Teleassistance data prioritization for self-driving vehicles
AssigneeUber Technologies, Inc.
InventorsBenjamin Kroop, William Ross, Andrew Heine
Life of this patent
Estimating the term…
Abstract
A system can analyze a live sensor view of a self-driving vehicle (SDV) in accordance with a safety threshold to detect objects of interest along a route and classify each detected object of interest. When the safety threshold is not met, the system can transmit a teleassistance inquiry using LIDAR data to a backend computing system. When a certainty threshold is not met for an object of interest, the system can transmit a different teleassistance inquiry using image data to the backend computing system.
Claims20
A system comprising:
- one or more processors;
- and
- a memory storing instructions that, when executed by the one or more processors, cause the system to:
- analyze a live sensor view of a self-driving vehicle (SDV) in accordance with a safety threshold to (i) detect objects of interest along a route, and (ii) classify each respective object of the detected objects of interest;
- determine that the safety threshold is not met;
- in response to determining that the safety threshold is not met, transmit a first teleassistance inquiry to a backend computing system, the first teleassistance inquiry comprising LIDAR data;
- determine that a classification of one or more of the detected objects of interest does not satisfy a certainty threshold;
- in response to determining that the classification of the one or more of the detected objects of interest does not satisfy the certainty threshold, transmit a second teleassistance inquiry to the backend computing system, the second teleassistance inquiry comprising image data that includes the one or more detected objects of interest;
- receive a resolution response from the backend computing system;
- and
- provide a control system of the SDV with data corresponding to the resolution response to enable the SDV to proceed in accordance with the resolution response.
A non-transitory computer readable medium storing instructions that, when executed by one or more processors, cause the one or more processors to:
- analyze a live sensor view of a self-driving vehicle (SDV) in accordance with a safety threshold to (i) detect objects of interest along a route, and (ii) classify each respective object of the detected objects of interest;
- determine that the safety threshold is not met;
- in response to determining that the safety threshold is not met, transmit a first teleassistance inquiry to a backend computing system, the first teleassistance inquiry comprising LIDAR data;
- determine that a classification of one or more of the detected objects of interest does not satisfy a certainty threshold;
- in response to determining that the classification of the one or more of the detected objects of interest does not satisfy the certainty threshold, transmit a second teleassistance inquiry to the backend computing system, the second teleassistance inquiry comprising image data that includes the one or more detected objects of interest;
- receive a resolution response from the backend computing system;
- and
- provide a control system of the SDV with data corresponding to the resolution response to enable the SDV to proceed in accordance with the resolution response.
A computer-implemented method performed by one or more processors and comprising:
- analyzing a live sensor view of a self-driving vehicle (SDV) in accordance with a safety threshold to (i) detect objects of interest along a route, and (ii) classify each respective object of the detected objects of interest;
- determining that the safety threshold is not met;
- in response to determining that the safety threshold is not met, transmitting a first teleassistance inquiry to a backend computing system, the first teleassistance inquiry comprising LIDAR data;
- determining that a classification of one or more of the detected objects of interest does not satisfy a certainty threshold;
- in response to determining that the classification of the one or more of the detected objects of interest does not satisfy the certainty threshold, transmitting a second teleassistance inquiry to the backend computing system, the second teleassistance inquiry comprising image data that includes the one or more detected objects of interest;
- receiving a resolution response from the backend computing system;
- and
- providing a control system of the SDV with data corresponding to the resolution response to enable the SDV to proceed in accordance with the resolution response.
Dependencies are inferred from the claim text.