Cloud-Supplemented Driver Assistance for Obstacle Detection
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current driver-assistance systems face challenges in accurately detecting obstacles, especially low-lying ones, due to limitations in conventional ultrasonic sensors and high costs and power consumption associated with advanced sensor technologies like Lidar, which require significant computing resources and additional infrastructure.
Innovation Solution
A method where environment data sets from motor vehicle sensors are transmitted to a cloud computer for processing, generating a supplemental data set that fills in blind spots and forecasts future environments, reducing the vehicle's computing load and power consumption by leveraging cloud computing and additional sensor data from other road users.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If high-resolution Lidar sensors are used to improve measurement precision, then measurement precision is improved, but device complexity and cost increase significantly
Solution Approach 1:
The patent creates virtual copies of sensor data by generating synthetic environment representations in the cloud computer. Instead of installing multiple physical sensors, the system uses cloud-based simulations to replicate and supplement sensor data, providing comprehensive environmental information without additional hardware complexity
Solution Approach 2:
The cloud computer acts as an intermediary between the vehicle's limited sensors and the comprehensive environmental data needed for automated driving. It receives raw sensor data, supplements it with simulated data from multiple virtual sensor perspectives, and returns enhanced environment representations to the vehicle
2Measurement precision
If advanced sensor processing and additional sensors are deployed to improve measurement precision, then measurement precision is improved, but use of energy increases
Solution Approach 1:
The patent extracts the computationally intensive sensor processing tasks from the vehicle and relocates them to the cloud computer. This separates the energy-consuming processing operations from the moving vehicle, allowing the vehicle to use minimal power for data transmission while the cloud handles heavy computational loads
Solution Approach 2:
The system replaces physical sensor hardware with virtual sensor simulations in the cloud. Instead of installing multiple physical sensors that would consume power, the system uses software-based sensor models that generate synthetic data without additional energy consumption at the vehicle
3Measurement precision
If computing resources are allocated for real-time sensor data processing, then measurement precision is improved, but productivity decreases due to increased processing time
Solution Approach 1:
The cloud computer performs preliminary processing of sensor data and pre-generates supplemented environment representations in advance. By preparing enhanced environment data before it is needed for driving decisions, the system reduces real-time processing requirements and improves response speed
Solution Approach 2:
The patent segments the processing workload between the vehicle and cloud computer. The vehicle handles immediate sensor data acquisition and transmission, while the cloud computer handles intensive supplementation and processing tasks, distributing the computational burden to improve overall system efficiency
4Device complexity
If cloud-based processing is used to reduce vehicle computing resources, then device complexity is reduced, but loss of time occurs during data transmission
Solution Approach 1:
The cloud computer prepares supplemented environment representations in advance before they are needed for driving maneuvers. This pre-processing approach ensures that when data is requested by the vehicle, enhanced environment information is already available, minimizing transmission delays
Solution Approach 2:
The system maintains continuous data exchange between vehicle and cloud computer, with the cloud constantly preparing and updating supplemented environment representations. This continuous operation ensures data is ready for immediate transmission when needed, reducing effective latency
Data Source
AI summary
A driver assistance system for a motor vehicle performs a maneuver using a trajectory determined according to an external environment. The vehicle has a plurality of environment sensors and a controller device configured to acquire an environment data set (UDS) using the environment sensors, which it transmits to a cloud computer. The cloud computer reads in the environment data set (UDS), generates a supplemental data set (EDS) for supplementing the environment data set (UDS), combines the environment data set (UDS) with the supplemental data set (EDS) in order to generate a supplemented environment data set (UDS′), and transmits the supplemented environment data set (UDS′) to the controller device. The supplemental data set (EDS) may be obtained by evaluating data of other road users within a predetermined radius of the vehicle. The controller device evaluates the supplemented environment data set (UDS′) for the purpose of controlling the trajectory.