Vehicle Drive Mode Switching via Object Occurrence Map
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing automatic driving systems face challenges in accurately recognizing external circumstances, leading to unreliable switching between automatic and manual drive modes, as the criteria for safe control differ between humans and systems, potentially resulting in unsafe driving conditions.
Innovation Solution
A drive control apparatus that includes a memory and circuitry for storing an object occurrence map, detecting objects in a vehicle's captured image, and switching the drive mode from automatic to manual based on detection accuracy, using a viewpoint-converted object occurrence map to enhance reliability and accuracy in defining occurrence areas.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Productivity
If automatic driving control is implemented, then productivity is improved, but reliability deteriorates due to inaccurate object detection in certain scenarios
Solution Approach 1:
The patent introduces an object occurrence map as an intermediary layer between the object detection system and the automatic driving control. This map stores pre-defined occurrence areas for various objects (pedestrians, vehicles, cyclists) and serves as a reference to verify detection results. When an object is detected, the system checks whether its position coincides with expected occurrence areas in the map, thereby mediating between raw detection data and control decisions to improve reliability.
Solution Approach 2:
The system implements feedback by continuously comparing detected object positions with the object occurrence map and using this comparison to adjust the automatic driving control state. When detection accuracy is verified through the map (detected objects match expected occurrence areas), the system maintains automatic mode; when mismatches occur indicating poor detection accuracy, the system switches to manual mode, providing feedback-based adaptive control.
2Measurement precision
If object detection is performed in all scenarios, then measurement precision is improved, but device complexity increases
Solution Approach 1:
The patent applies preliminary action by pre-establishing the object occurrence map before actual driving operations. The map contains pre-defined occurrence areas for various objects based on statistical data and typical traffic patterns. This preliminary preparation allows the system to quickly verify detection results during operation without performing complex real-time analysis, thereby improving measurement precision while avoiding excessive device complexity during actual detection.
Data Source
Figure 1
Figure 2
Figure 3
AI summary
An apparatus includes a memory, and circuitry which, in operation, performs operations including, storing, in the memory, an object occurrence map defining an occurrence area where there is a possibility that an object appears, detecting the object included in a captured image of a scene seen in a running direction of a vehicle, switching a vehicle drive mode, based on a result of the detection of the object and the object occurrence map, from an automatic drive mode in which the vehicle is automatically driven to a manual drive mode in which the vehicle is driven manually by a driver, and controlling driving of the vehicle in the switched manual drive mode.