Patents by Inventor Sandeep Gangundi
Sandeep Gangundi 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: 20240161511Abstract: Systems and techniques are provided for processing data from an optical sensor. An example method includes obtaining, from an optical sensor configured to rotate about an axis, sensor data; generating, based on the sensor data, slices of sensor data, each slice having a field-of-coverage (FOC) that is less than 360 degrees, wherein a slice size is determined based on a rate for publishing a combination of slices that yields 360 degrees of coverage within a threshold period, a number and size of slices estimated to yield a combined FOC of 360 degrees while achieving a desired reduction in a resources contention by consumer nodes, and/or a field-of-view (FOV) of a camera device; and providing, to the consumer nodes, a partial optical sensor scan comprising the slices of sensor data, the partial optical sensor scan being provided prior to obtaining a revolution of sensor data having a 360 degrees of coverage.Type: ApplicationFiled: November 10, 2022Publication date: May 16, 2024Inventors: Sandeep Gangundi, Cornelis Jacob Lekkerkerker, Pulkit Budhiraja, Victor Oliveira, Zachary Witte
-
Patent number: 11904870Abstract: The subject disclosure relates to techniques for managing the configuration of vehicles. A process of the disclosed technology can include steps of receiving a first vehicle identifier for a first vehicle, wherein the first vehicle is associated with a first vehicle platform, identifying a first configuration for the first vehicle platform based on the first vehicle identifier, receiving a second vehicle identifier for a second vehicle, wherein the second vehicle is associated with a second vehicle platform, and wherein the first vehicle platform is different from the second vehicle platform, and identifying a second configuration for the second vehicle platform based on the second vehicle identifier, wherein the first vehicle and the second vehicle run on an identical software stack. Systems and machine-readable media are also provided.Type: GrantFiled: December 27, 2021Date of Patent: February 20, 2024Assignee: GM Cruise Holdings LLCInventors: Zachary Witte, Sandeep Gangundi, Abdelrahman Elogeel
-
Publication number: 20230333226Abstract: The subject disclosure relates to ways to identify self-hit data collected by autonomous vehicle (AV) sensors. In some aspects, a method of the disclosed technology includes steps for generating a geometric model of an autonomous vehicle (AV), wherein the geometric model specifies physical boundaries of the AV in three-dimensional (3D) space, collecting sensor data for an environment around the AV, and identifying one or more data points, from among the collected sensor data, that correspond with a surface of the AV. Systems and machine-readable media are also provided.Type: ApplicationFiled: June 27, 2023Publication date: October 19, 2023Inventors: Sandeep Gangundi, Avinash Nair, Abdelrahman Elogeel, Kyle Vogt, Cornelis Jacob Lekkerkerker
-
Publication number: 20230326194Abstract: The disclosed technology provides methods for training of a convolutional neural network (CNN) to identify or predict its own errors, and then those errors are used as inputs with feature visualization to generate images of scenes associated with those errors. This allows adjustment of a set of labeled training images, and then the adjusted set of labeled training images are used to retrain or further train the CNN. Systems and machine-readable media are also provided.Type: ApplicationFiled: April 6, 2022Publication date: October 12, 2023Inventors: Craig Quiter, Siddhartho Bhattacharya, Mayank Ketkar, Raluca Musaloiu-Elefteri, Wanlin Yang, Sandeep Gangundi
-
Patent number: 11754719Abstract: Distance measurements are received from one or more distance measurement sensors, which may be coupled to a vehicle. A three-dimensional (3D) point cloud are generated based on the distance measurements. In some cases, 3D point clouds corresponding to distance measurements from different distance measurement sensors may be combined into one 3D point cloud. A voxelized model is generated based on the 3D point cloud. An object may be detected within the voxelized model, and in some cases may be classified by object type. If the distance measurement sensors are coupled to a vehicle, the vehicle may avoid the detected object.Type: GrantFiled: July 30, 2021Date of Patent: September 12, 2023Assignee: GM Cruise Holdings LLCInventors: Sandeep Gangundi, Sarthak Sahu, Nathan Harada, Phil Ferriere
-
