Patents by Inventor Nemanja Djuric
Nemanja Djuric has filed for patents to protect the following inventions. This listing includes patent applications that are pending as well as patents that have already been granted by the United States Patent and Trademark Office (USPTO).
-
Publication number: 20240124028Abstract: Various examples are directed to systems and methods for controlling an autonomous vehicle comprising a tractor and a trailer. For example, a system may determine that a line from a position of a first sensor on the autonomous vehicle to a position of a first actor in an environment of the autonomous vehicle intersects the trailer. The system may determine that the first actor is in a blind spot of the autonomous vehicle, generate a motion plan for the autonomous vehicle, and control the autonomous vehicle in accordance with the motion plan.Type: ApplicationFiled: October 14, 2022Publication date: April 18, 2024Inventors: Nemanja Djuric, Shivam Gautam, Abhishek Mohta
-
Publication number: 20240103522Abstract: An autonomous platform can obtain sensor data descriptive of an actor in an environment of an autonomous vehicle and at least a portion of the environment of the autonomous vehicle that does not include the actor, the sensor data comprising at least one sweep of the environment of the autonomous vehicle; process the sensor data with a machine-learned perception model to generate a detection of the actor and one or more predicted future velocities; and determine a motion trajectory for the autonomous vehicle based at least in part on the detection and the one or more predicted future velocities.Type: ApplicationFiled: September 27, 2022Publication date: March 28, 2024Inventors: Nemanja Djuric, Shivam Gautam, Peter M. Kingston, Chi-Kuei Liu
-
Patent number: 11851087Abstract: Systems, methods, tangible non-transitory computer-readable media, and devices associated with trajectory prediction are provided. For example, trajectory data and goal path data can be accessed. The trajectory data can be associated with an object's predicted trajectory. The predicted trajectory can include waypoints associated with waypoint position uncertainty distributions that can be based on an expectation maximization technique. The goal path data can be associated with a goal path and include locations the object is predicted to travel. Solution waypoints for the object can be determined based on application of optimization techniques to the waypoints and waypoint position uncertainty distributions. The optimization techniques can include operations to maximize the probability of each of the solution waypoints. Stitched trajectory data can be generated based on the solution waypoints. The stitched trajectory data can be associated with portions of the solution waypoints and the goal path.Type: GrantFiled: July 26, 2022Date of Patent: December 26, 2023Assignee: UATC, LLCInventors: Nemanja Djuric, Sai Bhargav Yalamanchi, Galen Clark Haynes, Tzu-Kuo Huang
-
Patent number: 11835951Abstract: Systems and methods for predicting object motion and controlling autonomous vehicles are provided. In one example embodiment, a computer implemented method includes obtaining state data indicative of at least a current or a past state of an object that is within a surrounding environment of an autonomous vehicle. The method includes obtaining data associated with a geographic area in which the object is located. The method includes generating a combined data set associated with the object based at least in part on a fusion of the state data and the data associated with the geographic area in which the object is located. The method includes obtaining data indicative of a machine-learned model. The method includes inputting the combined data set into the machine-learned model. The method includes receiving an output from the machine-learned model. The output can be indicative of a plurality of predicted trajectories of the object.Type: GrantFiled: September 3, 2021Date of Patent: December 5, 2023Assignee: UATC, LLCInventors: Nemanja Djuric, Vladan Radosavljevic, Thi Duong Nguyen, Tsung-Han Lin, Jeff Schneider, Henggang Cui, Fang-Chieh Chou, Tzu-Kuo Huang
-
Patent number: 11762391Abstract: Systems and methods for training machine-learned models are provided. A method can include receiving a rasterized image associated with a training object and generating a predicted trajectory of the training object by inputting the rasterized image into a first machine-learned model. The method can include converting the predicted trajectory into a rasterized trajectory that spatially corresponds to the rasterized image. The method can include utilizing a second machine-learned model to determine an accuracy of the predicted trajectory based on the rasterized trajectory. The method can include determining an overall loss for the first machine-learned model based on the accuracy of the predictive trajectory as determined by the second machine-learned model. The method can include training the first machine-learned model by minimizing the overall loss for the first machine-learned model.Type: GrantFiled: September 9, 2022Date of Patent: September 19, 2023Assignee: UATC, LLCInventors: Henggang Cui, Junheng Wang, Sai Bhargav Yalamanchi, Mohana Prasad Sathya Moorthy, Fang-Chieh Chou, Nemanja Djuric
-
