Virtual environment scenarios and observers for autonomous machine applications
US-2021294944-A1 · Sep 23, 2021 · US
US11814083B2 · US · B2
| Field | Value |
|---|---|
| Publication number | US-11814083-B2 |
| Application number | US-202016893630-A |
| Country | US |
| Kind code | B2 |
| Filing date | Jun 5, 2020 |
| Priority date | Mar 31, 2020 |
| Publication date | Nov 14, 2023 |
| Grant date | Nov 14, 2023 |
A practical reading order for non-experts. Skip the full description unless you need deep technical detail.
What the patent document calls the invention.
A short plain-language summary of the technical disclosure.
Who owns or filed the patent and who is credited as inventor.
Filing, priority, publication, and grant dates set the timeline.
The legal scope of protection — read this for what is actually claimed.
Technology tags used to group this patent with similar filings.
Prior art links and similar publications in this corpus.
Official abstract text for this publication.
Systems and methods are directed to an autonomy computing system for an autonomous vehicle. The autonomy computing system can include functional circuits associated with a first compute function of the autonomous vehicle. Each of the functional circuits can be configured to obtain sensor data that describes one or more aspects of an environment external to the autonomous vehicle at a current time. Each of the functional circuits can be configured to generate, over a time period and based on the sensor data, a respective output according to the specified order. The autonomy computing system can include monitoring circuits configured to evaluate an output consistency of the respective outputs, and in response to detecting an output inconsistency between two or more of the respective outputs, generate data indicative of a detected anomaly associated with the first autonomous compute function.
Opening claim text (preview).
What is claimed is: 1. An autonomy computing system for an autonomous vehicle, comprising: a plurality of functional circuits associated with a first autonomous compute function of the autonomous vehicle, each of the plurality of functional circuits comprising at least one processor that is configured to, according to a specified order: obtain sensor data associated with a sensor system of the autonomous vehicle, the sensor data describing one or more aspects of an environment external to the autonomous vehicle at a current time; and generate, independent of others of the plurality of functional circuits, over a time period and based at least in part on the sensor data, a respective output associated with the first autonomous compute function according to the specified order, the respective output comprising a stochastic output; one or more monitoring circuits configured to: evaluate, according to the specified order, an output consistency of the respective outputs; and in response to detecting an output inconsistency between two or more of the respective outputs, generate data indicative of a detected anomaly associated with the first autonomous compute function, wherein the data indicative of the detected anomaly comprises an assured output that is assured to a specified functional safety standard; and a vehicle control signal generator configured to generate one or more vehicle control signals for controlling the autonomous vehicle based at least in part on the respective outputs. 2. The autonomy computing system of claim 1 , wherein each of the plurality of functional circuits is configured to use a respective one of a plurality of neural networks associated with the first autonomous compute function to generate, over the time period and based at least in part on the sensor data, the respective output. 3. The autonomy computing system of claim 1 , wherein the specified order specifies an order for each of the plurality of functional circuits and a time delay between each of the plurality of functional circuits, the time delay being less than the time period. 4. The autonomy computing system of claim 1 , wherein at least one of the functional circuits of the plurality of functional circuits is configured to determine, based on the output consistency between each of the respective outputs, an optimal output. 5. The autonomy computing system of claim 4 , wherein: the autonomy computing system is part of a vehicle computing system configured to generate the one or more vehicle control signals for the autonomous vehicle based at least in part on the optimal output. 6. The autonomy computing system of claim 5 , wherein the autonomy computing system is configured to determine whether the output consistency between each of the respective outputs satisfies a consistency threshold, and in response to the output consistency failing to satisfy the consistency threshold, generate the one or more vehicle control signals to safely stop the autonomous vehicle. 7. The autonomy computing system of claim 4 , wherein the plurality of functional circuits comprises: first functional circuitry; and second functional circuitry configured to obtain the sensor data during at least a portion of the time period during which the first functional circuitry generates the respective output. 8. The autonomy computing system of claim 7 , further comprising: third functional circuitry configured to obtain the sensor data during at least a portion of the time period during which the second functional circuitry generates the respective output; wherein the sensor data obtained by the third functional circuitry describes one or more aspects of the environment external to the autonomous vehicle at a time different than the sensor data obtained by the second functional circuitry. 9. The autonomy computing system of claim 1 , wherein each of the functional circuits comprises at least one of: one or more processor cores; or one or more computing devices. 10. The autonomy computing system of claim 1 , wherein the one or more monitoring circuits comprises virtualized processing circuitry. 11. The autonomy computing system of claim 1 , wherein: each of the functional circuits includes one or more non-assured hardware processing circuits; and the one or more monitoring circuits includes one or more assured processing circuits. 12. The autonomy computing system of claim 1 , wherein: each of the respective outputs comprises a trajectory and a world state, the world state describing the environment external to the autonomous vehicle; and the autonomy computing system is configured to generate motion planning data including the trajectory based at least in part on the environment as described by the world state. 13. The autonomy computing system of claim 1 , wherein each of the respective outputs comprises a respective motion plan for the autonomous vehicle. 14. The autonomy computing system of claim 1 , wherein each of the respective outputs comprises a trajectory associated with a first object. 15. A computer-implemented method for verifying autonomous vehicle compute processing, comprising: obtaining, by a plurality of functional circuits of an autonomy computing system each comprising at least one processor, sensor data associated with a sensor system of the autonomous vehicle, the sensor data describing one or more aspects of an environment external to the autonomous vehicle at a current time, each of the plurality of functional circuits respectively independently associated with a first autonomous compute function of the autonomy computing system; generating, by each of the plurality of functional circuits and according to a specified order, a plurality of stochastic outputs, each of the plurality of stochastic outputs generated over a time period independently by each of the plurality of functional circuits; evaluating, by one or more monitoring circuits of the autonomy computing system and according to the specified order, an output consistency of the plurality of stochastic outputs; and in response to detecting an output inconsistency between two or more of the respective outputs, generating, by the autonomy computing system, data indicative of a detected anomaly associated with the first autonomous compute function, wherein the data indicative of the detected anomaly comprises an assured output that is assured to a specified functional safety standard. 16. The computer-implemented method of claim 15 , wherein each of the plurality of functional circuits is configured to use a respective one of a plurality of neural networks associated with the first autonomous compute function to generate, over the time period and based at least in part on the sensor data, the plurality of stochastic outputs. 17. The computer-implemented method of claim 15 , wherein the specified order specifies an order for each of the plurality of functional circuits and a time delay between each of the plurality of functional circuits, the time delay being less than the time period. 18. An autonomous vehicle, comprising: a sensor system configured to generate sensor data associated with an environment external to the autonomous vehicle; an autonomy computing system comprising: a plurality of functional circuits associated with a first autonomous compute function of the autonomous vehicle, each of the plurality of functional circuits comprising at least one processor that is configured to, according to a specified order: obtain sensor data associated with the sensor system of the autonomous vehic
specially adapted for specific operations · CPC title
Monitoring the functioning of the control system · CPC title
Planning or execution of driving tasks · CPC title
specially adapted for safety · CPC title
using trajectory prediction for other traffic participants · CPC title
Related publications grouped by family.
Answers are generated from the same data shown on this page.