公开(公告)号：US20210279570A1

公开(公告)日：2021-09-09

申请号：US17078079

申请日：2020-10-22

Applicant: HRL Laboratories, LLC

Inventor： Michael A. Warren ,  Christopher Serrano ,  Aleksey Nogin

IPC: G06N3/08

Abstract: Described is a system for proving correctness properties of a neural network for providing estimates for point cloud data. The system receives as input a description of a neural network for generating estimates from a set of point cloud data. The description of the neural network is parsed to obtain a symbolic representation. Based on a combination of the symbolic representation and a set of analysis parameters, the system generates an analysis output indicating whether the neural network satisfies a correctness property in generating the estimates from the set of point cloud data. The analysis output is a mathematical proof artifact proving that the set of analysis parameters is satisfied, a list of one or more point clouds for which the set of analysis parameters is violated, or a report that progress could not be made by the analysis.

公开(公告)号：US20210365596A1

公开(公告)日：2021-11-25

申请号：US17115770

申请日：2020-12-08

Applicant: HRL Laboratories, LLC

Inventor： Byron N. Heersink ,  Michael A. Warren ,  Christopher Serrano

IPC: G06F21/88 ,  G06N3/04

Abstract: Described is a system and method for generating safety conditions for a cyber-physical system with state space S, action space A and trajectory data labelled as either safe or unsafe. In operation, the system receives inputs and ten minimizes loss functions to cause a neural network to become a barrier function. Based on the barrier function, the system can then determine if the cyber-physical system is entering an usafe state, such that if the cyber-physical system is entering the usafe state, then the cyber-physical system is caused to initiate a maneuver to position the cyber-physical system into a safe state.

公开(公告)号：US20210089891A1

公开(公告)日：2021-03-25

申请号：US16937503

申请日：2020-07-23

Applicant: HRL Laboratories, LLC

Inventor： Michael A. Warren ,  Christopher Serrano ,  Pape Sylla

IPC: G06N3/08 ,  G06N3/04 ,  G06F17/18

Abstract: Described is an attack system for generating perturbations of input signals in a recurrent neural network (RNN) based target system using a deep reinforcement learning agent to generate the perturbations. The attack system trains a reinforcement learning agent to determine a magnitude of a perturbation with which to attack the RNN based target system. A perturbed input sensor signal having the determined magnitude is generated and presented to the RNN based target system such that the RNN based target system produces an altered output in response to the perturbed input sensor signal. The system identifies a failure mode of the RNN based target system using the altered output.

公开(公告)号：US11669731B2

公开(公告)日：2023-06-06

申请号：US16691446

申请日：2019-11-21

Applicant: HRL Laboratories, LLC

Inventor： Michael A. Warren ,  Christopher Serrano

IPC: G06N3/08 ,  G06N3/088 ,  G06N3/048

CPC classification number: G06N3/08 ,  G06N3/088 ,  G06N3/048

Abstract: Described is a system for controlling a mobile platform. A neural network that runs on the mobile platform is trained based on a current state of the mobile platform. A Satisfiability Modulo Theories (SMT) solver capable of reasoning over non-linear activation functions is periodically queried to obtain examples of states satisfying specified constraints of the mobile platform. The neural network is then trained on the examples of states. Following training on the examples of states, the neural network selects an action to be performed by the mobile platform in its environment. Finally, the system causes the mobile platform to perform the selected action in its environment.

公开(公告)号：US20210278854A1

公开(公告)日：2021-09-09

申请号：US16950803

申请日：2020-11-17

Applicant: HRL Laboratories, LLC

Inventor： Christopher Serrano ,  Michael A. Warren ,  Aleksey Nogin

IPC: G05D1/02 ,  G06N3/08

Abstract: Described is a system for training a neural network for estimating surface normals for use in operating an autonomous platform. The system uses a parallelizable k-nearest neighbor sorting algorithm to provide a patch of points, sampled from the point cloud data, as input to the neural network model. The points are transformed from Euclidean coordinates in a Euclidean space to spherical coordinates. A polar angle of a surface normal of the point cloud data is estimated in the spherical coordinates. The trained neural network model is utilized on the autonomous platform, and the estimate of the polar angle of the surface normal is used to guide operation of the autonomous platform within the environment.