Patent number: 11635764Abstract: Systems, methods, tangible non-transitory computer-readable media, and devices associated with the motion prediction and operation of a device including a vehicle are provided. For example, a vehicle computing system can access state data including information associated with locations and characteristics of objects over a plurality of time intervals. Trajectories of the objects at subsequent time intervals following the plurality of time intervals can be determined based on the state data and a machine-learned tracking and kinematics model. The trajectories of the objects can include predicted locations of the objects at subsequent time intervals that follow the plurality of time intervals. Further, the predicted locations of the objects can be based on physical constraints of the objects. Furthermore, indications, which can include visual indications, can be generated based on the predicted locations of the objects at the subsequent time intervals.Type: GrantFiled: July 9, 2019Date of Patent: April 25, 2023Assignee: UATC, LLC.Inventors: Nemanja Djuric, Henggang Cui, Thi Duong Nguyen, Fang-Chieh Chou, Tsung-Han Lin, Jeff Schneider, David McAllister Bradley
-
Publication number: 20230021034Abstract: Systems and methods for training machine-learned models are provided. A method can include receiving a rasterized image associated with a training object and generating a predicted trajectory of the training object by inputting the rasterized image into a first machine-learned model. The method can include converting the predicted trajectory into a rasterized trajectory that spatially corresponds to the rasterized image. The method can include utilizing a second machine-learned model to determine an accuracy of the predicted trajectory based on the rasterized trajectory. The method can include determining an overall loss for the first machine-learned model based on the accuracy of the predictive trajectory as determined by the second machine-learned model. The method can include training the first machine-learned model by minimizing the overall loss for the first machine-learned model.Type: ApplicationFiled: September 9, 2022Publication date: January 19, 2023Inventors: Henggang Cui, Junheng Wang, Sai Bhargav Yalamanchi, Mohana Prasad Sathya Moorthy, Fang-Chieh Chou, Nemanja Djuric
-
Publication number: 20220388537Abstract: Systems, methods, tangible non-transitory computer-readable media, and devices associated with trajectory prediction are provided. For example, trajectory data and goal path data can be accessed. The trajectory data can be associated with an object's predicted trajectory. The predicted trajectory can include waypoints associated with waypoint position uncertainty distributions that can be based on an expectation maximization technique. The goal path data can be associated with a goal path and include locations the object is predicted to travel. Solution waypoints for the object can be determined based on application of optimization techniques to the waypoints and waypoint position uncertainty distributions. The optimization techniques can include operations to maximize the probability of each of the solution waypoints. Stitched trajectory data can be generated based on the solution waypoints. The stitched trajectory data can be associated with portions of the solution waypoints and the goal path.Type: ApplicationFiled: July 26, 2022Publication date: December 8, 2022Inventors: Nemanja Djuric, Sai Bhargav Yalamanchi, Galen Clark Haynes, Tzu-Kuo Huang
-
Patent number: 11488277Abstract: A transport system can manage an on-demand transportation service to connect available vehicles with users, and can compile ride history data for each user. The ride history data can indicate the contextual usage of the on-demand transportation service by the user. Based on the ride history data, the transport system can determine demographic and personal interest information of the respective user. The transport system may then personalize one or more ride characteristics of any ride requested by the user based on the demographic and personal interest information determined from the ride history of the user.Type: GrantFiled: November 8, 2019Date of Patent: November 1, 2022Assignee: Uber Technologies, Inc.Inventors: Nemanja Djuric, Vladan Radosavljevic
-
Patent number: 11442459Abstract: Systems and methods for training machine-learned models are provided. A method can include receiving a rasterized image associated with a training object and generating a predicted trajectory of the training object by inputting the rasterized image into a first machine-learned model. The method can include converting the predicted trajectory into a rasterized trajectory that spatially corresponds to the rasterized image. The method can include utilizing a second machine-learned model to determine an accuracy of the predicted trajectory based on the rasterized trajectory. The method can include determining an overall loss for the first machine-learned model based on the accuracy of the predictive trajectory as determined by the second machine-learned model. The method can include training the first machine-learned model by minimizing the overall loss for the first machine-learned model.Type: GrantFiled: February 6, 2020Date of Patent: September 13, 2022Assignee: UATC, LLCInventors: Henggang Cui, Junheng Wang, Sai Bhargav Yalamanchi, Mohana Prasad Sathya Moorthy, Fang-Chieh Chou, Nemanja Djuric
-
