Vehicle-Centered Occupancy Grids for Beyond-Range Road User Tracking
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing automated vehicles face challenges in tracking and predicting the behavior of road users in complex traffic scenarios due to restricted sensor range and field of vision, particularly in urban environments, requiring significant computational effort and limiting effective path planning and collision avoidance.
Innovation Solution
A method utilizing on-board sensors to create a vehicle-centered occupancy grid with vectors describing road users, which are combined into a data field and transmitted to a back-end server for conversion into a global occupancy grid, enabling vehicles to access information beyond their sensor range and facilitating safe path planning and collision avoidance through a unified traffic picture.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Loss of information
If on-board sensors are used to detect road users, then information about the surroundings can be obtained, but the sensor range and field of vision are restricted particularly in urban environments
Solution Approach 1:
The patent combines occupancy grid data from multiple autonomous vehicles with different sensor ranges to create a comprehensive environment model. By merging sensor data from multiple sources, the system overcomes the limited field of vision of individual sensors and achieves complete coverage of the operational design domain.
Solution Approach 2:
The back-end server acts as an intermediary that receives, processes, and distributes occupancy grid information from multiple vehicles. It transforms vehicle-centered occupancy grids into a unified global coordinate system, enabling information sharing across the vehicle fleet and extending the effective sensor range for all participants.
2Reliability
If computational algorithms are used to track and predict road user behavior, then path planning and collision avoidance can be improved, but significant computational effort is required
Solution Approach 1:
The system performs preliminary tracking and prediction of road user behavior by continuously updating occupancy grids with detected road users and their predicted trajectories. This advance preparation of environmental models enables faster real-time decision-making during path planning, reducing the computational burden at critical moments.
Solution Approach 2:
The occupancy grid system dynamically updates road user positions, speeds, and trajectories in real-time, allowing the path planning algorithm to adapt to changing traffic conditions. This dynamic approach enables efficient collision avoidance by continuously recalculating safe paths based on current environmental knowledge.
3Measurement precision
If a vehicle-centered occupancy grid is created for each vehicle, then local surroundings can be mapped, but a unified picture of traffic conditions across the vehicle fleet cannot be achieved
Solution Approach 1:
The back-end server implements a universal coordinate transformation system that converts vehicle-centered occupancy grids into a common global reference frame. This multi-functional approach allows the same infrastructure to serve individual vehicle navigation needs while simultaneously enabling fleet-wide traffic analysis and coordination.
Solution Approach 2:
The system transforms occupancy grid data from a two-dimensional vehicle-centered coordinate system into a three-dimensional global coordinate system that encompasses the entire operational design domain. This dimensional transformation enables the integration of multiple vehicle perspectives into a unified spatial representation of traffic conditions.
Data Source
AI summary
A method for providing information detected by on-board sensors about road users in the surroundings of a vehicle involves providing the detected information as data structures representing vectors. Every vector is thereby associated with a cell of a predefined vehicle-mounted occupancy grid, in which a road user described by the respective information is situated. Every vector at least includes coordinates of an associated cell, in which the respective road user is situated, a speed vector, which represents a speed of the respective road user, a time stamp, which represents a point in time of a detection of the respective road user, and an object class, which represents a type of the respective road user.