In-path object detection for autonomous systems and applications
In various examples, in-path object detection for autonomous and semi-autonomous systems and applications is described herein. For instance, systems and methods may use sensor data, such as inertial measurement sensor data, to generate or determine a lane that is associated with a vehicle. In some examples, the lane is generated or determined by determining a curvature of a path that the vehicle is navigating and then adding distance boundaries to both sides of the path. The systems and methods may then use sensor data, such as RADAR data and/or LiDAR data, to determine one or more locations of one or more objects with respect to the vehicle. Using the geometry of the lane and the location(s) of the object(s), the systems and methods may then determine whether the object(s) is located along the path of the vehicle.
1 . A method comprising:
determining, based at least on first sensor data obtained using a machine, a wheel angle associated with the machine;
determining, based at least on the wheel angle, a curvature associated with a path of the machine;
determining, based at least on the curvature, a lane geometry associated with a lane of the machine that corresponds to the path of the machine, the lane geometry being defined using at least a first boundary that is spaced a first distance with respect to the path and a second boundary that is spaced a second distance with respect to the path;
determining, based at least on the first boundary, a third distance between a current location of the machine and a point that is located farther along the path than the current location of the machine;
determining, based at least on second sensor data obtained using the machine, a location associated with an object;
determining, based at least on the third distance and the location associated with the object, that the object is located along the path of the machine; and
causing, based at least on the object being located along the path of the machine, the machine to navigate along at least a portion of the path.
2 . The method of claim 1 , wherein boundaries are instantiated to represent the lane geometry based at least on the curvature, the boundaries being instantiated at least, by:
instantiating the first boundary at the first distance to a first side of the lane according to the curvature; and
instantiating the second boundary at the second distance to a second side of the lane according to the curvature.
3 . The method of claim 1 , further comprising:
determining, based at least on the location associated with the object, a fourth distance to the object; and
determining that the fourth distance is less than the third distance,
wherein the determining that the object is located along the path of the machine is based at least on the fourth distance being less than the third distance.
4 . The method of claim 1 , further comprising:
determining, based at least on the third distance and the location associated with the object, a lateral distance between the object and the path,
wherein the determining that the object is located along the path of the machine is based at least on the lateral distance.
5 . The method of claim 4 , further comprising:
determining that the lateral distance is less than a threshold distance,
wherein the determining that the object is located along the path of the machine is based at least on the lateral distance being less than the threshold distance.
6 . The method of claim 4 , further comprising:
determining, based at least on the third distance, an angle associated with the path,
wherein the determining the lateral distance is further based at least on the angle associated with the path.
7 . The method of claim 6 , further comprising:
determining, based at least on the location associated with the object, a fourth distance to the object and a second angle associated with the object,
wherein the determining the lateral distance is further based at least on the fourth distance to the object and the second angle associated with the object.
8 . The method of claim 1 , further comprising:
determining a wheelbase associated with the machine; and
determining, based at least on the wheel angle, a turning radius associated with the machine,
wherein the determining the curvature associated with the path of the machine comprises determining, based at least on the wheelbase and the turning radius, the curvature associated with the path of the machine.
9 . A system comprising:
one or more processors configured to:
determine, based at least on first sensor data obtained using a machine, a yaw rate associated with the machine;
determine, based at least on the yaw rate, a curvature associated with a path of the machine;
determine, based at least on the curvature, a lane geometry associated with a lane of the machine that corresponds to the path, the lane geometry being defined using at least a first boundary that is spaced a first distance with respect to the path and a second boundary that is spaced a second distance with respect to the path;
determine, based at least on the first boundary, a third distance between a current location of the machine on the path and a point that is located farther along the path than the current location of the machine;
determine, based at least on second sensor data obtained using the machine, a location associated with an object;
determine, based at least on the third distance and the location associated with the object, whether the object is located along the path of the machine; and
cause, based at least on whether the object is located along the path of the machine, the machine to navigate along at least a portion of the path.
10 . The system of claim 9 , wherein the one or more processors are further configured to:
determine a fourth distance from the current location of the machine to the location associated with the object,
wherein the determination of whether the object is located along the path of the machine is based at least on the third distance and the fourth distance.
11 . The system of claim 10 , wherein the one or more processors are further configured to:
determine whether the fourth distance is less than the third distance,
wherein the determination of whether the object is located along the path of the machine is based at least on whether the fourth distance is less than the third distance.
12 . The system of claim 9 , wherein the one or more processors are further configured to:
determine, based at least on the third distance and the location associated with the object, a lateral distance between the object and the path,
wherein the determination of whether the object is located along the path of the machine is based at least on the lateral distance.
13 . The system of claim 12 , wherein the determination of whether the object is located along the path of the machine comprises:
determining that the lateral distance is less than a threshold distance; and
determining, based at least on the lateral distance being less than the threshold distance, that the object is located along the path of the machine.
14 . The system of claim 12 , wherein the determination of whether the object is located along the path of the machine comprises:
determining that the lateral distance is greater than a threshold distance; and
determining, based at least on the lateral distance being greater than the threshold distance, that the object is not located along the path of the machine.
15 . The system of claim 9 , wherein the one or more processors are further configured to:
determine a wheelbase associated with the machine; and
determine, based at least on the yaw rate, a turning radius associated with the machine,
wherein the determination of the curvature associated with the path of the machine comprises determining, based at least on the wheelbase and the turning radius, the curvature associated with the path of the machine.
16 . The system of claim 9 , wherein the system is comprised in at least one of:
a control system for an autonomous or semi-autonomous machine;
a perception system for an autonomous or semi-autonomous machine;
a system for performing simulation operations;
a system for performing digital twin operations;
a system for performing light transport simulation;
a system for performing collaborative content creation for 3D assets;
a system for performing deep learning operations;
a system implemented using an edge device;
a system implemented using a robot;
a system for performing conversational AI operations;
a system implementing one or more large language models (LLMs);
a system for generating synthetic data;
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.
17 . One or more processors comprising processing circuitry to:
determine, based at least on first sensor data obtained using a machine, a wheel angle associated with the machine;
determine, based at least on the wheel angle, a curvature associated with a path of the machine;
determine, based at least on the curvature, a lane geometry that corresponds to the path and is defined using boundaries that are spaced one or more first distances with respect to the path;
determine, based at least on one of the boundaries, a second distance between a current location of the machine and a point located farther along the path than the current location of the machine;
determine, based at least on second sensor data obtained using the machine, a location associated with an object;
determine, based at least on the second distance and the location associated with the object, whether the object is located along the path; and
cause, based at least on whether the object is located along the path, the machine to navigate along at least a portion of the path.
18 . The one or more processors of claim 17 , wherein the one or more processors are comprised in at least one of:
a control system for an autonomous or semi-autonomous machine;
a perception system for an autonomous or semi-autonomous machine;
a system for performing simulation operations;
a system for performing digital twin operations;
a system for performing light transport simulation;
a system for performing collaborative content creation for 3D assets;
a system for performing deep learning operations;
a system implemented using an edge device;
a system implemented using a robot;
a system for performing conversational AI operations;
a system implementing one or more large language models (LLMs);
a system for generating synthetic data;
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.
19 . The system of claim 9 , wherein the third distance between the current location of the machine and the point that is located farther along the path is associated with a maximum line of sight along the path for the machine that is caused by the first boundary.
20 . The one or more processors of claim 17 , wherein the processing circuitry is further to:
determine, based at least on the second distance and the location associated with the object, a lateral distance between the object and the path,
wherein the determination of whether the object is located along the path is based at least on the lateral distance.