Patent number: 11420648Abstract: Systems, methods, tangible non-transitory computer-readable media, and devices associated with trajectory prediction are provided. For example, trajectory data and goal path data can be accessed. The trajectory data can be associated with an object's predicted trajectory. The predicted trajectory can include waypoints associated with waypoint position uncertainty distributions that can be based on an expectation maximization technique. The goal path data can be associated with a goal path and include locations the object is predicted to travel. Solution waypoints for the object can be determined based on application of optimization techniques to the waypoints and waypoint position uncertainty distributions. The optimization techniques can include operations to maximize the probability of each of the solution waypoints. Stitched trajectory data can be generated based on the solution waypoints. The stitched trajectory data can be associated with portions of the solution waypoints and the goal path.Type: GrantFiled: February 29, 2020Date of Patent: August 23, 2022Assignee: UATC, LLCInventors: Nemanja Djuric, Sai Bhargav Yalamanchi, Galen Clark Haynes, Tzu-Kuo Huang
-
Publication number: 20220261601Abstract: Systems, methods, tangible non-transitory computer-readable media, and devices for autonomous vehicle operation are provided. For example, a computing system can receive object data that includes portions of sensor data. The computing system can determine, in a first stage of a multiple stage classification using hardware components, one or more first stage characteristics of the portions of sensor data based on a first machine-learned model. In a second stage of the multiple stage classification, the computing system can determine second stage characteristics of the portions of sensor data based on a second machine-learned model. The computing system can generate an object output based on the first stage characteristics and the second stage characteristics. The object output can include indications associated with detection of objects in the portions of sensor data.Type: ApplicationFiled: April 29, 2022Publication date: August 18, 2022Inventors: Joseph Lawrence Amato, Nemanja Djuric, Shivam Gautam, Abhishek Mohta
-
Patent number: 11263664Abstract: Disclosed are systems and methods for improving interactions with and between computers in content searching, generating, hosting and/or providing systems supported by or configured with personal computing devices, servers and/or platforms. The systems interact to identify and retrieve data within or across platforms, which can be used to improve the quality of data used in processing interactions between or among processors in such systems. The disclosed systems and methods transform user search keywords into equivalent keyword formats commonly used and/or found within messaging platforms, and compile a data set from such information from which a search for content can be based. The present disclosure, therefore, provides systems and methods that augment users' search terms with terms found in users' mailboxes for purposes of searching for, identifying and communicating content that is relevant to those users.Type: GrantFiled: December 30, 2015Date of Patent: March 1, 2022Assignee: YAHOO ASSETS LLCInventors: Varun Bhagwan, Blake Carpenter, Mihajlo Grbovic, Doug Sharp, Vladan Radosavljevic, Nemanja Djuric
-
Publication number: 20210397185Abstract: Systems and methods for predicting object motion and controlling autonomous vehicles are provided. In one example embodiment, a computer implemented method includes obtaining state data indicative of at least a current or a past state of an object that is within a surrounding environment of an autonomous vehicle. The method includes obtaining data associated with a geographic area in which the object is located. The method includes generating a combined data set associated with the object based at least in part on a fusion of the state data and the data associated with the geographic area in which the object is located. The method includes obtaining data indicative of a machine-learned model. The method includes inputting the combined data set into the machine-learned model. The method includes receiving an output from the machine-learned model. The output can be indicative of a plurality of predicted trajectories of the object.Type: ApplicationFiled: September 3, 2021Publication date: December 23, 2021Inventors: Nemanja Djuric, Vladan Radosavljevic, Thi Duong Nguyen, Tsung-Han Lin, Jeff Schneider, Henggang Cui, Fang-Chieh Chou, Tzu-Kuo Huang
-
Patent number: 11112796Abstract: Systems and methods for predicting object motion and controlling autonomous vehicles are provided. In one example embodiment, a computer implemented method includes obtaining state data indicative of at least a current or a past state of an object that is within a surrounding environment of an autonomous vehicle. The method includes obtaining data associated with a geographic area in which the object is located. The method includes generating a combined data set associated with the object based at least in part on a fusion of the state data and the data associated with the geographic area in which the object is located. The method includes obtaining data indicative of a machine-learned model. The method includes inputting the combined data set into the machine-learned model. The method includes receiving an output from the machine-learned model. The output can be indicative of a plurality of predicted trajectories of the object.Type: GrantFiled: September 5, 2018Date of Patent: September 7, 2021Assignee: UATC, LLCInventors: Nemanja Djuric, Vladan Radosavljevic, Thi Duong Nguyen, Tsung-Han Lin, Jeff Schneider, Henggang Cui, Fang-Chieh Chou, Tzu-Kuo Huang
