-
公开(公告)号：US11458983B2
公开(公告)日：2022-10-04
申请号：US16989776
申请日：2020-08-10
申请人： Jun Luo , Julian Villella , Mohsen Rohani , David Rusu , Montgomery Alban , Seyed Ershad Banijamali
发明人： Jun Luo , Julian Villella , Mohsen Rohani , David Rusu , Montgomery Alban , Seyed Ershad Banijamali
摘要： Method and system for controlling the behavior of an object. Behavior of the object is controlled during a first time period by using a first agent that applies a first behavior policy to map observations about the object and the environment in the first time period to a corresponding control action. Control is transitioned from the first agent to a second agent during a transition period following the first time period. Behavior of the object during a second time period following the transition period is controlled by using a second agent that applies a second behavior policy to map observations about the object and the environment in the second time period to a corresponding control action that is applied to the object. During transition the first agent applies the first behavior policy control the object and the second agent applies the second behavior policy to map observations about the object and the environment to corresponding control actions that are not applied to the object.
-
公开(公告)号：US20220032935A1
公开(公告)日：2022-02-03
申请号：US16989776
申请日：2020-08-10
申请人： Jun LUO , Julian VILLELLA , Mohsen ROHANI , David RUSU , Montgomery ALBAN , Seyed Ershad BANIJAMALI
发明人： Jun LUO , Julian VILLELLA , Mohsen ROHANI , David RUSU , Montgomery ALBAN , Seyed Ershad BANIJAMALI
摘要： Method and system for controlling the behavior of an object. Behavior of the object is controlled during a first time period by using a first agent that applies a first behavior policy to map observations about the object and the environment in the first time period to a corresponding control action. Control is transitioned from the first agent to a second agent during a transition period following the first time period. Behavior of the object during a second time period following the transition period is controlled by using a second agent that applies a second behavior policy to map observations about the object and the environment in the second time period to a corresponding control action that is applied to the object. During transition the first agent applies the first behavior policy control the object and the second agent applies the second behavior policy to map observations about the object and the environment to corresponding control actions that are not applied to the object.
-
公开(公告)号：US20220032951A1
公开(公告)日：2022-02-03
申请号：US16941505
申请日：2020-07-28
申请人： Jun LUO , Julian VILLELLA , Mohsen ROHANI , David RUSU , Montgomery ALBAN , Seyed Ershad BANIJAMALI
发明人： Jun LUO , Julian VILLELLA , Mohsen ROHANI , David RUSU , Montgomery ALBAN , Seyed Ershad BANIJAMALI
摘要： Method and system for controlling the behavior of an object. Behavior of the object is controlled during a first time period by using a first agent that applies a first behavior policy to map observations about a state of the object in the first time period to a corresponding control action. Control is transitioned from the first agent to a second agent during a transition period following the first time period. Behavior of the object during a second time period following the transition period is controlled by using a second agent that applies a second behavior policy to map observations about a current state of the object in the second time period to a corresponding control action that is applied to the object. During transition the first agent applies the first behavior policy control the object and the second agent applies the second behavior policy to map observations about the state of the object to corresponding control actions that are not applied to the object.
-
公开(公告)号：US20210081843A1
公开(公告)日：2021-03-18
申请号：US17022771
申请日：2020-09-16
摘要： Methods and systems for observation prediction in autonomous vehicles are described. A set of observations is received, including a current observation and one or more previous observations. Each observation includes a respective view of the environment and a vehicle state at each time step. A current action is received. A current-action embedded view is produced, the current-action embedded view representing an estimated change in vehicle state caused by the current action in a current view. A predicted view is generated from the current-action embedded view and the set of observations. The predicted view is re-centered. A predicted observation is fed back, including the re-centered predicted view and estimated change in vehicle state, to be included in the set of observations as input for multi-step training of the action-based prediction subsystem.
-
公开(公告)号：US20230022896A1
公开(公告)日：2023-01-26
申请号：US17958944
申请日：2022-10-03
申请人： Jun LUO , Julian VILLELLA , Mohsen ROHANI, , David RUSU , Montgomery ALBAN , Seyed Ershad BANIJAMALI
发明人： Jun LUO , Julian VILLELLA , Mohsen ROHANI, , David RUSU , Montgomery ALBAN , Seyed Ershad BANIJAMALI
摘要： Method and system for controlling the behavior of an object. Behavior of the object is controlled during a first time period by using a first agent that applies a first behavior policy to map observations about the object and the environment in the first time period to a corresponding control action. Control is transitioned from the first agent to a second agent during a transition period following the first time period. Behavior of the object during a second time period following the transition period is controlled by using a second agent that applies a second behavior policy to map observations about the object and the environment in the second time period to a corresponding control action that is applied to the object. During transition the first agent applies the first behavior policy control the object and the second agent applies the second behavior policy to map observations about the object and the environment to corresponding control actions that are not applied to the object.
-
-
-
-
搜索结果
5 条记录 (耗时 0.012 秒)
