Risk Potential Field Map Sequence for Vehicle Trajectory Planning
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current methods for providing environmental images to assist motor vehicles in navigation and collision avoidance do not adequately account for future potential risks and dynamic object movements, limiting their ability to plan safe trajectories.
Innovation Solution
A method and device that estimate state probability distributions for static and dynamic objects using environmental data, create risk potential field maps, and combine these maps for current and future times to generate a risk potential field map sequence, which is used to output an improved environmental image for trajectory planning.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If current methods for providing environmental images are used, then the system is simple and easy to operate, but the ability to anticipate future risks and plan safe trajectories is insufficient
Solution Approach 1:
The system performs preliminary actions by estimating state probability distributions for future time points and creating risk potential field maps in advance. This allows the vehicle to anticipate potential risks before they materialize, improving trajectory planning safety by proactively identifying hazardous areas rather than merely reacting to current sensor data
Solution Approach 2:
The system dynamically adapts the environmental image by continuously updating risk potential field maps based on estimated future states of dynamic objects. The risk maps are not static but evolve over time, reflecting changing probability distributions of object states, which enhances the system's ability to plan safe trajectories in dynamic environments
2Loss of information
If risk potential field maps for current and future times are combined, then the predictive capability is improved, but the computational requirements and processing time increase
Solution Approach 1:
The system applies partial action by focusing computational resources on estimating state probability distributions only for relevant dynamic objects and creating risk potential field maps for critical future time points. This selective approach reduces overall computational load while still capturing essential future risk information needed for safe trajectory planning
Data Source
AI summary
The invention relates to a method for providing an environmental image of an environment of a mobile apparatus, comprising the following steps: Receiving and/or recording environmental data using an input apparatus, wherein the environmental data image the environment and comprise information on static objects and/or dynamic objects in the environment, executing the following steps for a current and for at least one future point in time by means of an estimating apparatus: estimating a state probability distribution for at least one of the static objects and/or dynamic objects based on the received and/or recorded environmental data, creating a risk potential field map of the environment based on the estimated state probability distribution of the at least one static object and/or dynamic object, wherein this is done taking into account at least one potential risk enhancement, and combining the risk potential field maps into a risk potential field map sequence, and outputting the risk potential field map sequence. The invention further relates to an associated device and a motor vehicle.