Functional Road Mapping for GPS-Free Autonomous Navigation
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current autonomous vehicle navigation systems rely on high-definition mapping that requires extensive manual effort and costly satellite GPS connections, limiting their ability to operate without pre-existing maps and GPS connections.
Innovation Solution
A method using real-time visual input from sensors to generate functional top-down road maps through an encoder-decoder neural network architecture, transforming visual data into functional information without relying on pre-determined precise mapping, enabling autonomous navigation without GPS or pre-existing maps.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If high-definition mapping with satellite GPS is used, then navigation accuracy is improved, but system cost and complexity increase
Solution Approach 1:
The patent creates a simplified top-down functional map that copies only the essential navigational features needed for autonomous driving, rather than using complete high-definition maps. This functional map includes lane markings, drivable areas, and road boundaries, providing sufficient navigation accuracy without requiring the full complexity of HD mapping infrastructure and satellite GPS connections.
Solution Approach 2:
The system extracts only the critical functional elements required for navigation from the complete environmental data, creating a streamlined top-down map that contains lane markings, drivable areas, and road boundaries. This extraction approach maintains navigation accuracy while eliminating unnecessary map details and reducing dependency on satellite GPS connections.
2Manufacturing precision
If manual HD mapping is used, then map precision is improved, but manufacturing time and cost increase
Solution Approach 1:
The system enables vehicles to automatically generate their own top-down functional maps using onboard sensors and neural networks, eliminating the need for manual HD mapping processes. The vehicle captures real-time sensor data, processes it through the neural network to generate functional maps, and uses these maps for navigation, achieving both precision and rapid deployment without manual intervention.
Solution Approach 2:
The neural network is pre-trained to automatically generate accurate top-down functional maps from sensor inputs, preparing the system in advance for rapid map generation. This preliminary training enables the system to quickly produce precise functional maps during actual operation without requiring manual mapping processes during deployment.
3Measurement precision
If pre-determined precise mapping is used, then location accuracy is improved, but adaptability to new locations decreases
Solution Approach 1:
The system dynamically generates top-down functional maps in real-time based on current sensor inputs from the vehicle's environment, rather than relying on static pre-determined maps. This dynamic approach allows the vehicle to adapt to new locations immediately upon arrival, maintaining location accuracy through real-time map generation while achieving universal adaptability across diverse geographic areas.
Data Source
AI summary
A method, an apparatus and a computer program for real-time generation of functional road maps. The method comprises obtaining a real-time input from a sensor mounted on a vehicle, that captures a front view of a road ahead of the vehicle and processing thereof by a neural network to generate a functional map of the road ahead of the vehicle. Each pixel in the functional map is associated with a predetermined relative position to the vehicle. A content of each pixel is assigned a set of values, each of which represents a functional feature relating to a location at a corresponding predetermined relative position to the pixel. The processing is performed without relying on a pre-determined precise mapping. The method further comprises providing the functional map to an autonomous navigation system of the vehicle, to autonomously drive the vehicle in accordance with functional features represented by the functional map.