Formally safe symbolic reinforcement learning on visual inputs
US11513520B2 · kind B2 · utility
Assignee
Inventors
Key dates
| Filing date | Dec 10, 2019 |
| Grant date | Nov 29, 2022 |
| Priority date | — |
| Expiry date | Jan 20, 2041 |
Classification
- Technology area (CPC G)Physics
- CPC primaryG06V20/58
- WIPO fieldComputer technology
- WIPO sectorElectrical engineering
Abstract
A method for training control software to reinforce safety constraints using visual inputs includes performing template matching for each object in an image of a reinforcement learning (RL) agent's action space using a visual template for each object wherein each object in the RL agent's action space is detected, mapping each detected object to a set of planar coordinates for each object in the RL agent's action space, determining a set of safe actions for the RL agent by applying a safety specification for the RL agent's action space to the set of variables for coordinates for each object in the RL agent's action space, outputting the set of safe actions to the RL agent for a current state of a RL procedure, and preventing the RL agent from executing an action that is unsafe, before the RL agent takes an action.
Source: USPTO / EPO open patent data. Objective bibliographic and citation counts.