Method for re-mapping safe and traversable routes

• US 10,578,443 B2
• Filed: 11/24/2016
• Issued: 03/03/2020
• Est. Priority Date: 11/24/2015
• Status: Active Grant

• Current Assignee: Daxbot Incorporated
• Original Assignee: Nova Dynamics, LLC
• Inventors: Sullivan, Joseph
• Primary Examiner(s): Swerdlow, Daniel
• Application Number:
  US15/361,042
• Publication Number:
  US 20180328743A1
• Time in Patent Office: 1,195 Days
• CPC Class Codes: B60W 2050/143 Alarm means
• CPC Class Codes: B60W 50/14 Means for informing the driver, warning the driver or prompting a driver intervention
• CPC Class Codes: G01C 21/3415 Dynamic re-routing, e.g. recalculating the route when the user deviates from calculated route or after detecting real-time traffic data or accidents
• CPC Class Codes: G01C 21/3848 Data obtained from both position sensors and additional sensors
• 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 1/0214 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 Class Codes: G06F 16/29 Geographical information databases
• CPC Class Codes: G06Q 10/083 Shipping
• CPC Class Codes: G06V 20/58 Recognition of moving objects or obstacles, e.g. vehicles or pedestrians; Recognition of traffic objects, e.g. traffic signs, traffic lights or roads

Abstract

A method for manually or semi-manually re-mapping an urban environment during delivery operations by an autonomous vehicle is provided herein. In an embodiment of the invention, an autonomous delivery vehicle performs delivery operations within an urban environment. The urban environment can comprise a city or a portion of a city such as a neighborhood. The autonomous vehicle traverses along a previously mapped and scanned route that has been determined to be safe and traversable for the delivery vehicle. As it traverses the route, the delivery vehicle scans the route again using the same sensors that were used to scan the route initially. If a sensor delta is exceeded, the vehicle may execute any one or combination of notifying an operator, deciding, choosing a different route, continuing, or executing a contingency plan.

Claims

1. A method for responding to unsafe conditions detected by a robot delivery vehicle during delivery operations, the method comprising:

following a route profile by the robot delivery vehicle to traverse a route, wherein the route profile includes one or more old sensor data sets, each being unique in a sensor type, wherein each old sensor data set comprises information respective to a stored set of one or more objects contained within the route, wherein a preset operating delta and a preset intervention delta are associated with each old sensor data set, and wherein the sensor type is selected from a group consisting of a GPS sensor, a radar sensor, a visual recording device, a sonar sensor, and a laser sensor;

traversing the route by the robot delivery vehicle while gathering one or more new sensor data sets using one or more sensors of a sensor array included in the robot delivery vehicle, wherein each new sensor data set includes data from an individual sensor of the sensor array and comprises information respective to a detected set of one or more objects contained in the route, and wherein at least one sensor of the array is of the same sensor type as one of the old sensor data sets;

comparing by the robot delivery vehicle the new sensor data sets and the old sensor data sets of the same sensor type to determine a variance between the stored set of one or more objects and the detected set of one or more objects;

calculating by the robot delivery vehicle whether the variance exceeds the preset operating delta and calculating by the robot delivery vehicle whether the variance exceeds the preset operating delta and the preset intervention delta;

executing by the robot delivery vehicle a contingency plan when the robot delivery vehicle determines that the variance exceeds the preset operating delta and does not exceed the preset intervention delta, wherein the contingency plan includes one or more instructions for the robot delivery vehicle to execute until the variance does not exceed the preset operating delta; and

causing the robot delivery vehicle to alert a human controller at a remote location when the robot delivery vehicle determines that the variance exceeds the preset operating delta and the preset intervention delta, and receiving commands remotely by the robot delivery vehicle from the human controller until the variance does not exceed the preset operating delta and the preset intervention delta.

2. The method of claim 1, wherein the one or more instructions include one or more of reducing speed, taking an alternate route, and remaining motionless.

3. The method of claim 1, wherein the variance is determined to exceed one or more of the preset operating delta and the preset intervention delta when an object of the detected set of one or more objects is not included in the stored set of one or more objects.

4. The method of claim 3, wherein the object of the detected set of one or more objects includes one or more of a fallen tree, a pedestrian, a pothole, an aggressive animal, a street closure, a trash can, a recycling can, snow, and ice.

5. The method of claim 1, further comprising reviewing by a human the one or more new sensor data sets that were gathered before, during, and after the intervention delta is exceeded;

and

determining by the human an occurrence that caused the intervention delta to be exceeded, wherein the occurrence is one of a non-traversable condition that is not represented in the route profile and a false alarm.

