Navigation Based on Liability Constraints

Patent metadata

Field	Value
Publication number	US-2021142421-A1
Application number	US-202017132428-A
Country	US
Kind code	A1
Filing date	Dec 23, 2020
Priority date	Aug 16, 2017
Publication date	May 13, 2021
Grant date	—

Abstract

A method includes operations to obtain a planned driving action for accomplishing a navigational goal of a host vehicle, identify a planned trajectory for the host vehicle, identify, from analysis of sensor data representative of an environment of the host vehicle, movement of an actor in the environment, identify a predicted trajectory of the actor, the planned trajectory for the host vehicle to intersect the predicted trajectory for the actor, determine a navigational constraint for the host vehicle, determine a higher priority of the navigational constraint over at least one other navigational constraint for the host vehicle in the environment, calculate a safety action of the host vehicle to respond to the predicted trajectory of the actor, wherein the safety action reduces intersection of the planned trajectory with the predicted trajectory of the actor; and cause the safety action to be applied in the host vehicle.

First claim

1 - 43 . (canceled)

44 . At least one machine-readable storage medium comprising instructions, which when executed by processor circuitry of a computing device, cause the processor circuitry to perform operations to:
obtain a planned driving action for accomplishing a navigational goal of a host vehicle; identify a planned trajectory for the host vehicle corresponding to the planned driving action; identify, from analysis of sensor data representative of an environment of the host vehicle, movement of an actor in the environment of the host vehicle; identify a predicted trajectory of the actor based on the movement of the actor, the planned trajectory for the host vehicle to intersect the predicted trajectory for the actor; determine a navigational constraint for the host vehicle based on the predicted trajectory of the actor; determine a higher priority of the navigational constraint over at least one other navigational constraint for the host vehicle in the environment; calculate a safety action of the host vehicle to respond to the predicted trajectory of the actor, based on the higher priority of the navigational constraint over the at least one other navigational constraint, wherein the safety action reduces intersection of the planned trajectory with the predicted trajectory of the actor; and cause the safety action to be applied in the host vehicle.

45 . The storage medium of claim 1 , wherein the actor is a pedestrian, or bicyclist, car, truck, or other vehicle.

46 . The storage medium of claim 44 , wherein the safety action is to be applied in the host vehicle when the actor violates a right of way of the host vehicle.

47 . The storage medium of claim 44 , wherein the at least one other navigational constraint relates to at least one other vehicle in the environment.

48 . The storage medium of claim 4 , wherein the higher priority of the navigational constraint is identified as higher than a lower priority of the other navigational constraint relating to the at least one other vehicle in the environment.

49 . The storage medium of claim 44 , wherein the planned driving action includes continuing the planned trajectory for the host vehicle within a roadway, wherein the safety action changes the planned trajectory for the host vehicle within the roadway.

50 . The storage medium of claim 44 , wherein operations to determine the safety action of the host vehicle further determine a braking action of the host vehicle, and wherein operations to cause the safety action to be applied in the host vehicle further cause the braking action to be applied in the host vehicle, to longitudinally change the planned trajectory of the host vehicle.

51 . The storage medium of claim 44 , wherein operations to determine the safety action of the host vehicle further determine a steering action of the host vehicle, and wherein operations to cause the safety action to be applied in the host vehicle further cause the steering action to be applied in the host vehicle, to laterally change the planned trajectory of the host vehicle.

52 . The storage medium of claim 44 , the instructions further to cause the processor circuitry to perform operations to obtain the sensor data from a sensor device of the host vehicle.

53 . The storage medium of claim 52 , wherein the sensor device includes a camera and the sensor data includes at least one image, or the sensor device includes at least one of a LIDAR system or a RADAR system and the sensor data includes data from the at least one of the LIDAR system or the RADAR system.

54 . The storage medium of claim 44 , wherein the sensor data includes data from at least three sensing systems of the host vehicle.

55 . The storage medium of claim 54 , wherein the sensor data from the at least three sensing systems is used to identify movement of the actor in the environment of the host vehicle.

56 . The storage medium of claim 54 , wherein the safety action to be performed in the host vehicle is determined based on fusion of constraints from at least two safety actions.

57 . The storage medium of claim 54 , the instructions further to cause the processor circuitry to:
identify a set of safety constraints, including a first safety constraint identified from sensor data of a first sensor system, a second safety constraint identified from sensor data of a second sensor system, and a third safety constraint identified from sensor data of a third sensor system; wherein the safety action to be performed in the host vehicle satisfies a majority of the set of safety constraints.

58 . The storage medium of claim 57 , wherein the majority is satisfied for safety constraints from two of three sensor systems.

59 . The storage medium of claim 57 , wherein the first, second, and third sensor systems are redundant sensing systems.

60 . The storage medium of claim 59 , wherein the redundant sensing systems use different sensing technologies or overlap in perception of the environment, wherein the different sensing technologies are provided from among camera, RADAR, and LiDAR technologies.

61 . A computing device, comprising:
at least one interface to receive sensor data from a sensor device, the sensor data representative of an environment surrounding a host vehicle; and at least one processor configured to perform operations to:
obtain a planned driving action for accomplishing a navigational goal of a host vehicle;
identify a planned trajectory for the host vehicle corresponding to the planned driving action;
identify, from analysis of sensor data representative of an environment of the host vehicle, movement of an actor in the environment of the host vehicle;
identify a predicted trajectory of the actor based on the movement of the actor, the planned trajectory for the host vehicle to intersect the predicted trajectory for the actor;
determine a navigational constraint for the host vehicle based on the predicted trajectory of the actor;
determine a higher priority of the navigational constraint over at least one other navigational constraint for the host vehicle in the environment;
calculate a safety action of the host vehicle to respond to the predicted trajectory of the actor, based on the higher priority of the navigational constraint over the at least one other navigational constraint, wherein the safety action reduces intersection of the planned trajectory with the predicted trajectory of the actor; and
cause the safety action to be applied in the host vehicle.

62 . The computing device of claim 61 , wherein the actor is a pedestrian, or bicyclist, car, truck, or other vehicle.

63 . The computing device of claim 61 , wherein the safety action is to be applied in the host vehicle when the actor violates a right of way of the host vehicle.

64 . The computing device of claim 61 , wherein the at least one other navigational constraint relates to at least one other vehicle in the environment.

65 . The computing device of claim 64 , wherein the higher priority of the navigational constraint is identified as higher than a lower priority of the other navigational constraint relating to the at least one other vehicle in the environment.

66 . The computing device of claim 61 , wherein the planned driving action includes continuing the planned trajectory for the host vehicle within a roadway, wherein the safety action changes the planned trajectory for the host vehicle within the roadway.

Assignees

• Mobileye Vision Technologies Ltd

Inventors

• Shalev-Shwartz Shai
• Shashua Amnon
• SHAMMAH Shaked

Classifications

• B60W30/09

  Taking automatic action to avoid collision, e.g. braking and steering · CPC title

• B60W60/0027

  using trajectory prediction for other traffic participants · CPC title

• B60W30/0953

  the prediction being responsive to vehicle dynamic parameters · CPC title

• B60W30/0956

  the prediction being responsive to traffic or environmental parameters · CPC title

• B60W2554/4048

  Field of view, e.g. obstructed view or direction of gaze · CPC title