Semantic Dynamic Occupancy Grids for Reliable Vehicle Maneuver Planning
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing dynamic occupancy grid algorithms in automated vehicles lack integration of semantic information, leading to inconsistent and unreliable maneuver planning, which can result in potential collisions and unsafe driving scenarios.
Innovation Solution
A method to incorporate semantic information into dynamic occupancy grids by assigning categories to grid cells and particles, using Bayesian inference for updating, and resampling to ensure consistency and accuracy, allowing for real-time decision-making.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If dynamic occupancy grid algorithms are used for environmental modeling, then the model can represent dynamic states of objects, but the model lacks semantic information leading to inconsistent and unreliable maneuver planning
Solution Approach 1:
The patent combines dynamic occupancy grid algorithms with semantic segmentation by merging the grid-based dynamic state representation with semantic category labels. Each grid cell maintains both occupancy probability information and semantic category information, creating a unified environmental model that preserves dynamic states while incorporating semantic meaning for reliable maneuver planning
Solution Approach 2:
The environmental model serves multiple functions simultaneously: it tracks dynamic states of objects (occupancy, velocity), provides semantic categorization (pedestrian, vehicle, cyclist), and supports maneuver planning decisions. This multi-functional approach eliminates the need for separate processing systems and ensures consistent planning based on integrated information
2Reliability
If semantic information is integrated into dynamic occupancy grids, then maneuver planning becomes more reliable, but the computational complexity increases
Solution Approach 1:
The patent segments the computational process into distinct stages: grid cell processing for dynamic state estimation, semantic segmentation for category labeling, and integrated planning. This segmentation allows each component to be optimized independently and processed efficiently, reducing overall computational complexity while maintaining modeling consistency
Solution Approach 2:
The system dynamically adjusts the level of semantic detail and processing intensity based on the driving situation. In high-risk scenarios, full semantic processing is applied, while in safe conditions, simplified processing is used. This dynamic approach maintains consistency when needed while reducing computational load during normal operation
Data Source
AI summary
A computer-implemented method of assisting in the operation of a vehicle is disclosed, the method comprises the steps of: with at least one sensor, sensing an environment of the vehicle thereby obtaining sensor data, and deriving spatial information of the environment and semantic information from the sensor data. Furthermore, generating a dynamic occupancy grid model, in which the sensed environment is represented as a grid consisting of a plurality of grid cells, the grid cells comprising occupying information and a dynamic state represented by a set of particles, and assigning the grid cells and the particles semantic information derived from the sensor data, wherein the semantic information is represented by a set of categories. The method further comprising the steps of predicting new particle positions on the grid; determining for the grid cells predicted semantic information based on combining the semantic information assigned to the grid cells with the semantic information assigned to the particles based on their predicted new particle positions; obtaining new sensor data, and updating the predicted semantic information assigned to the grid cells and the semantic information assigned to the particles from the new sensor data, and deriving an automated driving action based on the determined new semantic information and the dynamic state of the one or more grid cells. Also disclosed is a system for performing the computer-implemented method of assisting operation of a vehicle and the vehicle comprising said system.