6. The method of claim 5, further comprising updating the route profile manually by the human to include the new sensor data representative of the non-traversable condition, and updating the route profile manually by the human to avoid the non-traversable condition when the human determines that the occurrence is caused by the non-traversable condition.

7. The method of claim 6, wherein the robot delivery vehicle is a first robot delivery vehicle, and wherein the updated route profile is to be used in the future by a second robot delivery vehicle when the second robot delivery vehicle traverses the route.

8. The method of claim 5, further comprising adjusting one or more of the preset operating delta and the preset intervention delta when the human deter nines that the occurrence is caused by the false alarm.

9. The method of claim 1, further comprising continuing to traverse the route by the robot delivery vehicle when the robot delivery vehicle determines that the variance does not exceed the operating delta.

10. The method of claim 1, wherein the robot delivery vehicle is a self-propelled vehicle configured to travel over one or more of sidewalks and crowded sidewalks.

11. A method for responding to unsafe conditions detected by a robot delivery vehicle during delivery operations, the method comprising:

following a route profile by the robot delivery vehicle to traverse a route, wherein the route profile comprises information respective to a stored set of one or more objects contained within the route, wherein a preset operating delta and a preset intervention delta are associated with the route profile;

traversing the route by the robot delivery vehicle while gathering one or more sensor data sets using one or more sensors of a sensor array included in the robot delivery vehicle, wherein each sensor data set includes data from an individual sensor of the sensor array and comprises information respective to a detected set of one or more objects contained in the route, wherein the detected set of one or more objects comprises a new route profile, and wherein each sensor of the array is of a sensor type selected from a group consisting of a GPS sensor, a radar sensor, a visual recording device, a sonar sensor, and a laser sensor;

comparing by the robot delivery vehicle the route profile and the new route profile to determine a variance between the stored set of one or more objects and the detected set of one or more objects;

calculating by the robot delivery vehicle whether the variance exceeds the operating delta;

calculating by the robot delivery vehicle whether the variance exceeds the intervention delta when the robot delivery vehicle determines that the operating delta is exceeded;

executing by the robot delivery vehicle a contingency plan when the robot delivery vehicle determines that the variance exceeds the operating delta and does not exceed the intervention delta, wherein the contingency plan includes one or more instructions for the robot delivery vehicle to execute;

causing the robot delivery vehicle to alert a human controller at a remote location when the robot delivery vehicle determines that the variance exceeds the intervention delta and the operating delta; and

continuing to traverse the route by the robot delivery vehicle when the robot delivery vehicle determines that the variance does not exceed the operating delta.

12. The method of claim 11, wherein the one or more instructions include one or more of reducing speed, taking an alternate route, and remaining motionless.

13. The method of claim 11, wherein the variance is determined to exceed one or more of the operating delta and the intervention delta when an object that is included in the new route profile is not included in the route profile.

14. The method of claim 13, wherein the object includes one or more of a fallen tree, a pedestrian, a pothole, an aggressive animal, a street closure, a trash can, a recycling can, snow, and ice.

15. The method of claim 11, further comprising reviewing by a human the one or more sensor data sets that were gathered before, during, and after the intervention delta is exceeded;

and

determining by the human an occurrence that caused the intervention delta to be exceeded, wherein the occurrence is one of a non-traversable condition that is not represented in the route profile and a false alarm.

16. The method of claim 15, further comprising updating the route profile manually by the human to include the non-traversable condition represented in the new route profile, and updating the route profile manually by the human to avoid the non-traversable condition when the human determines that the occurrence is caused by the non-traversable condition.

17. The method of claim 15, further comprising adjusting one or more of the preset operating delta and the preset intervention delta when the human determines that the occurrence is caused by the false alarm.

18. The method of claim 11, wherein the route profile further includes additional navigation information, and wherein the additional navigation information includes one or more of cardinal directions, turn directions, landmarks, terrain information, environmental information, and chronological information.

19. The method of claim 17, wherein the robot delivery vehicle is a first robot delivery vehicle, and wherein the one or more of the adjusted preset operating delta and the adjusted preset intervention delta are to be used in the future by a second robot delivery vehicle when the second robot delivery vehicle traverses the route.

20. The method of claim 11, wherein the robot delivery vehicle is a self-propelled vehicle configured to travel over one or more of sidewalks and crowded sidewalks.