Autonomous Mobile Object Control Using Labeled Scene Grids
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Automated driving systems face challenges in performing rapid control due to the complexity of information processing, leading to difficulties in movement control for autonomous mobile objects.
Innovation Solution
A mobile object control device and method that generates a first movement plan in a first period and a second movement plan in a shorter second period, using label data with different values indicating the presence or absence of moving objects, to enable efficient movement control, particularly by inputting data to a model learned through reinforcement learning for scene-specific control.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If complex information processing is performed for automated driving control, then control accuracy and safety are improved, but control speed and response time deteriorate
Solution Approach 1:
The patent divides the control period into a first period for generating a first movement plan and a second period for generating a second movement plan. This segmentation allows the system to perform different levels of processing at different time scales, maintaining both accuracy and speed.
Solution Approach 2:
The system performs preliminary processing by generating label data that simplifies the representation of the surrounding situation. This pre-processing reduces the complexity of subsequent control decisions, enabling faster response times while maintaining control accuracy.
2Measurement precision
If detailed surrounding situation recognition is performed, then movement plan accuracy is improved, but processing time increases
Solution Approach 1:
The system performs preliminary processing by generating label data that simplifies the representation of the surrounding situation. This pre-processing reduces the complexity of subsequent control decisions, enabling faster response times while maintaining control accuracy.
Solution Approach 2:
The patent transforms the detailed surrounding situation into a simplified label data representation with different values indicating presence or absence of moving objects. This parameter transformation reduces processing complexity while preserving essential information for control decisions.
3Speed
If a learned model is used for rapid control, then control speed is improved, but reliability in unknown scenes deteriorates
Solution Approach 1:
The system uses feedback from the detection device to continuously update the surrounding situation recognition. This feedback mechanism allows the system to adapt to new situations and maintain reliability even when encountering unknown scenes, while preserving the speed benefits of using a learned model.
Data Source
AI summary
A mobile object control device includes a first controller that recognizes a surrounding situation of a mobile object based on an output of a detection device having a space around the mobile object as a detection range and generates a first movement plan for the mobile object in a first period based on the recognized surrounding situation of the mobile object, and a second controller that generates a second movement plan for the mobile object in a second period shorter than the first period, and when the second controller generates label data in which label information indicating different values depending on at least the presence or absence of a moving object is imparted to each of division elements obtained by dividing the space around the mobile object into a finite number, and generates the second movement plan based on the label data.