired by the information acquisition unit.