Trajectory prediction from precomputed or dynamically generated bank of trajectories
US11858508B2 · kind B2 · utility
Assignee
Inventors
Key dates
| Filing date | Dec 12, 2022 |
| Grant date | Jan 2, 2024 |
| Priority date | — |
| Expiry date | Dec 12, 2042 |
Classification
- Technology area (CPC G)Physics
- CPC primaryG01S13/865
- WIPO fieldMeasurement
- WIPO sectorInstruments
Abstract
Among other things, techniques are described for predicting how an agent (e.g., a vehicle, bicycle, pedestrian, etc.) will move in an environment based on prior movement, the road network, the surrounding objects and/or other relevant environmental factors. One trajectory prediction technique involves generating a probability map for an agent's movement. Another trajectory prediction technique involves generating a trajectory lattice, for an agent's movement. In addition, a different trajectory prediction technique involves multi-modal regression where a classifier (e.g., a neural network) is trained to classify the probability of a number of (learned) modes such that each model produces a trajectory based on the current input.
Source: USPTO / EPO open patent data. Objective bibliographic and citation counts.