Systems and methods for estimating the risk associated with a vehicular maneuver

Patent metadata

Field	Value
Publication number	US-11724691-B2
Application number	US-201916440546-A
Country	US
Kind code	B2
Filing date	Jun 13, 2019
Priority date	Sep 15, 2018
Publication date	Aug 15, 2023
Grant date	Aug 15, 2023

Abstract

Systems and methods described herein relate to estimating risk associated with a vehicular maneuver. One embodiment acquires a geometric representation of an intersection including a lane in which a vehicle is traveling and at least one other lane; discretizes the at least one other lane into a plurality of segments; determines a trajectory along which the vehicle will travel; estimates a probability density function for whether a road agent external to the vehicle is present in the respective segments; estimates a traffic-conflict probability of a traffic conflict in the respective segments conditioned on whether an external road agent is present; estimates a risk associated with the vehicle following the trajectory by integrating a product of the probability density function and the traffic-conflict probability over the at least one other lane and the plurality of segments; and controls operation of the vehicle based, at least in part, on the estimated risk.

First claim

What is claimed is:

1. A system for estimating risk associated with a vehicular maneuver, the system comprising:
one or more sensors to produce sensor data;
one or more processors; and
a memory communicably coupled to the one or more processors and storing:
a risk estimation module including instructions that when executed by the one or more processors cause the one or more processors to:
acquire a geometric representation of an intersection, the geometric representation including a lane in which a vehicle is traveling and at least one other lane;
discretize the at least one other lane into a plurality of segments;
determine a trajectory along which the vehicle will travel relative to the intersection;
estimate, at each of a plurality of adjacent discrete time steps using an Eulerian model, an updated probability density function for whether a road agent external to the vehicle is present in the respective segments in the plurality of segments based, at least in part, on the sensor data, wherein the Eulerian model partially corrects faulty perception results that are based on the sensor data;
estimate a traffic-conflict probability, as a result of the vehicle traveling along the trajectory, of a traffic conflict occurring in the respective segments in the plurality of segments conditioned on whether an external road agent is present in the respective segments in the plurality of segments; and
estimate a risk associated with the vehicle traveling along the trajectory by integrating a product of the probability density function and the traffic-conflict probability over the at least one other lane and the plurality of segments; and

a control module including instructions that when executed by the one or more processors cause the one or more processors to control operation of the vehicle based, at least in part, on the estimated risk.

2. The system of claim 1 , wherein the instructions included in the control module to control operation of the vehicle based, at least in part, on the estimated risk include instructions to control at least steering, acceleration, and braking of the vehicle in an autonomous driving mode of the vehicle.

3. The system of claim 1 , wherein the instructions included in the control module to control operation of the vehicle based, at least in part, on the estimated risk include instructions to share control of at least one of steering, acceleration, and braking of the vehicle between an advanced driver-assistance system of the vehicle and a human driver.

4. The system of claim 1 , wherein the instructions included in the risk estimation module to estimate the risk include instructions to account for an occlusion with respect to a viewpoint of the vehicle in at least one of the plurality of segments.

5. The system of claim 1 , wherein the instructions included in the risk estimation module to estimate the risk include at least one of instructions to account for failure of an operator of an external road agent to observe the vehicle as the vehicle approaches the intersection along the trajectory and instructions to account for failure, due to environmental conditions, of an external road agent to act on an observation of the vehicle as the vehicle approaches the intersection along the trajectory.

6. The system of claim 1 , wherein the instructions included in the control module to control operation of the vehicle based, at least in part, on the estimated risk include instructions to:
cause the vehicle, upon reaching the intersection, to proceed at a target speed along the trajectory, when the estimated risk does not exceed a predetermined threshold; and
cause the vehicle, before the vehicle has reached the intersection, to reduce its speed relative to the target speed, when the estimated risk exceeds the predetermined threshold.