公开(公告)号：US20200226464A1

公开(公告)日：2020-07-16

申请号：US16691446

申请日：2019-11-21

Applicant: HRL Laboratories, LLC

Inventor： Michael A. Warren ,  Christopher Serrano

IPC: G06N3/08

Abstract: Described is a system for controlling a mobile platform. A neural network that runs on the mobile platform is trained based on a current state of the mobile platform. A Satisfiability Modulo Theories (SMT) solver capable of reasoning over non-linear activation functions is periodically queried to obtain examples of states satisfying specified constraints of the mobile platform. The neural network is then trained on the examples of states. Following training on the examples of states, the neural network selects an action to be performed by the mobile platform in its environment. Finally, the system causes the mobile platform to perform the selected action in its environment.

公开(公告)号：US12073318B2

公开(公告)日：2024-08-27

申请号：US16937503

申请日：2020-07-23

Applicant: HRL Laboratories, LLC

Inventor： Michael A. Warren ,  Christopher Serrano ,  Pape Sylla

IPC: G06N20/00 ,  G06N3/08

CPC classification number: G06N3/08 ,  G06N20/00

Abstract: Described is an attack system for generating perturbations of input signals in a recurrent neural network (RNN) based target system using a deep reinforcement learning agent to generate the perturbations. The attack system trains a reinforcement learning agent to determine a magnitude of a perturbation with which to attack the RNN based target system. A perturbed input sensor signal having the determined magnitude is generated and presented to the RNN based target system such that the RNN based target system produces an altered output in response to the perturbed input sensor signal. The system identifies a failure mode of the RNN based target system using the altered output.

公开(公告)号：US11928585B2

公开(公告)日：2024-03-12

申请号：US16950803

申请日：2020-11-17

Applicant: HRL Laboratories, LLC

Inventor： Christopher Serrano ,  Michael A. Warren ,  Aleksey Nogin

IPC: G06N3/08 ,  B60W60/00 ,  G05D1/00 ,  G05D1/02 ,  G06F7/544

CPC classification number: G06N3/08 ,  G05D1/0221 ,  G05D1/0276 ,  B60W60/001 ,  B60W2556/45 ,  G06F7/544

Abstract: Described is a system for training a neural network for estimating surface normals for use in operating an autonomous platform. The system uses a parallelizable k-nearest neighbor sorting algorithm to provide a patch of points, sampled from the point cloud data, as input to the neural network model. The points are transformed from Euclidean coordinates in a Euclidean space to spherical coordinates. A polar angle of a surface normal of the point cloud data is estimated in the spherical coordinates. The trained neural network model is utilized on the autonomous platform, and the estimate of the polar angle of the surface normal is used to guide operation of the autonomous platform within the environment.

公开(公告)号：US11663370B2

公开(公告)日：2023-05-30

申请号：US17115770

申请日：2020-12-08

Applicant: HRL Laboratories, LLC

Inventor： Byron N. Heersink ,  Michael A. Warren ,  Christopher Serrano

IPC: G06N3/04 ,  G06F21/88

CPC classification number: G06F21/88 ,  G06N3/04

Abstract: Described is a system and method for generating safety conditions for a cyber-physical system with state space S, action space A and trajectory data labelled as either safe or unsafe. In operation, the system receives inputs and ten minimizes loss functions to cause a neural network to become a barrier function. Based on the barrier function, the system can then determine if the cyber-physical system is entering an usafe state, such that if the cyber-physical system is entering the usafe state, then the cyber-physical system is caused to initiate a maneuver to position the cyber-physical system into a safe state.

公开(公告)号：US20210319313A1

公开(公告)日：2021-10-14

申请号：US17115646

申请日：2020-12-08

Applicant: HRL Laboratories, LLC

Inventor： Michael A. Warren ,  Christopher Serrano

IPC: G06N3/08 ,  G06N3/04

Abstract: Described is a system for generating environmental features using deep reinforcement learning. The system receives a policy network architecture, initialization parameters, and a simulation environment that models a trajectory of a target system through a physical environment. Landmark features sampled from the policy network are initialized, and a trained policy network is generated by training the policy network using a reinforcement learning algorithm. A set of environmental features are generated using the trained policy network and displayed on a display device.