Computer system and method for automated mapping by robots

• US 10,539,960 B2
• Filed: 02/28/2018
• Issued: 01/21/2020
• Est. Priority Date: 05/01/2017
• Status: Active Grant

• Current Assignee: Savioke, Inc.
• Original Assignee: Savioke, Inc.
• Inventors: Bauer, Robert S., Minier, Alain, Wirth, Stephan, Chiesa, Lucas, Fritz, Christian, Canoso, Adrian
• Primary Examiner(s): Zanelli, Michael J
• Application Number:
  US15/908,037
• Publication Number:
  US 20180314254A1
• Time in Patent Office: 692 Days
• CPC Class Codes: G01C 21/206 specially adapted for indoor navigation
• 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 1/0246 using a video camera in combination with image processing means
• CPC Class Codes: G05D 1/0274 using mapping information stored in a memory device navigation using map-matching G01C21/30
• CPC Class Codes: G05D 1/0285 using signals transmitted via a public communication network, e.g. GSM network
• CPC Class Codes: G09B 29/00 Maps; Plans; Charts; Diagrams, e.g. route diagram star maps G09B27/04; devices for holding or supporting maps A47B97/02; for computing purposes G06G1/14, G09B1/16; display boards G09F

Abstract

A method for autonomous map generation by a robot comprising: instructing the robot to traverse a route within an environment in which the robot is deployed; while following the route, causing the robot to collect sensor data to identify features in the environment and to generate an initial map of areas in environment that have been traversed; upon completion of the route, autonomously generating a map of valid areas of the environment by moving throughout the environment while collecting sensor data; while autonomously generating the map, determining that a particular area is potentially invalid by detecting features that are previously unknown to the robot; generating and providing an electronic message to an operator of the robot comprising sensor data of the particular area and a prompt requesting information indicating whether the particular area is valid or invalid; upon receiving a response from the operator, continuing autonomously generating the map according to the response wherein if the particular area is valid, collecting sensor data from the particular area and, if the particular area is invalid, proceeding to an unmapped, valid area of the environment; determining that there are no remaining unmapped, valid areas of the environment, ending autonomously generating the map.

Claims

1. A method for a robot to autonomously generate a digitally stored map of an environment, the method comprising:

receiving, via an input signal to a stored program executing in the robot, an instruction to physically traverse a route within the environment, the route comprising a path through the environment, and in response to the input signal, initiating physical traversal of the robot of the route;

while traversing the route, collecting digital data from one or more sensors of the robot and digitally transforming the collected digital data to result in identifying one or more features of the environment and to generate a digitally stored initial map representing areas in the environment that have been traversed;

determine whether collected digital data is sufficient for the robot to perform autonomous mapping;

in response to determining that the collected digital data is sufficient for the robot to perform autonomous mapping, initiating autonomous mapping of one or more unmapped portions of the environment.

2. The method of claim 1 wherein autonomous mapping of the one or more unmapped portions of the environment comprises:

determining one or more valid areas of the environment;

generating and storing a digital map representing the one or more valid areas of the environment.

3. The method of claim 1 wherein autonomous mapping of the one or more unmapped portions of the environment comprises:

determining one or more potentially invalid areas of the environment;

for each potentially invalid area of the one or more potentially invalid areas, generating and transmitting an electronic message comprising collected sensor data for the potentially invalid area and a prompt requesting information indicating whether the potentially invalid area is valid.

4. The method of claim 1 further comprising during autonomous mapping of the one or more unmapped portions of the environment, determining that a particular feature of the environment in a previously mapped area is not represented in a digital map, and in response, updating the digital map to indicate the particular feature.

5. The method of claim 1 wherein determining whether the collected digital data is sufficient for the robot to perform autonomous mapping comprises determining whether one or more particular features have been identified.

6. The method of claim 1 wherein determining whether the collected digital data is sufficient for the robot to perform autonomous mapping comprises determining whether a particular number of features have been identified.

7. The method of claim 1 wherein determining whether the collected digital data is sufficient for the robot to perform autonomous mapping comprises determining whether a length of the route traversed exceeds a particular length.

8. The method of claim 1 further comprising, in response to determining the collected digital data is not sufficient for the robot to perform autonomous mapping, generating and transmitting an electronic message comprising a request to traverse an additional route.

9. The method of claim 1 further comprising:

during autonomous mapping of the one or more unmapped portions of the environment, identifying one or more features located in the one or more unmapped portions of the environment;

generating and storing digital map label values in association with the one or more features.

10. The method of claim 9 wherein identifying the one or more features in the one or more unmapped portions of the environment is based on one or more previously identified features.

11. A robot programmed to execute a method to autonomously generate a digitally stored map of an environment, the robot comprising:

one or more computers;

one or more digital sensors that are coupled to the one or more computers and operable under program control of the one or more computers to collect signals based upon sensing the environment of the robot;

a non-transitory computer-readable storage medium coupled to the one or more computers and storing instructions which, when executed by the one or more computers, cause performing;

receiving, via an input signal to a stored program executing in the robot, an instruction to physically traverse a route within the environment, the route comprising a path through the environment, and in response to the input signal, initiating physical traversal of the robot of the route;

while traversing the route, collecting digital data from one or more sensors of the robot and digitally transforming the collected digital data to result in identifying one or more features of the environment and to generate a digitally stored initial map representing areas in the environment that have been traversed;

determine whether collected digital data is sufficient for the robot to perform autonomous mapping;

in response to determining that the collected digital data is sufficient for the robot to perform autonomous mapping, initiating autonomous mapping of one or more unmapped portions of the environment.

12. The robot of claim 11 wherein autonomous mapping of the one or more unmapped portions of the environment comprises:

determining one or more valid areas of the environment;

generating and storing a digital map representing the one or more valid areas of the environment.

13. The robot of claim 11 wherein autonomous mapping of the one or more unmapped portions of the environment comprises:

determining one or more potentially invalid areas of the environment;

for each potentially invalid area of the one or more potentially invalid areas, generating and transmitting an electronic message comprising collected sensor data for the potentially invalid area and a prompt requesting information indicating whether the potentially invalid area is valid.

14. The robot of claim 11 further comprising instructions which, when executed by the one or more computers, cause during autonomous mapping of the one or more unmapped portions of the environment, determining that a particular feature of the environment in a previously mapped area is not represented in a digital map, and in response, updating the digital map to indicate the particular feature.

15. The robot of claim 11 wherein determining whether the collected digital data is sufficient for the robot to perform autonomous mapping comprises determining whether one or more particular features have been identified.

16. The robot of claim 11 wherein determining whether the collected digital data is sufficient for the robot to perform autonomous mapping comprises determining whether a particular number of features have been identified.

17. The robot of claim 11 wherein determining whether the collected digital data is sufficient for the robot to perform autonomous mapping comprises determining whether a length of the route traversed exceeds a particular length.

18. The robot of claim 11 further comprising instructions which, when executed by the one or more computers, cause in response to determining the collected digital data is not sufficient for the robot to perform autonomous mapping, generating and transmitting an electronic message comprising a request to traverse an additional route.

19. The robot of claim 11 further comprising instructions which, when executed by the one or more computers, cause:

during autonomous mapping of the one or more unmapped portions of the environment, identifying one or more features located in the one or more unmapped portions of the environment;

generating and storing digital map label values in association with the one or more features.

20. The robot of claim 19 wherein identifying the one or more features in the one or more unmapped portions of the environment is based on one or more previously identified features.