7. The system of claim 1 , wherein the instructions included in the control module to control operation of the vehicle based, at least in part, on the estimated risk include, to avoid a traffic conflict, instructions to adjust the vehicle's speed along the trajectory after the vehicle has entered the intersection.

8. The system of claim 1 , wherein the intersection is unsignalized and is one of a merge, a four-way intersection, and a roundabout.

9. The system of claim 1 , wherein the estimated risk is an upper bound on an expected number of traffic conflicts.

10. The system of claim 1 , wherein the one or more sensors include at least one of a camera, a Light Detection and Ranging (LIDAR) sensor, a radar sensor, and a sonar sensor.

11. A non-transitory computer-readable medium for estimating risk associated with a vehicular maneuver and storing instructions that when executed by one or more processors cause the one or more processors to:
acquire a geometric representation of an intersection, the geometric representation including a lane in which a vehicle is traveling and at least one other lane;
discretize the at least one other lane into a plurality of segments;
determine a trajectory along which the vehicle will travel relative to the intersection;
estimate, at each of a plurality of adjacent discrete time steps using an Eulerian model, an updated probability density function for whether a road agent external to the vehicle is present in the respective segments in the plurality of segments based, at least in part, on sensor data, wherein the Eulerian model partially corrects faulty perception results that are based on the sensor data;
estimate a traffic-conflict probability, as a result of the vehicle traveling along the trajectory, of a traffic conflict occurring in the respective segments in the plurality of segments conditioned on whether an external road agent is present in the respective segments in the plurality of segments;
estimate a risk associated with the vehicle traveling along the trajectory by integrating a product of the probability density function and the traffic-conflict probability over the at least one other lane and the plurality of segments; and
control operation of the vehicle based, at least in part, on the estimated risk.

12. The non-transitory computer-readable medium of claim 11 , wherein the instructions to control operation of the vehicle based, at least in part, on the estimated risk include instructions to:
cause the vehicle, upon reaching the intersection, to proceed at a target speed along the trajectory, when the estimated risk does not exceed a predetermined threshold; and
cause the vehicle, before the vehicle has reached the intersection, to reduce its speed relative to the target speed, when the estimated risk exceeds the predetermined threshold.

13. The non-transitory computer-readable medium of claim 11 , wherein the instructions to control operation of the vehicle based, at least in part, on the estimated risk include, to avoid a traffic conflict, instructions to adjust the vehicle's speed along the trajectory after the vehicle has entered the intersection.

14. A method of estimating risk associated with a vehicular maneuver, the method comprising:
acquiring a geometric representation of an intersection, the geometric representation including a lane in which a vehicle is traveling and at least one other lane;
discretizing the at least one other lane into a plurality of segments;
determining a trajectory along which the vehicle will travel relative to the intersection;
estimating, at each of a plurality of adjacent discrete time steps using an Eulerian model, an updated probability density function for whether a road agent external to the vehicle is present in the respective segments in the plurality of segments based, at least

Assignees

• Toyota Res Inst Inc
• Massachusetts Inst Technology

Inventors

• Mcgill Jr Stephen G
• Rosman Guy
• Ort Moses Theodore
• Pierson Alyssa
• Gilitschenski Igor
• Araki Minoru Brandon
• Fletcher Luke S
• Karaman Sertac
• Rus Daniela
• Leonard John Joseph

Classifications

• G05D1/0088

  characterized by the autonomous decision making process, e.g. artificial intelligence, predefined behaviours (using knowledge based models G06N5/00) · CPC title

• G05D1/0214

  in accordance with safety or protection criteria, e.g. avoiding hazardous areas (monitoring the location of vehicles within a certain area, e.g. forbidden or allowed areas, in traffic control systems for road vehicles G08G1/13) · CPC title

• B60W2420/408

  Radar; Laser, e.g. lidar · CPC title

• B60W30/09 Primary

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

• B60W10/04

  including control of propulsion units · CPC title