Publication number: 20230256988Abstract: Methods and systems are provided for dynamically adjusting at least one setting of a lidar. In some aspects, a process can include steps for receiving, at an autonomous vehicle system, road condition data associated with an autonomous vehicle, generating, by the autonomous vehicle system, instructions to adjust the at least one setting of the lidar of the autonomous vehicle based on the road condition data, and providing, by the autonomous vehicle system, the instructions to adjust the at least one setting of the lidar to the lidar, the instructions including updating firmware of the lidar to adjust the at least one setting of the lidar.Type: ApplicationFiled: February 17, 2022Publication date: August 17, 2023Inventor: Sandeep Gangundi
-
Patent number: 11726188Abstract: The subject disclosure relates to ways to identify self-hit data collected by autonomous vehicle (AV) sensors. In some aspects, a method of the disclosed technology includes steps for generating a geometric model of an autonomous vehicle (AV), wherein the geometric model specifies physical boundaries of the AV in three-dimensional (3D) space, collecting sensor data for an environment around the AV, and identifying one or more data points, from among the collected sensor data, that correspond with a surface of the AV. Systems and machine-readable media are also provided.Type: GrantFiled: April 22, 2020Date of Patent: August 15, 2023Assignee: GM Cruise Holdings LLCInventors: Sandeep Gangundi, Avinash Nair, Abdelrahman Elogeel, Kyle Vogt, Cornelis Jacob Lekkerkerker
-
Publication number: 20230251384Abstract: The present technology is directed to generating augmented data that are used for training a machine-learning (ML) algorithm to recognize objects under different weather conditions. The present technology may include receiving, by one or more processors, data of an environment including objects in a first geographical location. The data of the environment may be received from sensors on a vehicle moving on a road under a first weather condition. The present technology may also include receiving reference data that represent a second weather condition. The second weather condition may include a precipitation type. The present technology may also include generating augmented data including a subset of the reference data superimposed on the data of the environment. The augmented data simulates the environment under the second weather condition to simulate the environment under the second weather condition.Type: ApplicationFiled: February 9, 2022Publication date: August 10, 2023Inventor: Sandeep Gangundi
-
Publication number: 20230215134Abstract: The disclosed technology provides solutions for finding samples from image data that are similar to failure cases, by constructing N-dimensional vectors of the failure cases. The vectors of failure cases are compared to other image data, with the objective of identifying groups of images that can be labeled. The labeled images are then used to retrain a model. Systems and machine-readable media are also provided.Type: ApplicationFiled: January 4, 2022Publication date: July 6, 2023Inventors: Siddhartho Bhattacharya, Craig Quiter, Mayank Ketkar, Wanlin Yang, Sandeep Gangundi, Raluca Musaloiu-Elefteri
-
Publication number: 20230202489Abstract: The subject disclosure relates to techniques for managing the configuration of vehicles. A process of the disclosed technology can include steps of receiving a first vehicle identifier for a first vehicle, wherein the first vehicle is associated with a first vehicle platform, identifying a first configuration for the first vehicle platform based on the first vehicle identifier, receiving a second vehicle identifier for a second vehicle, wherein the second vehicle is associated with a second vehicle platform, and wherein the first vehicle platform is different from the second vehicle platform, and identifying a second configuration for the second vehicle platform based on the second vehicle identifier, wherein the first vehicle and the second vehicle run on an identical software stack. Systems and machine-readable media are also provided.Type: ApplicationFiled: December 27, 2021Publication date: June 29, 2023Inventors: Zachary Witte, Sandeep Gangundi, Abdelrahman Elogeel
-
Publication number: 20230204738Abstract: Autonomous Vehicles (AVs) can navigate roadways without a human driver by using sensors, such as Lidar sensors, positioned around the AV. Systems, apparatuses, methods, computer readable medium, and circuits are provided for emulating a Lidar point cloud of an evaluation Lidar to be evaluated by transforming historical data received from a reference Lidar in order to determine a performance difference between the evaluation Lidar and the reference Lidar.Type: ApplicationFiled: December 27, 2021Publication date: June 29, 2023Inventors: Sandeep Gangundi, Pulkit Budhiraja, Zhaoyin Jia
-
Patent number: 11574097Abstract: Techniques to improve the accuracy and speed for detection and remediation of difficult to test nodes in a circuit design netlist. The techniques utilize improved netlist representations, test point insertion, and trained neural networks.Type: GrantFiled: April 15, 2021Date of Patent: February 7, 2023Assignee: NVIDIA CORP.Inventors: Harbinder Sikka, Kaushik Narayanun, Lijuan Luo, Karthikeyan Natarajan, Manjunatha Gowda, Sandeep Gangundi
