Resilient safety system for a robotic vehicle

Patent metadata

Field	Value
Publication number	US-10745003-B2
Application number	US-201514932952-A
Country	US
Kind code	B2
Filing date	Nov 4, 2015
Priority date	Nov 4, 2015
Publication date	Aug 18, 2020
Grant date	Aug 18, 2020

Abstract

Systems, apparatus, and methods implemented in algorithms, software, firmware, logic, or circuitry may be configured to process data and sensory input in real-time to determine whether an object external to an autonomous vehicle may be a potential collision threat to the autonomous vehicle. The autonomous vehicle may be configured to deploy one or more bladders positioned external to the autonomous vehicle to absorb forces from an impact to the vehicle by the object. A perception system of the vehicle may receive a sensor signal and generate object data associated with the object. A planner system of the vehicle may process the object data to predict an impact time and an impact location on the vehicle. The planner system may cause a drive system of the vehicle to maneuver the vehicle to position an impact-absorbing structure and/or one or more bladders of the vehicle to coincide with the predicted impact location.

First claim

What is claimed is:

1. A method for controlling an autonomous vehicle configured to drive autonomously on a roadway in an environment, the autonomous vehicle having a plurality of sensors, the method comprising:
calculating, based at least in part on a location of the autonomous vehicle in the environment, a current trajectory of the autonomous vehicle;
receiving first sensor data from one or more of the plurality of sensors;
detecting, based at least in part on a portion of the first sensor data, an object in the environment;
generating, based at least in part on the first sensor data and the location of the object, a predicted object trajectory of the object in the environment;
determining, based at least in part on the current trajectory and the predicted object trajectory, a first time to impact of the object with the autonomous vehicle at an intersection of the current trajectory and the predicted object trajectory;
determining, based at least in part on the first time to impact being less than or equal to a first threshold time, a safety output comprising an alert configured to be perceptible by the object;
outputting, using a safety system, the safety output;
receiving second sensor data from the one or more of the plurality of sensors;
generating, based at least in part on the second sensor data, an updated predicted object trajectory;
determining, based at least in part on the current trajectory and the updated predicted object trajectory, an updated time to impact of the object with the autonomous vehicle;
calculating, based at least in part on the updated time to impact being equal to or below a second threshold time lower than the first threshold time, a maneuver for the autonomous vehicle to perform; and
causing the autonomous vehicle to perform the maneuver.

2. The method of claim 1 , wherein calculating the maneuver comprises:
determining a predicted point of impact of the object with the autonomous vehicle; and
determining a preferred point of impact of the object with the autonomous vehicle, the preferred point of impact being different from the predicted point of impact,
wherein performing the maneuver comprises maneuvering the autonomous vehicle to align the preferred point of impact with an intersection of the current trajectory and the updated predicted object trajectory.

3. The method of claim 2 , further comprising:
determining an external safety system associated with the preferred point of impact; and
activating the external safety system.

4. The method of claim 2 , further comprising:
determining a position of a passenger in the vehicle, a distance between the position of the passenger and the predicted point of impact comprising a first distance,
wherein the preferred point of impact is a second distance from the position of the passenger, the second distance between greater than the first distance.

5. The method of claim 1 , wherein the safety system comprises a plurality of light emitters, the method further comprising:
selecting, from a plurality of light emitters, a light emitter to provide the safety output; and
causing the light emitter to provide the safety output as a visual alert comprising a light pattern perceptible by the object.

6. The method of claim 1 , wherein the safety system comprises a plurality of audio emitters, the method further comprising:
selecting from the plurality of audio emitters, an audio emitter to provide the safety output; and
causing the audio emitter to provide the safety output as an audible alert comprising an audio output perceptible by the object.

7. The method of claim 1 , further comprising:
determining an object classification of the object, the object classification being one of a pedestrian classification, a car classification, or an infrastructure classification, each object classification being associated with an object behavior,
wherein the predicted object trajectory is based at least in part on the object behavior.

8. The method of claim 1 , further comprising:
determining a presence of a passenger in a seat of the autonomous vehicle;
determining that the first time to impact or the updated time to impact is equal to or less than a third threshold time; and
increasing a tension of a seat belt associated with the seat based at least in part on the time to impact or the updated time to impact being equal to or less than a third threshold time.

9. A system comprising:
an autonomous vehicle configured to drive autonomously on a roadway;
a sensor disposed on the autonomous vehicle and operative to generate sensor data representative of an environment of the autonomous vehicle;
one or more safety systems; and
one or more processors configured to execute instructions to perform actions, including:
calculating, based at least in part on first sensor data of the sensor data, a current trajectory of the autonomous vehicle;
identifying, based at least in part on the first sensor data, an object within the environment;
determining a predicted trajectory of the object;
determining, based at least in part on the current trajectory and the predicted trajectory, a time to impact for the object with the autonomous vehicle at an intersection of the current trajectory and the predicted trajectory;
activating, based at least in part on the time to impact being equal to or less than a first time threshold, a safety system of the autonomous vehicle;
determining, based at least in part on second sensor data of the sensor data, an updated trajectory of the object;
generating, based at least in part on the updated trajectory, an updated time of impact;
calculating, based at least in part on the updated time to impact being equal to or below a second threshold time lower than the first threshold time, a maneuver for the autonomous vehicle to perform; and
causing the autonomous vehicle to perform the maneuver.

10. The system of claim 9 , wherein calculating the maneuver comprises:
determining a predicted point of impact of the object with the autonomous vehicle; and
determining a preferred point of impact of the object with the autonomous vehicle, the preferred point of impact being different from the predicted point of impact,
wherein performing the maneuver comprises maneuvering the autonomous vehicle to align the preferred point of impact with an intersection of the current trajectory and the updated predicted object trajectory.

11. The system of claim 10 , the actions further comprising:
determining an object classification of the object comprising at least one of a pedestrian, a bicyclist, or another vehicle,
wherein the preferred point of impact is based at least in part on the classification of the object.

12. The system of claim 11 wherein the preferred point of impact is determined as a first preferred point of impact based on an object classification of the object being a first object classification and wherein the preferred point of impact is determined as a second preferred point of impact based on the object classification being a second object classification.

13. The system of claim 9 , the actions further comprising:
predicting a probability of impact between the object and the autonomous vehicle based at least in part on a location of the object and the current trajectory of the autonomous vehicle,
wherein the time to impact is based at least in part on the probability of impact.

14. The system of claim 9 , the actions further comprising:
determining a presence of a passenger in a seat of the autonomous vehicle;
determining that the time to impact or the updated time to impact is equal to or

Assignees

• Zoox Inc

Inventors

• Kentley-Klay Timothy David
• Gamara Rachad Youssef
• Behere Sagar

Classifications

• B60W30/08 Primary

  Active safety systems} predicting or avoiding probable or impending collision {or attempting to minimise its consequences · CPC title

• B60Q1/525 Primary

  automatically indicating risk of collision between vehicles in traffic or with pedestrians, e.g. after risk assessment using the vehicle sensor data · CPC title

• G06V20/58

  Recognition of moving objects or obstacles, e.g. vehicles or pedestrians; Recognition of traffic objects, e.g. traffic signs, traffic lights or roads · CPC title

• B60R19/205

  inflatable in the direction of an obstacle upon impending impact, e.g. using air bags · CPC title

• B60R19/42

  extending primarily along the sides of, or completely encircling, a vehicle (ornamental or guard strips B60R13/04) · CPC title