公开(公告)号：US20180364717A1

公开(公告)日：2018-12-20

申请号：US15622905

申请日：2017-06-14

Applicant: Zoox, Inc.

Inventor： Bertrand Robert Douillard ,  Subhasis Das ,  Zeng Wang ,  Dragomir Dimitrov Anguelov ,  Jesse Sol Levinson

IPC: G05D1/02 ,  G06T7/11 ,  G06K9/00 ,  G01S17/89 ,  G01S17/93

CPC classification number: G05D1/024 ,  G01S13/726 ,  G01S13/862 ,  G01S13/865 ,  G01S13/867 ,  G01S13/931 ,  G01S15/025 ,  G01S15/931 ,  G01S17/023 ,  G01S17/58 ,  G01S17/66 ,  G01S17/89 ,  G01S17/936 ,  G05D1/0212 ,  G06K9/00791 ,  G06T7/11 ,  G06T7/187 ,  G06T2207/10028 ,  G06T2207/30252

Abstract: Systems, methods, and apparatuses described herein are directed to performing segmentation on voxels representing three-dimensional data to identify static and dynamic objects. LIDAR data may be captured by a perception system for an autonomous vehicle and represented in a voxel space. Operations may include determining a drivable surface by parsing individual voxels to determine an orientation of a surface normal of a planar approximation of the voxelized data relative to a reference direction. Clustering techniques can be used to grow a ground plane including a plurality of locally flat voxels. Ground plane data can be set aside from the voxel space, and the remaining voxels can be clustered to determine objects. Voxel data can be analyzed over time to determine dynamic objects. Segmentation information associated with ground voxels, static object, and dynamic objects can be provided to a tracker and/or planner in conjunction with operating the autonomous vehicle.

公开(公告)号：US20250022284A1

公开(公告)日：2025-01-16

申请号：US18750796

申请日：2024-06-21

Applicant: Zoox, Inc.

Inventor： Scott M. Purdy ,  Derek Xiang Ma ,  Subhasis Das ,  Zeng Wang

IPC: G06V20/58 ,  B60W60/00 ,  G01S17/931 ,  G06T7/20 ,  G06T7/50 ,  G06V10/44

Abstract: Techniques are discussed herein for controlling autonomous vehicles within a driving environment, including generating and using bounding contours associated with objects detected in the environment. Image data may be captured and analyzed to identify and/or classify objects within the environment. Image-based and/or lidar-based techniques may be used to determine depth data associated with the objects, and a bounding contour may be determined based on the object boundaries and associated depth data. An autonomous vehicle may use the bounding contours of objects within the environment to classify the objects, predict the positions, poses, and trajectories of the objects, and determine trajectories and perform other vehicle control actions while safely navigating the environment.

公开(公告)号：US12012127B2

公开(公告)日：2024-06-18

申请号：US16779576

申请日：2020-01-31

Applicant: Zoox, Inc.

Inventor： Subhasis Das ,  Benjamin Isaac Zwiebel ,  Kai Yu ,  James William Vaisey Philbin

IPC: B60W60/00 ,  G01S13/89 ,  G01S13/931 ,  G01S17/89 ,  G01S17/931 ,  G05D1/00 ,  G06T7/215 ,  G06T7/246 ,  G06T7/292 ,  G06V10/25 ,  G06V10/778 ,  G06V10/80 ,  G06V20/56 ,  G06V30/19 ,  G06V30/24

CPC classification number: B60W60/0027 ,  G01S13/89 ,  G01S13/931 ,  G01S17/89 ,  G01S17/931 ,  G05D1/0248 ,  G06T7/215 ,  G06T7/251 ,  G06T7/292 ,  G06V10/25 ,  G06V10/778 ,  G06V10/80 ,  G06V20/56 ,  G06V30/19147 ,  G06V30/19173 ,  G06V30/1918 ,  G06V30/2552 ,  G01S2013/932 ,  G06T2207/20081 ,  G06T2207/20084 ,  G06T2207/30241 ,  G06T2207/30261

Abstract: Tracking a current and/or previous position, velocity, acceleration, and/or heading of an object using sensor data may comprise determining whether to associate a current object detection generated from recently received (e.g., current) sensor data with a previous object detection generated from formerly received sensor data. In other words, a track may identify that an object detected in former sensor data is the same object detected in current sensor data. However, multiple types of sensor data may be used to detect objects and some objects may not be detected by different sensor types or may be detected differently, which may confound attempts to track an object. An ML model may be trained to receive outputs associated with different sensor types and/or a track associated with an object, and determine a data structure comprising a region of interest, object classification, and/or a pose associated with the object.