-
Publication number: 20210358145Abstract: Distance measurements are received from one or more distance measurement sensors, which may be coupled to a vehicle. A three-dimensional (3D) point cloud are generated based on the distance measurements. In some cases, 3D point clouds corresponding to distance measurements from different distance measurement sensors may be combined into one 3D point cloud. A voxelized model is generated based on the 3D point cloud. An object may be detected within the voxelized model, and in some cases may be classified by object type. If the distance measurement sensors are coupled to a vehicle, the vehicle may avoid the detected object.Type: ApplicationFiled: July 30, 2021Publication date: November 18, 2021Inventors: Sandeep Gangundi, Sarthak Sahu, Nathan Harada, Phil Ferriere
-
Publication number: 20210333373Abstract: The subject disclosure relates to ways to identify self-hit data collected by autonomous vehicle (AV) sensors. In some aspects, a method of the disclosed technology includes steps for generating a geometric model of an autonomous vehicle (AV), wherein the geometric model specifies physical boundaries of the AV in three-dimensional (3D) space, collecting sensor data for an environment around the AV, and identifying one or more data points, from among the collected sensor data, that correspond with a surface of the AV. Systems and machine-readable media are also provided.Type: ApplicationFiled: April 22, 2020Publication date: October 28, 2021Inventors: Sandeep Gangundi, Avinash Nair, Abdelrahman Elogeel, Kyle Vogt, Cornelis Jacob Lekkerkerker
-
Publication number: 20210295169Abstract: Techniques to improve the accuracy and speed for detection and remediation of difficult to test nodes in a circuit design netlist. The techniques utilize improved netlist representations, test point insertion, and trained neural networks.Type: ApplicationFiled: April 15, 2021Publication date: September 23, 2021Applicant: NVIDIA Corp.Inventors: Harbinder Sikka, Kaushik Narayanun, Lijuan Luo, Karthikeyan Natarajan, Manjunatha Gowda, Sandeep Gangundi
-
Patent number: 11107227Abstract: Distance measurements are received from one or more distance measurement sensors, which may be coupled to a vehicle. A three-dimensional (3D) point cloud are generated based on the distance measurements. In some cases, 3D point clouds corresponding to distance measurements from different distance measurement sensors may be combined into one 3D point cloud. A voxelized model is generated based on the 3D point cloud. An object may be detected within the voxelized model, and in some cases may be classified by object type. If the distance measurement sensors are coupled to a vehicle, the vehicle may avoid the detected object.Type: GrantFiled: February 19, 2020Date of Patent: August 31, 2021Assignee: GM Cruise Holdings, LLCInventors: Sandeep Gangundi, Sarthak Sahu, Nathan Harada, Phil Ferriere
-
Publication number: 20210256718Abstract: Distance measurements are received from one or more distance measurement sensors, which may be coupled to a vehicle. A three-dimensional (3D) point cloud are generated based on the distance measurements. In some cases, 3D point clouds corresponding to distance measurements from different distance measurement sensors may be combined into one 3D point cloud. A voxelized model is generated based on the 3D point cloud. An object may be detected within the voxelized model, and in some cases may be classified by object type. If the distance measurement sensors are coupled to a vehicle, the vehicle may avoid the detected object.Type: ApplicationFiled: February 19, 2020Publication date: August 19, 2021Inventors: Sandeep Gangundi, Sarthak Sahu, Nathan Harada, Phil Ferriere
-
Patent number: 11010516Abstract: Techniques to improve the accuracy and speed for detection and remediation of difficult to test nodes in a circuit design netlist. The techniques utilize improved netlist representations, test point insertion, and trained neural networks.Type: GrantFiled: August 9, 2019Date of Patent: May 18, 2021Assignee: NVIDIA Corp.Inventors: Harbinder Sikka, Kaushik Narayanun, Lijuan Luo, Karthikeyan Natarajan, Manjunatha Gowda, Sandeep Gangundi
-
Publication number: 20200151289Abstract: Techniques to improve the accuracy and speed for detection and remediation of difficult to test nodes in a circuit design netlist. The techniques utilize improved netlist representations, test point insertion, and trained neural networks.Type: ApplicationFiled: August 9, 2019Publication date: May 14, 2020Applicant: NVIDIA Corp.Inventors: Harbinder Sikka, Kaushik Narayanun, Lijuan Luo, Karthikeyan Natarajan, Manjunatha Gowda, Sandeep Gangundi