-
公开(公告)号：US12228936B2
公开(公告)日：2025-02-18
申请号：US18096695
申请日：2023-01-13
Applicant: Gatik AI Inc.
Inventor： Gautam Narang , Apeksha Kumavat , Arjun Narang , Kinh Tieu , Michael Smart , Marko Ilievski
IPC: G05D1/00 , G06F18/21 , G06F18/214 , G06N20/00 , G06V10/764 , G06V10/82 , G06V20/56
Abstract: A system for deterministic trajectory selection based on uncertainty estimation includes a set of one or more computing systems. A method for deterministic trajectory selection includes receiving a set of inputs; determining a set of outputs; determining uncertainty parameters associated with any or all of the set of inputs and/or any or all of the set of outputs; and evaluating the uncertainty parameters and optionally triggering a process and/or action in response.
-
2.发明公开公开(公告)号：US20240300531A1
公开(公告)日：2024-09-12
申请号：US18654315
申请日：2024-05-03
Applicant: Gatik AI Inc.
Inventor： Gautam Narang , Apeksha Kumavat , Arjun Narang , Kinh Tieu , Michael Smart , Marko Ilievski
IPC: B60W60/00 , B60W30/09 , B60W30/095 , G05B13/02 , G06N3/045
CPC classification number: B60W60/0011 , B60W30/09 , B60W30/0956 , G05B13/027 , G06N3/045 , B60W2420/408 , B60W2554/20 , B60W2554/40 , B60W2555/60 , B60W2556/50
Abstract: A system for data-driven, modular decision making and trajectory generation includes a computing system. A method for data-driven, modular decision making and trajectory generation includes: receiving a set of inputs; selecting a learning module such as a deep decision network and/or a deep trajectory network from a set of learning modules; producing an output based on the learning module; repeating any or all of the above processes; and/or any other suitable processes. Additionally or alternatively, the method can include training any or all of the learning modules; validating one or more outputs; and/or any other suitable processes and/or combination of processes.
-
公开(公告)号：US20220214693A1
公开(公告)日：2022-07-07
申请号：US17704301
申请日：2022-03-25
Applicant: Gatik AI Inc.
Inventor： Gautam Narang , Apeksha Kumavat , Arjun Narang , Kinh Tieu , Michael Smart , Marko Ilievski
Abstract: A system for deterministic trajectory selection based on uncertainty estimation includes a set of one or more computing systems. A method for deterministic trajectory selection includes receiving a set of inputs; determining a set of outputs; determining uncertainty parameters associated with any or all of the set of inputs and/or any or all of the set of outputs; and evaluating the uncertainty parameters and optionally triggering a process and/or action in response.
-
公开(公告)号：US20220135072A1
公开(公告)日：2022-05-05
申请号：US17579862
申请日：2022-01-20
Applicant: Gatik AI Inc.
Inventor： Gautam Narang , Apeksha Kumavat , Arjun Narang , Kinh Tieu , Michael Smart , Marko Ilievski
IPC: B60W60/00 , G05B13/02 , G06N3/04 , B60W30/095 , B60W30/09
Abstract: A system for data-driven, modular decision making and trajectory generation includes a computing system. A method for data-driven, modular decision making and trajectory generation includes: receiving a set of inputs; selecting a learning module such as a deep decision network and/or a deep trajectory network from a set of learning modules; producing an output based on the learning module; repeating any or all of the above processes; and/or any other suitable processes. Additionally or alternatively, the method can include training any or all of the learning modules; validating one or more outputs; and/or any other suitable processes and/or combination of processes.
-
公开(公告)号：US20230365153A1
公开(公告)日：2023-11-16
申请号：US18225319
申请日：2023-07-24
Applicant: Gatik AI Inc.
Inventor： Gautam Narang , Apeksha Kumavat , Arjun Narang , Kinh Tieu , Michael Smart , Marko Ilievski
IPC: B60W60/00 , G01C21/36 , H04W4/021 , G01C21/34 , G06N20/00 , G06F18/214 , G06V10/764 , G06V10/82 , G06V10/70 , G06V20/56
CPC classification number: B60W60/001 , G01C21/3673 , H04W4/021 , G01C21/3461 , G06N20/00 , G06F18/2155 , G06V10/764 , G06V10/82 , G06V10/87 , G06V20/56
Abstract: A system for context-aware decision making of an autonomous agent includes a computing system having a context selector and a map. A method for context-aware decision making of an autonomous agent includes receiving a set of inputs, determining a context associated with an autonomous agent based on the set of inputs, and optionally any or all of: labeling a map; selecting a learning module (context-specific learning module) based on the context; defining an action space based on the learning module; selecting an action from the action space; planning a trajectory based on the action S260; and/or any other suitable processes.
