Introspective competence modeling for AV decision making

US11307585B2 · kind B2 · utility

Assignees

• NISSAN NORTH AMERICA, INC. · US
• University of Massachusetts · US
• Renault S.A.S. · FR

Inventors

• Connor Basich · Northampton, US
• Kyle Hollins Wray · Fremont, US
• Stefan Witwicki · San Carlos, US
• Shlomo Zilberstein · Amherst, US

Key dates

• Filing date: Oct 30, 2019
• Grant date: Apr 19, 2022
• Expiry date: Jun 24, 2040

Classification

• Technology area (CPC G): Physics
• CPC primary: G05D1/0061
• WIPO field: Control
• WIPO sector: Instruments

Abstract

A first method includes detecting, based on sensor data, an environment state; selecting an action based on the environment state; determining an autonomy level associated with the environment state and the action; and performing the action according to the autonomy level. The autonomy level can be selected based at least on an autonomy model and a feedback model. A second method includes calculating, by solving an extended Stochastic Shortest Path (SSP) problem, a policy for solving a task. The policy can map environment states and autonomy levels to actions and autonomy levels. Calculating the policy can include generating plans that operate across multiple levels of autonomy.