Automated control of interactions between self-driving vehicles and animals

• US 9,481,366 B1
• Filed: 08/19/2015
• Issued: 11/01/2016
• Est. Priority Date: 08/19/2015
• Status: Expired due to Fees

• Current Assignee: International Business Machines Corporation
• Original Assignee: International Business Machines Corporation
• Inventors: Gordon, Michael S., Kozloski, James R., Kundu, Ashish, Malkin, Peter K., Pickover, Clifford A.
• Primary Examiner(s): Wong, Yuen
• Application Number:
  US14/830,103
• Time in Patent Office: 440 Days
• US Class Current: 1/1
• CPC Class Codes: B60W 30/09 Taking automatic action to avoid collision, e.g. braking and steering
• CPC Class Codes: G05D 1/0088 characterized by the autonomous decision making process, e.g. artificial intelligence, predefined behaviours using knowledge based models G06N5/00
• CPC Class Codes: G05D 1/028 using a RF signal
• CPC Class Codes: G05D 2201/0213 Road vehicle, e.g. car or truck

Abstract

A computer-implemented method, system, and/or computer program product causes a self-driving vehicle (SDV) to avoid a physical encounter with an animal. An SDV on-board computer on an SDV receives an animal predicted movement signal from an animal signal transceiver worn by an animal, and an SDV movement signal from a set of SDV sensors on the SDV that track movement of the SDV. One or more processors determine a probability of a physical encounter (E) between the SDV and the animal exceeding a predefined confidence value (C) based on the animal predicted movement signal and the SDV movement signal. In response to determining that E>C, the SDV on-board computer instructs an SDV control processor on the SDV to direct SDV vehicular physical control mechanisms on the SDV to adjust the current speed and direction of movement of the SDV.

Claims

1. A computer-implemented method for causing a self-driving vehicle (SDV) to avoid a physical encounter with an animal, the computer-implemented method comprising:

receiving, by an SDV on-board computer on the SDV, a primary animal predicted movement signal from a first animal signal transceiver worn by a first animal, wherein the primary animal predicted movement signal is indicative of a predicted movement of the first animal towards a position that the SDV is approaching on a roadway;

receiving, by the SDV on-board computer, an SDV movement signal from a set of SDV sensors on the SDV that track movement of the SDV, wherein the SDV movement signal describes a current speed and direction of movement of the SDV on the roadway;

determining, by one or more processors, a probability of a physical encounter (E) between the SDV and the first animal exceeding a predefined confidence value (C) based on the primary animal predicted movement signal and the SDV movement signal;

in response to determining, by the SDV on-board computer and based on the SDV movement signal and the primary animal predicted movement signal, that E is greater than C, the SDV on-board computer instructing an SDV control processor on the SDV to direct SDV vehicular physical control mechanisms on the SDV to adjust the current speed and direction of movement of the SDV, thereby reducing a likelihood of the SDV striking the first animal at the position that the SDV is approaching on the roadway;

receiving, by the SDV on-board computer on the SDV, a second animal presence signal from a second animal signal transceiver worn by a second animal, wherein the second animal presence signal describes a presence of the second animal within a predefined proximity of the first animal;

retrieving, by the one or more processors, historical data that describes two animals moving towards each other in the roadway within the predefined proximity to one another;

predicting, by the one or more processors, that the first animal and the second animal will approach each other at the position that the SDV is approaching on the roadway based on the historical data; and

further adjusting, by the SDV control processor on the SDV, the current speed and direction of movement of the SDV based on a prediction that the first animal and the second animal will approach each other at the position that the SDV is approaching on the roadway, in order to avoid striking the first animal.

2. The computer-implemented method of claim 1, further comprising:

retrieving, by the one or more processors, first animal profile information about the first animal;

assigning, by the one or more processors, the first animal to a cohort of first animals that have crossed the position on the roadway that the SDV is approaching, wherein the first animal shares more than a predetermined quantity of traits with members of the cohort of first animals;

retrieving, by the one or more processors, historical data describing movement by the members of the cohort of first animals when approaching the position on the roadway that the SDV is approaching;

predicting, by the one or more processors, when the first animal will reach the position on the roadway that the SDV is approaching based on the historical data describing the movement by the members of the cohort of first animals when crossing the position on the roadway that the SDV is approaching; and

further adjusting, by the SDV control processor on the SDV, the current speed and direction of movement of the SDV according to the historical data describing the movement by the members of the cohort of first animals when crossing the position on the roadway that the SDV is approaching.

3. The processor-implemented method of claim 1, further comprising:

receiving, by the one or more processors, roadway sensor readings from multiple roadway sensors, wherein each of the multiple roadway sensors detects different current conditions of the roadway;

weighting, by the one or more processors, each of the roadway sensor readings for the different current conditions of the roadway;

summing, by the one or more processors, weighted roadway sensor readings for the different current conditions of the roadway;

determining, by the one or more processors, whether the summed weighted roadway sensor readings exceed a predefined level; and

in response to determining that the summed roadway weighted sensor readings exceed the predefined level, further adjusting, by the SDV control processor on the SDV, the current speed and direction of movement of the SDV in order to avoid the SDV striking the first animal at the position on the roadway that the SDV is approaching.