-
Patent Agency Ranking
6.发明公开公开(公告)号：US20230152816A1
公开(公告)日：2023-05-18
申请号：US18096695
申请日：2023-01-13
Applicant: Gatik AI Inc.
Inventor： Gautam Narang , Apeksha Kumavat , Arjun Narang , Kinh Tieu , Michael Smart , Marko Ilievski
IPC: G05D1/02 , G05D1/00 , G06N20/00 , G06F18/21 , G06F18/214 , G06V10/764 , G06V10/82 , G06V20/56
CPC classification number: G05D1/0219 , G05D1/0221 , G05D1/0088 , G06N20/00 , G05D1/0214 , G06F18/217 , G06F18/2155 , G06V10/764 , G06V10/82 , G06V20/56
Abstract: A system for deterministic trajectory selection based on uncertainty estimation includes a set of one or more computing systems. A method for deterministic trajectory selection includes receiving a set of inputs; determining a set of outputs; determining uncertainty parameters associated with any or all of the set of inputs and/or any or all of the set of outputs; and evaluating the uncertainty parameters and optionally triggering a process and/or action in response.
-
公开(公告)号：US11586214B2
公开(公告)日：2023-02-21
申请号：US17704301
申请日：2022-03-25
Applicant: Gatik AI Inc.
Inventor： Gautam Narang , Apeksha Kumavat , Arjun Narang , Kinh Tieu , Michael Smart , Marko Ilievski
Abstract: A system for deterministic trajectory selection based on uncertainty estimation includes a set of one or more computing systems. A method for deterministic trajectory selection includes receiving a set of inputs; determining a set of outputs; determining uncertainty parameters associated with any or all of the set of inputs and/or any or all of the set of outputs; and evaluating the uncertainty parameters and optionally triggering a process and/or action in response.
-
公开(公告)号：US11487296B2
公开(公告)日：2022-11-01
申请号：US17685905
申请日：2022-03-03
Applicant: Gatik AI Inc.
Inventor： Gautam Narang , Apeksha Kumavat , Arjun Narang , Kinh Tieu , Michael Smart , Marko Ilievski
Abstract: A system for deterministic trajectory selection based on uncertainty estimation includes a set of one or more computing systems. A method for deterministic trajectory selection includes receiving a set of inputs; determining a set of outputs; determining uncertainty parameters associated with any or all of the set of inputs and/or any or all of the set of outputs; and evaluating the uncertainty parameters and optionally triggering a process and/or action in response.
-
公开(公告)号：US20220315042A1
公开(公告)日：2022-10-06
申请号：US17846870
申请日：2022-06-22
Applicant: Gatik AI Inc.
Inventor： Gautam Narang , Apeksha Kumavat , Arjun Narang , Kinh Tieu , Michael Smart , Marko Ilievski
Abstract: A system for context-aware decision making of an autonomous agent includes a computing system having a context selector and a map. A method for context-aware decision making of an autonomous agent includes receiving a set of inputs, determining a context associated with an autonomous agent based on the set of inputs, and optionally any or all of: labeling a map; selecting a learning module (context-specific learning module) based on the context; defining an action space based on the learning module; selecting an action from the action space; planning a trajectory based on the action S260; and/or any other suitable processes.
-
公开(公告)号：US11260883B2
公开(公告)日：2022-03-01
申请号：US17333518
申请日：2021-05-28
Applicant: Gatik AI Inc.
Inventor： Gautam Narang , Apeksha Kumavat , Arjun Narang , Kinh Tieu , Michael Smart , Marko Ilievski
IPC: B60W30/09 , B60W60/00 , G05B13/02 , G06N3/04 , B60W30/095
Abstract: A system for data-driven, modular decision making and trajectory generation includes a computing system. A method for data-driven, modular decision making and trajectory generation includes: receiving a set of inputs; selecting a learning module such as a deep decision network and/or a deep trajectory network from a set of learning modules; producing an output based on the learning module; repeating any or all of the above processes; and/or any other suitable processes. Additionally or alternatively, the method can include training any or all of the learning modules; validating one or more outputs; and/or any other suitable processes and/or combination of processes.
-
-
-
-
-
-
-
-
-
Search Results
34
records
(took 0.021 seconds)
