Autonomous Vehicle Position Estimation Switching by Motion State
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Autonomous vehicles face challenges in accurately estimating their self-position, as existing methods do not adapt to the vehicle's state, such as being stopped or moving, leading to inefficiencies and increased cumulative errors.
Innovation Solution
An information processing apparatus that determines whether the autonomous mobile object is in a stopped or moving state to switch between successive self-position estimation using internal world information and discrete self-position estimation using external world information, allowing for adaptive self-position estimation.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If the same self-position estimation method is used regardless of vehicle state, then the system is simple to operate, but the measurement precision deteriorates due to cumulative errors in moving state
Solution Approach 1:
The patent applies dynamics by making the self-position estimation method adaptable to the vehicle's state. The system dynamically switches between first estimation method (using internal sensor data) when the vehicle is moving and second estimation method (using external sensor data) when the vehicle is stopped, optimizing accuracy for each state without requiring a completely complex system architecture
Solution Approach 2:
The patent changes the parameter of estimation method selection based on the vehicle state parameter. When the vehicle state changes from moving to stopped or vice versa, the system changes which estimation method is active, thereby adapting the measurement approach to current conditions and preventing cumulative error accumulation
2Measurement precision
If external world information sensing is continuously used, then the self-position estimation accuracy is improved, but the use of energy increases
Solution Approach 1:
The patent implements periodic action by alternating between different estimation methods based on vehicle state. Instead of continuously using the more accurate but energy-intensive second estimation method, the system periodically switches to the first estimation method when the vehicle is moving, and only activates the second method when stopped, thereby reducing overall energy consumption while maintaining accuracy when needed
Solution Approach 2:
The system uses internally generated data from the first sensor unit (odometry, inertial data) to maintain position estimation during movement, serving itself without requiring continuous external reference. This self-service approach reduces energy consumption by relying on onboard sensors rather than continuously activating external world sensing
Data Source
AI summary
There is provided an information processing apparatus including a controller that, when an autonomous mobile object estimates a self-position, determines which of a first estimation method using a result of sensing by a first sensor unit configured to sense internal world information in relation to the autonomous mobile object and a second estimation method using a result of sensing by a second sensor unit configured to sense external world information in relation to the autonomous mobile object is used by the autonomous mobile object based on whether a state of the autonomous mobile object is a stopped state.