Method for long-term trajectory prediction of traffic participants
A technology for participants and transportation, applied in forecasting, traffic control systems, neural learning methods, etc., can solve the problem that the model cannot predict the time range
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
Embodiment Construction
[0069] figure 1 A schematic diagram of the system 10 for long-term trajectory prediction of traffic participants is shown. The notation used is commonly used in the deep learning scientific literature. The system uses four inputs, namely environment data E, batched public state P[t-1], previous action data A[t-1] and previous state data S[t-1].
[0070] The environmental data E are in the form of environmental vectors. Preferably, this is a circular representation of the host vehicle's surroundings. The granularity of the environmental data E is arbitrary, however preferably 360° around the host vehicle to be relevant to the environment in all directions. Environmental data E includes all static and dynamic objects surrounding the host vehicle.
[0071] The previous public state data P[t−1], also referred to as batches of public states, relate to different states of nearby objects, in particular road users, in previous time steps. The previous public state data P[t-1] inc...
PUM
Login to View More Abstract
Description
Claims
Application Information
Login to View More 