公开(公告)号：US11879978B1

公开(公告)日：2024-01-23

申请号：US16549694

申请日：2019-08-23

Applicant: Zoox, Inc.

Inventor： Subhasis Das ,  Chuang Wang ,  Sabeek Mani Pradhan

IPC: G01S17/89 ,  G01S19/39 ,  G01C21/34 ,  G05D1/02 ,  G06N20/00

CPC classification number: G01S17/89 ,  G01C21/3492 ,  G01S19/393 ,  G05D1/0221 ,  G05D1/0223 ,  G06N20/00

Abstract: Techniques for updating data operations in a perception system are discussed herein. A vehicle may use a perception system to capture data about an environment proximate to the vehicle. The perception system may receive image data, lidar data, and/or radar data to determine information about an object in the environment. As different sensors may be associated with different time periods for capturing and/or processing operations, the techniques include updating object data with data from sensors associated with a shorter time period to generate intermediate object data.

公开(公告)号：US11814070B1

公开(公告)日：2023-11-14

申请号：US17490503

申请日：2021-09-30

Applicant: Zoox, Inc.

Inventor： Antonio Prioletti ,  Subhasis Das ,  Minsu Jang ,  He Yi

IPC: B60W60/00 ,  G07C5/00 ,  G05B17/02 ,  B60W50/00

CPC classification number: B60W60/001 ,  B60W50/00 ,  G05B17/02 ,  G07C5/008 ,  B60W2050/0028 ,  B60W2050/0083 ,  B60W2554/402 ,  B60W2554/4041 ,  B60W2554/4042 ,  B60W2554/4043 ,  B60W2554/4044 ,  B60W2554/801 ,  B60W2554/802 ,  B60W2555/20

Abstract: Techniques for determining error models for use in simulations are discussed herein. Ground truth perception data and vehicle perception data can be determined from vehicle log data. Further, objects in the log data can be identified as relevant objects by signals output by a planner system or based on the object being located in a driving corridor. Differences between the ground truth perception data and the vehicle perception data can be determined and used to generate error models for the relevant objects. The error models can be applied to objects during simulation to increase realism and test vehicle components.

公开(公告)号：US11782815B2

公开(公告)日：2023-10-10

申请号：US17581699

申请日：2022-01-21

Applicant: Zoox, Inc.

Inventor： Michael Carsten Bosse ,  Gerry Chen ,  Subhasis Das ,  Francesco Papi ,  Zachary Sun

IPC: G06F11/36 ,  B60W50/02 ,  B60W50/04 ,  G06F11/34 ,  B60W40/04

CPC classification number: G06F11/3612 ,  B60W40/04 ,  B60W50/0205 ,  B60W50/045 ,  G06F11/3409 ,  B60W2050/0215 ,  B60W2554/4041 ,  B60W2556/45

Abstract: A computer-implemented method. Includes obtaining pointwise data indicating, for a plurality of time steps, a pointwise measurement of a state of an object detected by an object detection system. Includes obtaining, from a runtime model, runtime data indicating, for the plurality of time steps, a runtime estimate of the state of the object. Includes processing, by a benchmark model, the pointwise data to determine, for the plurality of time steps, a benchmark estimate of the state of the object. Includes evaluating a metric measuring, for the plurality of time steps, a deviation between the runtime estimate and the benchmark estimate of the state of the object. Includes updating, based on the on the evaluation of the metric, the runtime model.

公开(公告)号：US11710296B2

公开(公告)日：2023-07-25

申请号：US17542354

申请日：2021-12-03

Applicant: Zoox, Inc.

