Vehicle Control Device Using Learned Route Navigation
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current vehicle control systems lack the ability to autonomously navigate vehicles based on learned driving information without relying on real-time sensor data, particularly in environments where sensor-based autonomous driving is not feasible or safe.
Innovation Solution
A vehicle control device equipped with a processor that utilizes driving information learned through manual driving modes to autonomously navigate the vehicle, using a combination of stored route data and communication with external devices to adapt to changing conditions, and includes a sensing unit to detect objects not accounted for in the original driving data.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If sensor-based autonomous driving systems are used, then real-time object detection capability is improved, but system reliability deteriorates in environments where sensors are ineffective or unsafe
Solution Approach 1:
The patent segments autonomous driving into two distinct modes: sensor-based autonomous driving for real-time object detection and learning-based autonomous driving for route navigation. Each mode operates independently based on its suitability for specific driving situations, allowing the system to leverage the strengths of both approaches while mitigating their individual weaknesses.
Solution Approach 2:
The patent introduces a communication unit as an intermediary that enables information exchange between the learning-based and sensor-based autonomous driving systems. This intermediary allows the systems to share data and coordinate operations, ensuring that learning-based navigation and sensor-based detection work together harmoniously to improve overall system reliability.
2Device complexity
If only sensor-based autonomous driving is implemented, then device complexity is reduced, but functional versatility deteriorates
Solution Approach 1:
The patent implements a multi-functional autonomous driving system that can operate in diverse environments by switching between learning-based and sensor-based modes. The system is designed to perform multiple functions: learning-based autonomous driving for navigation in sensor-ineffective areas and sensor-based autonomous driving for real-time object detection. This universal design allows the system to adapt to various driving conditions without requiring completely different hardware configurations.
3Productivity
If learning data from multiple vehicles is aggregated, then autonomous driving performance is improved, but data processing complexity and communication requirements increase
Solution Approach 1:
The patent implements feedback mechanisms where driving information from multiple vehicles is collected, processed, and used to improve autonomous driving performance. The communication unit enables vehicles to share learning data, creating a feedback loop that continuously enhances the system's capabilities. This distributed feedback approach allows the network of vehicles to collectively improve while individual vehicles maintain manageable processing complexity.
Data Source
Figure 1
Figure 2
Figure 3
AI summary
The present invention relates to a vehicle control device provided in a vehicle and a method of controlling the vehicle. A vehicle control device according to one embodiment of the present invention includes a processor to autonomously run a vehicle using driving information that the vehicle has traveled in a manual driving mode, wherein the driving information includes a start place where the manual driving mode is started, an end place where the manual driving mode is ended, and a travel route from the start place to the end place, wherein the processor autonomously runs the vehicle along the travel route from the start place to the end place when the vehicle has moved up to the start place through manual driving.