Risk Aware Executor with Action Set Recommendations

Patent №

US 11,635,758

Granted

2023-04-25

Filed 2019

Owner

THE UNIVERSITY OF MASSACHUSETTS

+1 more

Lab

—

AI components

ml · nlp · kr · planning · hardware

Assignment

Recorded

Dataset

AIPD

2023_r1 edition

Application

16696235

A method for use in traversing a vehicle transportation network by an autonomous vehicle (AV) includes traversing, by the AV, the vehicle transportation network. Traversing the vehicle transportation network includes identifying a distinct vehicle operational scenario; instantiating a first decision component instance; receiving a first set of candidate vehicle control actions from the first decision component instance; selecting an action; and controlling the AV to traverse a portion of the vehicle transportation network based on the action. The first decision component instance is an instance of a first decision component modeling the distinct vehicle operational scenario.

Machine learning Natural language Knowledge representation Planning AI hardwareB60W 30/04G05D 1/0088B60W 30/08B60W 30/14B60W 30/18159B60W 60/00G01C 21/3492G05D 1/0212+4 more

Google Patents

AI classification

Planning1.00

Knowledge representation1.00

Machine learning1.00

AI hardware0.93

Natural language0.85

Vision0.13

Speech0.01

Evolutionary computation0.00

Ownership

THE UNIVERSITY OF MASSACHUSETTS

assignment · 517110265

NISSAN NORTH AMERICA, INC.

assignment · 517110370

Assignors

WITWICKI, STEFAN, WRAY, KYLE HOLLINS

On an employer assignment, the assignors are typically the inventors.

From the same owner

Autonomous Vehicle Operational ManagementUS 12,643,571 · 2026 Vehicle Decision Making Using Sequential Information ProbingUS 12,559,113 · 2026 Online State Space Refinement for Competence-Aware SystemsUS 12,344,280 · 2025 Explainability of Autonomous Vehicle Decision MakingUS 11,714,971 · 2023 Autonomous Vehicle Operation with Explicit Occlusion ReasoningUS 11,702,070 · 2023 LEARNING SAFETY AND HUMAN-CENTERED CONSTRAINTS IN AUTONOMOUS VEHICLESUS 11,613,269 · 2023 Explainability of Autonomous Vehicle Decision MakingUS 11,577,746 · 2023 Autonomous Vehicle Operational Management Including Operating A Partially Observable Markov Decision Process Model InstanceUS 11,500,380 · 2022

Cites (22)

REINFORCEMENT LEARNING ON AUTONOMOUS VEHICLESUS 10,990,096 · 2021 AUTONOMOUS VEHICLE OPERATION FEATURE MONITORING AND EVALUATION OF EFFECTIVENESSUS 10,599,155 · 2020 Information Presenting Device and Information Presenting MethodUS 10,538,252 · 2020 CONSTRAINT AUGMENTATION IN A NAVIGATIONAL SYSTEMUS 10,514,705 · 2019 ACCIDENT FAULT DETERMINATION FOR AUTONOMOUS VEHICLESUS 10,319,039 · 2019 ACCIDENT FAULT DETERMINATION FOR AUTONOMOUS VEHICLESUS 10,185,998 · 2019 TRAFFIC SIGNAL TIMING ESTIMATION USING AN ARTIFICIAL NEURAL NETWORK MODELUS 10,126,135 · 2018 AUTOMATICALLY PROVIDING EXPLANATIONS FOR ACTIONS TAKEN BY A SELF-DRIVING VEHICLEUS 10,093,322 · 2018 MISHAP AMELIORATION BASED ON SECOND-ORDER SENSING BY A SELF-DRIVING VEHICLEUS 10,061,326 · 2018 Controlling Driving Modes of Self-Driving VehiclesUS 10,029,701 · 2018 ACCIDENT FAULT DETERMINATION FOR AUTONOMOUS VEHICLESUS 9,972,054 · 2018 ACCIDENT RESPONSE USING AUTONOMOUS VEHICLE MONITORINGUS 9,646,428 · 2017 AUTONOMOUS VEHICLE OPERATED WITH GUIDE ASSISTANCE OF HUMAN DRIVEN VEHICLESUS 9,494,439 · 2016 LOCALITY ADAPTED COMPUTERIZED ASSISTED OR AUTONOMOUS DRIVING OF VEHICLESUS 9,134,731 · 2015 Mapping Techniques Using Probe VehiclesUS 9,103,671 · 2015 ROUTE NAVIGATION WITH OPTIMAL SPEED PROFILEUS 9,081,651 · 2015 LANE MAPPING IN A VEHICLE-TO-VEHICLE COMMUNICATION SYSTEMUS 8,884,782 · 2014 Target Trailing with Safe Navigation with colregs for Maritime Autonomous Surface VehiclesUS 8,849,483 · 2014 Consideration of Risks in Active Sensing for an Autonomous VehicleUS 8,781,669 · 2014 Patent US 10,408,638US 10,408,638 Patent US 11,037,320US 11,037,320 Patent US 9,568,915US 9,568,915

Related research

Risk-informed decision-making and control strategies for autonomous vehicles in emergency situations.Semantic Scholar Risk-anticipatory autonomous driving strategies considering vehicles' weights, based on hierarchical deep reinforcement learningarXiv Risk-Aware Decision-Making and Planning Using Prediction-Guided Strategy Tree for the Uncontrolled IntersectionsOpenAlex Reliable Risk Management for Autonomous Vehicles based on Sequential Bayesian Decision Networks and Dynamic Inter-Vehicular AssessmentOpenAlex Decision-Making for Autonomous Driving via a Coupled Reinforcement Learning Network Combined With Risk AssessmentOpenAlex

Full text

Google Patents