System and method for a unified architecture multi-task deep learning machine for object recognition
US-2017344808-A1 · Nov 30, 2017 · US
US12353213B2 · US · B2
| Field | Value |
|---|---|
| Publication number | US-12353213-B2 |
| Application number | US-202418432887-A |
| Country | US |
| Kind code | B2 |
| Filing date | Feb 5, 2024 |
| Priority date | Feb 2, 2018 |
| Publication date | Jul 8, 2025 |
| Grant date | Jul 8, 2025 |
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.
In various examples, a current claimed set of points representative of a volume in an environment occupied by a vehicle at a time may be determined. A vehicle-occupied trajectory and at least one object-occupied trajectory may be generated at the time. An intersection between the vehicle-occupied trajectory and an object-occupied trajectory may be determined based at least in part on comparing the vehicle-occupied trajectory to the object-occupied trajectory. Based on the intersection, the vehicle may then execute the first safety procedure or an alternative procedure that, when implemented by the vehicle when the object implements the second safety procedure, is determined to have a lesser likelihood of incurring a collision between the vehicle and the object than the first safety procedure.
Opening claim text (preview).
What is claimed is: 1. A method comprising: determining, based at least on a first safety procedure associated with a vehicle, a first trajectory of the vehicle; determining, based at least on one or more second safety procedures associated with one or more objects, one or more second trajectories associated with the one or more objects; and causing, based at least on the first trajectory and the one or more second trajectories, the vehicle to navigate along a route. 2. The method of claim 1 , further comprising: determining, based at least on the first trajectory and the one or more second trajectories, a likelihood of collision between the vehicle and the one or more objects, wherein the causing the vehicle to navigate is based at least on the likelihood of collision. 3. The method of claim 1 , further comprising: determining, based at least on first sensor data generated using one or more sensors, a first current trajectory associated with the vehicle that is different than the first trajectory; and determining, based at least on second sensor data generated using the one or more sensors, one or more second current trajectories associated with the one or more objects that are different than the one or more second trajectories. 4. The method of claim 3 , wherein: the determining the first trajectory is based at least on implementing the first safety procedure at a time along with the first current trajectory; and the determining the one or more second trajectories is based at least on implementing the one or more second safety procedures at a time along the one or more second current trajectories. 5. The method of claim 1 , wherein: the first safety procedure is associated with at least the first trajectory that the vehicle may perform to avoid a collision with the one or more objects; and the one or more second safety procedures are associated with at least the one or more second trajectories that the one or more objects may perform to avoid the collision. 6. The method of claim 1 , wherein the causing the vehicle to navigate comprises causing the vehicle to navigate along a current trajectory based at least on the first trajectory and the one or more second trajectories indicating that there is no likelihood of collision between the machine-vehicle and the one or more objects. 7. The method of claim 1 , wherein the causing the vehicle to navigate comprises: determining, based at least the first trajectory and the one or more second trajectories, one or more constraints associated with reducing a likelihood of collision between the vehicle and the one or more objects; determining a third trajectory based at least on the one or more constraints, the third trajectory including the route; and causing the vehicle to navigate along the third trajectory. 8. The method of claim 1 , further comprising: determining, based at least on the first trajectory, one or more first points within an environment that the vehicle may occupy; and determining, based at least on the one or more second trajectories, one or more second points within the environment that the one or more objects may occupy, wherein the causing the vehicle to navigate is based at least on the one or more first points and the one or more second points. 9. A system comprising: one or more processors to: determine one or more first points within an environment that a vehicle is estimated to occupy if implementing a first safety procedure at a time; determine one or more second points within the environment that one or more objects are estimated to occupy if implementing one or more second safety procedures at the time; and cause, based at least on the one or more first points and the one or more second points, the vehicle to navigate along a route. 10. The system of claim 9 , wherein the one or more processors are further to: determine, based at least on the one or more first points and the one or more second points, a likelihood of collision between the vehicle and the one or more objects, wherein the vehicle is caused to navigate based at least on the likelihood of collision. 11. The system of claim 10 , wherein the system is comprised in at least one of: a control system for an autonomous or semi-autonomous vehicle; a perception system for an autonomous or semi-autonomous vehicle; a system for performing simulation operations; a system for performing deep learning operations; a system on chip (SoC); a system including a programmable vision accelerator (PVA); a system including a vison processing unit; a system implemented using an edge device; a system implemented using a robot; a system incorporating one or more virtual machines (VMs); a system implemented at least partially in a data center; or a system implemented at least partially using cloud computing resources. 12. The system of claim 9 , wherein the one or more processors are further to: determine an amount of overlap associated with the one or more first points and the one or more second points, wherein the vehicle is caused to navigate based at least on the amount of overlap. 13. The system of claim 9 , wherein the one or more processors are further to: determine, based at least on first sensor data generated using one or more sensors, a first current trajectory associated with the vehicle; and determine, based at least on second sensor data generated using the one or more sensors, one or more second current trajectories associated with the one or more objects. 14. The system of claim 13 , wherein: the determination of the one or more first points is based at least on implementing the first safety procedure at the time along with the first current trajectory; and the determination of the one or more second points is based at least on implementing the one or more second safety procedures at the time along the one or more second current trajectories. 15. The system of claim 9 , wherein: the determination of the one or more first points comprises determining, based at least on implementing the first safety procedure at the time, a first area of the environment that may be occupied by the vehicle, the first area including the one or more first points; and the determination of the one or more second points comprises determining, based at least on implementing the one or more second safety procedures at the time, a second area of the environment that may be occupied by the one or more objects, the second area including the one or more second points. 16. The system of claim 9 , wherein: the first safety procedure is associated with one or more first trajectories that the vehicle may perform to avoid a collision with the one or more objects; and the one or more second safety procedures are associated with one or more second trajectories that the one or more objects may perform to avoid the collision. 17. The system of claim 9 , wherein the vehicle is caused to navigate, at least, by: determining, based at least the one or more first points and the one or more second points, one or more constraints associated with reducing a likelihood of collision between the vehicle and the one or more objects; determining a trajectory based at least on the one or more constraints, the route including the trajectory; and causing the vehicle to navigate along the trajectory. 18. A method comprising: causing a vehicle to navigate based at least on a first trajectory associated with the vehicle and one or more second trajectories associated with one or more objects, wherein the first
Spatial relation or speed relative to objects · CPC title
specially adapted for safety · CPC title
Cycles · CPC title
Pedestrians · CPC title
using signals provided by artificial sources external to the vehicle, e.g. navigation beacons · CPC title
Related publications grouped by family.
Answers are generated from the same data shown on this page.