-
Publication number: 20210269059Abstract: Systems, methods, tangible non-transitory computer-readable media, and devices associated with trajectory prediction are provided. For example, trajectory data and goal path data can be accessed. The trajectory data can be associated with an object's predicted trajectory. The predicted trajectory can include waypoints associated with waypoint position uncertainty distributions that can be based on an expectation maximization technique. The goal path data can be associated with a goal path and include locations the object is predicted to travel. Solution waypoints for the object can be determined based on application of optimization techniques to the waypoints and waypoint position uncertainty distributions. The optimization techniques can include operations to maximize the probability of each of the solution waypoints. Stitched trajectory data can be generated based on the solution waypoints. The stitched trajectory data can be associated with portions of the solution waypoints and the goal path.Type: ApplicationFiled: February 29, 2020Publication date: September 2, 2021Inventors: Nemanja Djuric, Sai Bhargav Yalamanchi, Galen Clark Haynes, Tzu-Kuo Huang
-
Publication number: 20210181754Abstract: Systems and methods for training machine-learned models are provided. A method can include receiving a rasterized image associated with a training object and generating a predicted trajectory of the training object by inputting the rasterized image into a first machine-learned model. The method can include converting the predicted trajectory into a rasterized trajectory that spatially corresponds to the rasterized image. The method can include utilizing a second machine-learned model to determine an accuracy of the predicted trajectory based on the rasterized trajectory. The method can include determining an overall loss for the first machine-learned model based on the accuracy of the predictive trajectory as determined by the second machine-learned model. The method can include training the first machine-learned model by minimizing the overall loss for the first machine-learned model.Type: ApplicationFiled: February 6, 2020Publication date: June 17, 2021Inventors: Henggang Cui, Junheng Wang, Sai Bhargav Yalamanchi, Mohana Prasad Sathya Moorthy, Fang-Chieh Chou, Nemanja Djuric
-
Publication number: 20200272160Abstract: Systems, methods, tangible non-transitory computer-readable media, and devices associated with the motion prediction and operation of a device including a vehicle are provided. For example, a vehicle computing system can access state data including information associated with locations and characteristics of objects over a plurality of time intervals. Trajectories of the objects at subsequent time intervals following the plurality of time intervals can be determined based on the state data and a machine-learned tracking and kinematics model. The trajectories of the objects can include predicted locations of the objects at subsequent time intervals that follow the plurality of time intervals. Further, the predicted locations of the objects can be based on physical constraints of the objects. Furthermore, indications, which can include visual indications, can be generated based on the predicted locations of the objects at the subsequent time intervals.Type: ApplicationFiled: July 9, 2019Publication date: August 27, 2020Inventors: Nemanja Djuric, Henggang Cui, Thi Duong Nguyen, Fang-Chieh Chou, Tsung-Han Lin, Jeff Schneider, David McAllister Bradley
-
Publication number: 20200209857Abstract: According to examples, a self-driving vehicle (“SDV”) is operable to select one of (i) an autonomous localization mode, in which the SDV autonomously operates using a localization map, or (ii) an autonomous neural network mode, in which the SDV uses a neural network component that implements one or more machine learning models. The SDV can autonomously operate on at least a segment of a planned route using the selected one of the autonomous localization mode or the autonomous neural network mode.Type: ApplicationFiled: February 5, 2019Publication date: July 2, 2020Inventors: Nemanja Djuric, John Houston, Jeffrey Schneider
-
Patent number: 10656657Abstract: Systems and methods for predicting object motion and controlling autonomous vehicles are provided. In one example embodiment, a computer implemented method includes obtaining state data indicative of at least a current or a past state of an object that is within a surrounding environment of an autonomous vehicle. The method includes obtaining data associated with a geographic area in which the object is located. The method includes generating a combined data set associated with the object based at least in part on a fusion of the state data and the data associated with the geographic area in which the object is located. The method includes obtaining data indicative of a machine-learned model. The method includes inputting the combined data set into the machine-learned model. The method includes receiving an output from the machine-learned model. The output can be indicative of a predicted trajectory of the object.Type: GrantFiled: October 13, 2017Date of Patent: May 19, 2020Assignee: UATC, LLCInventors: Nemanja Djuric, Vladan Radosavljevic, Thi Duong Nguyen, Tsung-Han Lin, Jeff Schneider