Inventor： Cheng-Hsin Wuu ,  Subhasis Das ,  Po-Jen Lai ,  Qian Song ,  Benjamin Isaac Zwiebel

IPC: G06V10/70 ,  G06V20/58 ,  G06V20/40 ,  G06V20/56

CPC classification number: G06V10/70 ,  G06V20/41 ,  G06V20/582 ,  G06V20/584 ,  G06V20/588

Abstract: Techniques for a perception system of a vehicle that can detect and track objects in an environment are described herein. The perception system may include a machine-learned model that includes one or more different portions, such as different components, subprocesses, or the like. In some instances, the techniques may include training the machine-learned model end-to-end such that outputs of a first portion of the machine-learned model are tailored for use as inputs to another portion of the machine-learned model. Additionally, or alternatively, the perception system described herein may utilize temporal data to track objects in the environment of the vehicle and associate tracking data with specific objects in the environment detected by the machine-learned model. That is, the architecture of the machine-learned model may include both a detection portion and a tracking portion in the same loop.

公开(公告)号：US20230174110A1

公开(公告)日：2023-06-08

申请号：US17542352

申请日：2021-12-03

Applicant: Zoox, Inc.

Inventor： Cheng-Hsin Wuu ,  Subhasis Das ,  Po-Jen Lai ,  Qian Song ,  Benjamin Isaac Zwiebel

IPC: B60W60/00 ,  G06V20/58 ,  G06V10/764 ,  G06N20/00

CPC classification number: B60W60/0027 ,  G06V20/58 ,  G06V10/764 ,  G06N20/00 ,  B60W2554/404 ,  B60W2554/80

Abstract: Techniques for a perception system of a vehicle that can detect and track objects in an environment are described herein. The perception system may include a machine-learned model that includes one or more different portions, such as different components, subprocesses, or the like. In some instances, the techniques may include training the machine-learned model end-to-end such that outputs of a first portion of the machine-learned model are tailored for use as inputs to another portion of the machine-learned model. Additionally, or alternatively, the perception system described herein may utilize temporal data to track objects in the environment of the vehicle and associate tracking data with specific objects in the environment detected by the machine-learned model. That is, the architecture of the machine-learned model may include both a detection portion and a tracking portion in the same loop.

公开(公告)号：US11625041B2

公开(公告)日：2023-04-11

申请号：US16797656

申请日：2020-02-21

Applicant: Zoox, Inc.

Inventor： Subhasis Das ,  Shida Shen ,  Kai Yu ,  Benjamin Isaac Zwiebel

IPC: G05D1/02 ,  G06T7/20 ,  G06N20/00 ,  G06K9/62 ,  G06N3/084 ,  G06V10/25 ,  G06V20/64

Abstract: Techniques are disclosed for a combined machine learned (ML) model that may generate a track confidence metric associated with a track and/or a classification of an object. Techniques may include obtaining a track. The track, which may include object detections from one or more sensor data types and/or pipelines, may be input into a machine-learning (ML) model. The model may output a track confidence metric and a classification. In some examples, if the track confidence metric does not satisfy a threshold, the ML model may cause the suppression of the output of the track to a planning component of an autonomous vehicle.

公开(公告)号：US20220366703A1

公开(公告)日：2022-11-17

申请号：US17827182

申请日：2022-05-27

Applicant: Zoox, Inc.

Inventor： Shiwei Sheng ,  Subhasis Das ,  Yassen Ivanchev Dobrev ,  Chuang Wang

IPC: G06V20/58 ,  G06T7/277

Abstract: Navigation systems can identify objects in an environment and generate representations of those objects. A representation of an articulated vehicle can include two segments rotated relative to each other about a pivot, with a first segment corresponding to a first portion of the articulated vehicle and the second segment corresponding to a second portion of the articulated vehicle. The articulated object can be tracked in the environment by generating estimated updated states of the articulated agent based on previous states and/or measured states of the object using differing motion model updates for the differing portions. The estimated updated states may be determined using one or more filtering algorithms, which may be constrained using pseudo-observables.