4. The processor-implemented method of claim 1, further comprising:

receiving, by the one or more processors, operational readings from one or more operational sensors on the SDV, wherein the one or more operational sensors detect a current state of equipment on the SDV;

detecting, by the one or more processors and based on the received operational readings, a fault with the equipment on the SDV; and

in response to detecting the fault with the equipment on the SDV, further adjusting, by the SDV control processor on the SDV, the current speed and direction of movement of the SDV in order to avoid the SDV striking the first animal at the position on the roadway that the SDV is approaching.

5. The processor-implemented method of claim 1, wherein the primary animal predicted movement signal is based on sensor signals generated by a first animal sensor on the first animal, and wherein the processor-implemented method further comprises:

receiving, by the SDV on-board computer on the SDV, a secondary animal predicted movement signal that is indicative of the predicted movement of the first animal, wherein the secondary animal predicted movement signal is based on sensor signals generated by a second animal sensor on the first animal;

comparing, by the one or more processors, the primary animal predicted movement signal to the secondary animal predicted second signal; and

further determining, by the one or more processors, the probability of the physical encounter (E) between the SDV and the first animal based on a level of similarity of movement predictions described in the primary animal predicted movement signal and the secondary animal predicted movement signal.

6. The processor-implemented method of claim 1, further comprising:

receiving, by the SDV on-board computer on the SDV, a leash connection signal from the first animal signal transceiver, wherein the leash connection signal describes a connection state between a collar worn by the first animal and a leash; and

further adjusting, by the SDV control processor on the SDV, the current speed and direction of movement of the SDV based on the leash connection signal.

7. The computer-implemented method of claim 1, further comprising:

receiving, by the SDV on-board computer on the SDV, a first set of sensor readings describing a physical condition of the roadway and a second set of sensor readings describing a mechanical condition of the SDV; and

selectively shifting, by the SDV on-board computer on the SDV, the SDV from a normal autonomous mode to a caution autonomous mode, wherein the caution autonomous mode directs the SDV to travel slower than when in the normal autonomous mode.

8. A computer program product for causing a self-driving vehicle (SDV) to avoid a physical encounter with an animal, the computer program product comprising a non-transitory computer readable storage medium having program code embodied therewith, the program code readable and executable by a processor to perform a method, the method comprising:

receiving a primary animal predicted movement signal from a first animal signal transceiver worn by a first animal, wherein the primary animal predicted movement signal is indicative of a predicted movement of the first animal towards a position that the SDV is approaching on a roadway;

receiving an SDV movement signal from a set of SDV sensors on the SDV that track movement of the SDV, wherein the SDV movement signal describes a current speed and direction of movement of the SDV on the roadway;

determining a probability of a physical encounter (E) between the SDV and the first animal exceeding a predefined confidence value (C) based on the primary animal predicted movement signal and the SDV movement signal;

in response to determining, based on the SDV movement signal and the primary animal predicted movement signal, that E is greater than C, instructing an SDV control processor on the SDV to direct SDV vehicular physical control mechanisms on the SDV to adjust the current speed and direction of movement of the SDV, thereby reducing a likelihood of the SDV striking the first animal at the position that the SDV is approaching on the roadway;

receiving a leash connection signal from the first animal signal transceiver, wherein the leash connection signal describes a connection state between a collar worn by the first animal and a leash; and

directing the SDV control processor on the SDV to further adjust the current speed and direction of movement of the SDV based on the leash connection signal.

9. The computer program product of claim 8, wherein the method further comprises:

retrieving first animal profile information about the first animal;

assigning the first animal to a cohort of first animals that have crossed the position on the roadway that the SDV is approaching, wherein the first animal shares more than a predetermined quantity of traits with members of the cohort of first animals;

retrieving historical data describing movement by members of the cohort of first animals when approaching the position on the roadway that the SDV is approaching;

predicting when the first animal will reach the position on the roadway that the SDV is approaching based on the historical data describing the movement by the members of the cohort of first animals when crossing the position on the roadway that the SDV is approaching; and

directing the SDV control processor on the SDV to further adjust the current speed and direction of movement of the SDV according to the historical data describing movement by the members of the cohort of first animals when crossing the position on the roadway that the SDV is approaching.

10. The computer program product of claim 8, wherein the method further comprises:

receiving roadway sensor readings from multiple roadway sensors, wherein each of the multiple roadway sensors detects different current conditions of the roadway;

weighting each of the roadway sensor readings for the different current conditions of the roadway;

summing weighted roadway sensor readings for the different current conditions of the roadway;

determining whether the summed weighted roadway sensor readings exceed a predefined level; and

in response to determining that the summed roadway weighted sensor readings exceed the predefined level, directing the SDV control processor on the SDV to further adjust the current speed and direction of movement of the SDV in order to avoid the SDV striking the first animal at the position on the roadway that the SDV is approaching.

