INTERVENTION IN OPERATION OF A VEHICLE HAVING AUTONOMOUS DRIVING CAPABILITIES
Among other things, a determination is made that intervention in an operation of one or more autonomous driving capabilities of a vehicle is appropriate. Based on the determination, a person is enabled to provide information for an intervention. The intervention is caused in the operation of the one or more autonomous driving capabilities of the vehicle.
1 . A vehicle comprising:
one or more computer processors; and
one or more non-transitory storage media storing instructions which, when executed by the one or more computer processors, cause the vehicle to:
determine, using past inputs and past sensor measurements, an estimated state of a hardware component of the vehicle;
receive, using one or more sensors of the vehicle, a sensor measurement of the vehicle;
determine, using the received sensor measurement, an actual state of the hardware component; and
transmit, to a teleoperation server, a request for a teleoperation command in response to a difference between the estimated state of the hardware component and the actual state of the hardware component being above a threshold value.
2 . The vehicle of claim 1 , wherein the sensor measurement comprises at least one of a position of the vehicle, a linear velocity of the vehicle, an angular velocity of the vehicle, a linear acceleration of the vehicle, an angular acceleration of the vehicle, or a heading of the vehicle.
3 . The vehicle of claim 1 , wherein the one or more sensors comprise at least one of a GPS sensor, an inertial measurement unit, a wheel speed sensor, a brake pressure sensor, a braking torque sensor, an engine torque sensor, a wheel torque sensors, a steering wheel angle sensor, or a steering wheel angular rate sensors.
4 . The vehicle of claim 1 , wherein the difference between the estimated state of the hardware component and the actual state of the hardware component represents a brake malfunction.
5 . The vehicle of claim 1 , wherein the difference between the estimated state of the hardware component and the actual state of the hardware component represents a flat tire.
6 . The vehicle of claim 1 , wherein the difference between the estimated state of the hardware component and the actual state of the hardware component represents a blockage of a field of view of a vision sensor of the vehicle.
7 . The vehicle of claim 1 , wherein the instructions, when executed by the one or more computer processors, further cause the vehicle to generate, using the one or more processors, a request for a fallback operation while the vehicle is waiting for the teleoperation command from the teleoperation server.
8 . The vehicle of claim 7 , wherein the instructions, when executed by the one or more computer processors, further cause the vehicle to implement the fallback operation, and wherein the fallback operation comprises driving at a specified velocity.
9 . The vehicle of claim 7 , wherein the fallback operation comprises following a specified trajectory.
10 . The vehicle of claim 7 , wherein the fallback operation comprises invoking a satellite communication system.
11 . The vehicle of claim 7 , wherein the instructions, when executed by the one or more computer processors, further cause the vehicle to transition from performing the fallback operation to performing the teleoperation command.
12 . The vehicle of claim 1 , wherein the teleoperation command comprises a trajectory for the vehicle.
13 . The vehicle of claim 1 , wherein the teleoperation command comprises a position of the vehicle and a heading of the vehicle.
14 . The vehicle of claim 1 , wherein the teleoperation command comprises a speed profile for the vehicle, the speed profile describing a preferred velocity of the vehicle on a trajectory segment.
15 . The vehicle of claim 1 , wherein the instructions, when executed by the one or more computer processors, further cause the vehicle to analyze the difference between the estimated state of the hardware component and the actual state of the hardware component using pattern recognition to evaluate an abnormal pattern in the received sensor measurement.
16 . The vehicle of claim 15 , wherein the instructions, when executed by the one or more computer processors, further cause the vehicle to learn, using a machine learning algorithm, the abnormal pattern.
17 . The vehicle of claim 1 , wherein the teleoperation command comprises:
identifying a safe-to-stop location; and
generating a new trajectory to the safe-to-stop location.
18 . The vehicle of claim 1 , wherein the teleoperation command comprises:
treating a position of the vehicle that is specified in the teleoperation command as prior knowledge; and
using an inference algorithm to update the position of the vehicle.
19 . The vehicle of claim 1 , wherein the teleoperation command comprises concatenating two trajectory segments, the concatenating comprising:
smoothing the two trajectory segments; and
smoothing speed profiles across the two trajectory segments.
20 . The vehicle of claim 1 , wherein the teleoperation command specifies, to the vehicle, one or more un-traversable road segments.