Autonomous vehicle advanced sensing and response

Patent metadata

Field	Value
Publication number	US-11810405-B2
Application number	US-202117539083-A
Country	US
Kind code	B2
Filing date	Nov 30, 2021
Priority date	Apr 17, 2017
Publication date	Nov 7, 2023
Grant date	Nov 7, 2023

Abstract

An autonomous vehicle is provided that includes one or more processors configured to provide a local compute manager to manage execution of compute workloads associated with the autonomous vehicle. The local compute manager can perform various compute operations, including receiving offload of compute operations from to other compute nodes and offloading compute operations to other compute notes, where the other compute nodes can be other autonomous vehicles. The local compute manager can also facilitate autonomous navigation functionality.

First claim

What is claimed is:

1. An autonomous vehicle comprising:
one or more processors to provide a local compute manager to manage execution of compute workloads associated with the autonomous vehicle, the local compute manager configured to:
establish an encrypted communication link with an autonomous vehicle network via a wireless communication interface;
receive, via the wireless communication interface, a search descriptor associated with a search operation to be performed based on real-time sensory data; and
spawn a work item to perform a search operation on based on processed sensor data.

2. The autonomous vehicle as in claim 1 , wherein the local compute manager is to receive the search descriptor from a vehicle-to-infrastructure node connected with the autonomous vehicle network.

3. The autonomous vehicle as in claim 1 , wherein the local compute manager is to receive the search descriptor from a first remote autonomous vehicle connected with the autonomous vehicle network.

4. The autonomous vehicle as in claim 1 , wherein the local compute manager is to:
discover a remote autonomous vehicle connected with the autonomous vehicle network; and
transmit the search descriptor to the remote autonomous vehicle, wherein the local compute manager is to:
establish a trust relationship with a remote compute manager of the remote autonomous vehicle before transmission of the search descriptor to the remote autonomous vehicle;
determine a location for the remote autonomous vehicle; and
transmit the search descriptor to the remote autonomous vehicle based on the location of the remote autonomous vehicle.

5. The autonomous vehicle as in claim 1 , wherein the search descriptor includes search details for the search operation.

6. The autonomous vehicle as in claim 5 , wherein the search details include a search area for the search operation.

7. The autonomous vehicle as in claim 5 , wherein the search details include a vehicle description for the search operation.

8. The autonomous vehicle as in claim 1 , wherein the work item to perform the search operation is a background compute operation to enable passive analysis of processed sensor data.

9. An autonomous vehicle comprising:
one or more processors to provide a local compute manager to manage execution of compute workloads associated with the autonomous vehicle, the local compute manager configured to:
establish a map of occupied positions within the autonomous vehicle based on data received from a first set of sensors for determining an internal position of one or more occupants of the autonomous vehicle;
detect an impending collision during autonomous navigation based on a second set of sensors for facilitating navigation of the autonomous vehicle;
determining whether the impending collision is unavoidable; and
in response to a determination that the impending collision is unavoidable, configure the autonomous vehicle to mitigate harm caused by the impending collision based on the map of occupied positions within the autonomous vehicle.

10. The autonomous vehicle as in claim 9 , wherein to configure the autonomous vehicle to mitigate the impending collision includes to maneuver the autonomous vehicle to reduce collision damage to occupied positions within the autonomous vehicle.

11. The autonomous vehicle as in claim 9 , wherein to configure the autonomous vehicle to mitigate the impending collision includes to pre-inflate an internal airbag of the autonomous vehicle.

12. The autonomous vehicle as in claim 9 , wherein to configure the autonomous vehicle to mitigate the impending collision includes to pre-inflate an external airbag of the autonomous vehicle.

13. The autonomous vehicle as in claim 9 , wherein to configure the autonomous vehicle to mitigate the impending collision includes to activate a seat belt pre-tensioner of the autonomous vehicle.

14. The autonomous vehicle as in claim 9 , wherein the local compute manager is configured to:
detect movement within the autonomous vehicle; and
update the map of occupied positions within the autonomous vehicle.

15. The autonomous vehicle as in claim 9 , wherein the local compute manager is configured to:
determine a post-collision mobility state for the autonomous vehicle; and
in response to determination that the autonomous vehicle is mobile, cause the autonomous vehicle to autonomously move to a location determined based on the second set of sensors.

16. An autonomous vehicle comprising:
one or more processors to provide a local compute manager to manage execution of compute workloads associated with the autonomous vehicle, the local compute manager configured to detect a collision associated with the autonomous vehicle based on a first set of sensors for health characteristics of occupants of the autonomous vehicle or a second set of sensors for vehicle characteristics of the autonomous vehicle and,
in response to detection of the collision, infer a post-collision response based on sensor data gathered via the first set of sensors or the second set of sensors.

17. The autonomous vehicle as in claim 16 , wherein the second set of sensors includes a collision detection sensor or vehicle damage sensor.

18. The autonomous vehicle as in claim 16 , wherein the second set of sensors includes a camera, radar sensor, or lidar sensor.

19. The autonomous vehicle as in claim 16 , wherein to infer the post-collision response based on sensor data includes to provide the sensor data to a machine learning model executed by the local compute manager and receive an inferred post-collision response from the machine learning model.

20. The autonomous vehicle as in claim 16 , wherein the post-collision response includes to:
compile an incident report based on the sensor data;
determine an injury severity for occupants of the autonomous vehicle; and
determine a damage severity for the autonomous vehicle.

21. The autonomous vehicle as in claim 20 , wherein the post-collision response additionally includes to, in response to determination of severe damage or sever injury, transmit the incident report to emergency services associated with a determined location of the autonomous vehicle.

22. The autonomous vehicle as in claim 16 , wherein the post-collision response additionally includes to:
determine a post-collision mobility state for the autonomous vehicle;
in response to determination that the autonomous vehicle is mobile, cause the autonomous vehicle to autonomously move to a location determined based on the second set of sensors; and
in response to determination that the autonomous vehicle is immobile, engage a post-collision safety feature of the autonomous vehicle.

23. The autonomous vehicle as in claim 22 , wherein to engage the post-collision safety feature includes to disable a drive motor of the autonomous vehicle.

24. The autonomous vehicle as in claim 22 , wherein to engage the post-collision safety feature includes to unlock a door of the autonomous vehicle.

25. The autonomous vehicle as in claim 22 , wherein to engage the post-collision safety feature includes to enable a hazard or warning light of the autonomous vehicle.

Assignees

• Intel Corp

Inventors

• Lakshamanan Barath
• Hurd Linda L
• Ashbaugh Ben J
• Ould-Ahmed-Vall Elmoustapha
• Ma Liwei
• Jin Jingyi
• Gottschlich Justin E
• Sakthivel Chandrasekaran
• Strickland Michael S
• Lewis Brian T
• Kuper Lindsey
• Koker Altug
• Appu Abhishek R
• Surti Prasoonkumar
• Ray Joydeep
• Vembu Balaji
• Turek Javier S
• Farooqui Naila

Classifications

• G06N3/0464

  Convolutional networks [CNN, ConvNet] · CPC title

• G06N3/0895

  Weakly supervised learning, e.g. semi-supervised or self-supervised learning · CPC title

• G06N3/09

  Supervised learning · CPC title

• G06N3/098

  Distributed learning, e.g. federated learning · CPC title

• G06N3/0442

  characterised by memory or gating, e.g. long short-term memory [LSTM] or gated recurrent units [GRU] · CPC title