11. The computer program product of claim 8, wherein the method further comprises:

receiving operational readings from one or more operational sensors on the SDV, wherein the one or more operational sensors detect a current state of equipment on the SDV;

detecting, based on the received operational readings, a fault with the equipment on the SDV; and

in response to detecting the fault with the equipment on the SDV, directing the SDV control processor on the SDV to further adjust the current speed and direction of movement of the SDV in order to avoid the SDV striking the first animal at the position on the roadway that the SDV is approaching.

12. The computer program product of claim 8, wherein the primary animal predicted movement signal is based on sensor signals generated by a first animal sensor on the first animal, and wherein the processor-implemented method further comprises, and wherein the method further comprises:

receiving a secondary animal predicted movement signal describing the predicted movement of the first animal, wherein the secondary animal predicted movement signal is based on sensor signals generated by a second animal sensor on the first animal;

comparing the primary animal predicted movement signal to the secondary animal predicted second signal; and

further determining the probability of the physical encounter (E) between the SDV and the first animal based on a level of similarity of movement predictions described in the primary animal predicted movement signal and the secondary animal predicted movement signal.

13. A computer system for causing a self-driving vehicle (SDV) to avoid a physical encounter with an animal, comprising:

one or more processors;

one or more computer readable memories; and

one or more non-transitory computer readable storage mediums, and wherein program instructions are stored on at least one of the one or more non-transitory storage mediums for execution by at least one of the one or more processors via at least one of the one or more memories, to perform a method, the method comprising;

receiving a primary animal predicted movement signal from a first animal signal transceiver worn by a first animal, wherein the primary animal predicted movement signal is indicative of a predicted movement of the first animal towards a position that the SDV is approaching on a roadway;

receiving an SDV movement signal from a set of SDV sensors on the SDV that track movement of the SDV, wherein the SDV movement signal describes a current speed and direction of movement of the SDV on the roadway;

determining a probability of a physical encounter (E) between the SDV and the first animal exceeding a predefined confidence value (C) based on the primary animal predicted movement signal and the SDV movement signal;

in response to determining based on the SDV movement signal and the primary animal predicted movement signal that E is greater than C, instructing an SDV control processor on the SDV to direct SDV vehicular physical control mechanisms on the SDV to adjust the current speed and direction of movement of the SDV, thereby reducing a likelihood of the SDV striking the first animal at the position that the SDV is approaching on the roadway;

retrieving first animal profile information about the first animal;

assigning the first animal to a cohort of first animals that have crossed the position on the roadway that the SDV is approaching, wherein the first animal shares more than a predetermined quantity of traits with members of the cohort of first animals;

retrieving historical data describing movement by members of the cohort of first animals when approaching the position on the roadway that the SDV is approaching;

predicting when the first animal will reach the position on the roadway that the SDV is approaching based on the historical data describing the movement by the members of the cohort of first animals when crossing the position on the roadway that the SDV is approaching; and

directing the SDV control processor on the SDV to further adjust the current speed and direction of movement of the SDV according to the historical data describing the movement by the members of the cohort of animals when crossing the position on the roadway that the SDV is approaching.

14. The computer system of claim 13, wherein the method further comprises:

receiving roadway sensor readings from multiple roadway sensors, wherein each of the multiple roadway sensors detects different current conditions of the roadway;

weighting each of the roadway sensor readings for the different current conditions of the roadway;

summing weighted roadway sensor readings for the different current conditions of the roadway;

determining whether the summed weighted roadway sensor readings exceed a predefined level; and

in response to determining that the summed roadway weighted sensor readings exceed the predefined level, directing the SDV control processor on the SDV to further adjust the current speed and direction of movement of the SDV in order to avoid striking the first animal at the position on the roadway that is being approached by the SDV.

15. The computer system of claim 13, wherein the method further comprises:

receiving operational readings from one or more operational sensors on the SDV, wherein the one or more operational sensors detect a current state of equipment on the SDV;

detecting, based on received operational readings, a fault with the equipment on the SDV; and

in response to detecting the fault with the equipment on the SDV, directing the SDV control processor on the SDV to further adjust the current speed and direction of movement of the SDV in order to avoid striking the first animal at the position on the roadway that is being approached by the SDV.

16. The computer system of claim 13, wherein the method further comprises:

receiving a second animal presence signal from a second animal signal transceiver worn by a second animal, wherein the second animal presence signal describes a presence of the second animal within a predefined proximity of the first animal;

retrieving historical data that describes two animals moving towards each other in the roadway within the predefined proximity to one another;

predicting that the first animal and the second animal will approach each other at the position that the SDV is approaching on the roadway based on the historical data; and

further adjusting the current speed and direction of movement of the SDV based on a prediction that the first animal and the second animal will approach each other at the position that the SDV is approaching on the roadway, in order to avoid striking the first animal.

17. The computer system of claim 13, wherein the method further comprises:

receiving a leash connection signal from the first animal signal transceiver, wherein the leash connection signal describes a connection state between a collar worn by the first animal and a leash; and

further directing the SDV control processor on the SDV to adjust the current speed and direction of movement of the SDV based on the leash connection signal.