Autonomous vehicle advanced sensing and response

Patent metadata

Field	Value
Publication number	US-11217040-B2
Application number	US-201916383849-A
Country	US
Kind code	B2
Filing date	Apr 15, 2019
Priority date	Apr 17, 2017
Publication date	Jan 4, 2022
Grant date	Jan 4, 2022

Abstract

One embodiment provides for a computing device within an autonomous vehicle, the compute device comprising a wireless network device to enable a wireless data connection with an autonomous vehicle network, a set of multiple processors including a general-purpose processor and a general-purpose graphics processor, the set of multiple processors to execute a compute manager to manage execution of compute workloads associated with the autonomous vehicle, the compute workload associated with autonomous operations of the autonomous vehicle, and offload logic configured to execute on the set of multiple processors, the offload logic to determine to offload one or more of the compute workloads to one or more autonomous vehicles within range of the wireless network device.

First claim

The invention claimed is:

1. An autonomous vehicle comprising:
a wireless network device to enable a wireless data connection with an autonomous vehicle network; and
a set of multiple processors including a general-purpose processor, a general-purpose graphics processor, and a vision processor, the set of multiple processors to provide a local compute manager to manage execution of compute workloads associated with the autonomous vehicle, the vision processor to accelerate processing of real-time sensory data, the local compute manager to establish an encrypted communication link with a remote compute manager of trusted remote autonomous vehicle via the autonomous vehicle network, wherein the local compute manager is to transmit, via the autonomous vehicle network, an inference determination associated with an event detected via the real-time sensory data.

2. The autonomous vehicle as in claim 1 , wherein the local compute manager includes a trust module to store credentials to establish authenticity of the local compute manager.

3. The autonomous vehicle as in claim 2 , wherein credentials to establish authenticity of the local compute manager include one or more identity tokens and identity certificates.

4. The autonomous vehicle as in claim 2 , wherein local compute manager additionally includes a key to enable encryption of data to be transmitted via the autonomous vehicle network and a certificate that includes data to enable a signature to be applied to the data to be transmitted via the autonomous vehicle network.

5. The autonomous vehicle as in claim 2 , wherein local compute manager includes a remote discovery unit and the local compute manager is to:
discover the remote autonomous vehicle via the remote discovery unit;
determine a location for the remote autonomous vehicle; and
establish a trust relationship with the remote autonomous vehicle via the trust module.

6. The autonomous vehicle as in claim 5 , wherein the event detected via the real-time sensory data includes detection of an obstacle along a path that is common to the autonomous vehicle and the remote autonomous vehicle.

7. The autonomous vehicle as in claim 6 , wherein the event is detected during autonomous operation of the autonomous vehicle.

8. The autonomous vehicle as in claim 1 , wherein to transmit the inference determination associated with an event includes to transmit an inference data handler to the remote compute manager of the trusted remote autonomous vehicle.

9. The autonomous vehicle as in claim 8 , wherein the inference data handler is to facilitate translation of inference data associated with the inference determination from a format associated with the local compute manager to a format associated with the remote compute manager.

10. A method on a computing device within an autonomous vehicle, the method comprising:
establishing a wireless data connection with an autonomous vehicle network;
discovering a remote autonomous vehicle via the autonomous vehicle network;
determining a location for the remote autonomous vehicle;
establishing a trust relationship with the remote autonomous vehicle via credentials exchanged with the remote autonomous vehicle via the autonomous vehicle network; and
transmitting, to the remote autonomous vehicle, an inference determination associated with an event detected via real-time sensory data processed via a vision processor of the autonomous vehicle.

11. The method as in claim 10 , wherein the credentials exchanged with the remote autonomous vehicle include one or more identity tokens and identity certificates associated with the autonomous vehicle and the remote autonomous vehicle.

12. The method as in claim 10 , wherein the event detected via the real-time sensory data includes detection of an obstacle along a path that is common to the autonomous vehicle and the remote autonomous vehicle.

13. The method as in claim 12 , wherein the event is detected during autonomous operation of the autonomous vehicle.

14. The method as in claim 13 , wherein to transmit the inference determination associated with an event includes to transmit an inference data handler to the remote compute manager of the remote autonomous vehicle, wherein the inference data handler is to facilitate translation of the inference data associated with the inference determination from a format associated with a local compute manager of the autonomous vehicle to a format associated with a remote compute manager of the remote autonomous vehicle.

15. A computing device within an autonomous vehicle, the computing device comprising:
a wireless network device to enable a wireless data connection with an autonomous vehicle network;
a memory device coupled with the wireless network device; and
a set of multiple processors including a general-purpose processor, a general-purpose graphics processor, and a vision processor, the set of multiple processors to provide a local compute manager to manage execution of compute workloads associated with the autonomous vehicle, the vision processor to accelerate processing of real-time sensory data, the local compute manager to establish an encrypted communication link with a remote compute manager of trusted remote autonomous vehicle via the autonomous vehicle network, wherein the local compute manager is to transmit, via the autonomous vehicle network, an inference determination associated with an event detected via the real-time sensory data.

16. The computing device as in claim 15 , wherein local compute manager includes a remote discovery unit and the local compute manager is to:
discover the remote autonomous vehicle via the remote discovery unit;
determine a location for the remote autonomous vehicle; and
establish a trust relationship with the remote autonomous vehicle via a trust module included within the local compute manager.

17. The computing device as in claim 16 , wherein the event detected via the real-time sensory data includes detection of an obstacle along a path that is common to the autonomous vehicle and the remote autonomous vehicle.

18. The computing device as in claim 17 , wherein the event is detected during autonomous operation of the autonomous vehicle.

19. The computing device as in claim 15 , wherein to transmit the inference determination associated with an event includes to transmit an inference data handler to the remote compute manager of the trusted remote autonomous vehicle.

20. The computing device as in claim 19 , wherein the inference data handler is to facilitate translation of the inference data associated with the inference determination from a format associated with the local compute manager to a format associated with the remote compute manager.

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

• G06N3/045

  Combinations of networks · CPC title

• G06N3/044

  Recurrent networks, e.g. Hopfield networks · CPC title

• 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