Mobile Body Control Device Noise Filtering via Signal Dispersion
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing object tracking systems using Kalman filters can misrecognize noise as a tracking target, leading to inefficient energy consumption due to continuous tracking.
Innovation Solution
Implement a mobile body control device that utilizes an object recognition unit to recognize objects based on sensor observation values, and an object tracking unit to determine tracking targets based on signal intensity and dispersion, employing a Kalman filter with initialization, gating, and machine learning through an auto-encoder to distinguish noise from actual objects.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Ease of operation
If autonomous driving functions are added to vehicles, then convenience and safety are improved, but system complexity and cost increase
Solution Approach 1:
The autonomous driving control system is divided into multiple independent ECUs (Electronic Control Units), each responsible for specific functions such as steering, acceleration, braking, and sensor processing. This segmentation allows the complex autonomous driving system to be managed through modular, independently developable and testable components, reducing overall system complexity while maintaining full functionality.
Solution Approach 2:
The patent implements a universal communication interface and data transmission protocol that can be used across different ECU types and vehicle models. This multi-functional communication framework allows the same basic infrastructure to support various autonomous driving functions and configurations, reducing complexity by avoiding the need for dedicated communication channels for each function.
2Adaptability or versatility
If multiple ECUs are used for autonomous driving control, then functional flexibility is improved, but communication latency and coordination difficulty increase
Solution Approach 1:
The patent implements a feedback mechanism where each ECU continuously reports its state, processing status, and data reception confirmation to the central control system. This real-time feedback allows the system to monitor communication delays, detect latency issues, and dynamically adjust data transmission priorities to minimize the impact of communication time on overall system performance.
Solution Approach 2:
The system performs preliminary data preprocessing and filtering at each ECU before transmission, and pre-allocates communication resources based on predicted data needs. By preparing data in advance and pre-configuring communication channels, the system reduces actual transmission time and minimizes latency during critical autonomous driving operations.
3Measurement precision
If data transmission between ECUs is increased, then coordination accuracy is improved, but communication bandwidth consumption and processing load increase
Solution Approach 1:
The patent implements differential data transmission where each ECU analyzes its own data changes and only transmits data that has actually changed or requires updating. This local quality assessment prevents redundant transmissions of unchanged data, reducing overall communication bandwidth consumption and energy usage while maintaining coordination accuracy by ensuring all necessary data changes are transmitted.
Solution Approach 2:
The system transmits only the necessary portion of data required for coordination rather than complete data sets. By selectively transmitting partial data that is sufficient for maintaining coordination accuracy, the system reduces communication load and energy consumption while avoiding the need to transmit excessive data that would not contribute to coordination precision.
Data Source
Figure 1
Figure 2
Figure 3
AI summary
A control device for a mobile body, which moves while recognizing a vicinity of the mobile body, includes an object recognition unit configured to recognize an object in the vicinity of the mobile body on the basis of an observation value of a sensor provided in the mobile body, and an object tracking unit configured to track the object recognized by the object recognition unit, on the basis of time-series data of the observation value, in which the object tracking unit is configured to determine whether the object is a tracking target, on the basis of a signal intensity of the observation value and a dispersion of the observation value.