Dynamically Maintaining A Map Of A Fleet Of Robotic Devices In An Environment To Facilitate Robotic Action

Patent metadata

Field	Value
Publication number	US-2016129592-A1
Application number	US-201514863620-A
Country	US
Kind code	A1
Filing date	Sep 24, 2015
Priority date	Nov 11, 2014
Publication date	May 12, 2016
Grant date	—

Abstract

Methods and systems for dynamically maintaining a map of robotic devices in an environment are provided herein. A map of robotic devices may be determined, where the map includes predicted future locations of at least some of the robotic devices. One or more robotic devices may then be caused to perform a task. During a performance of the task by the one or more robotic devices, task progress data may be received from the robotic devices, indicative of which of the task phases have been performed. Based on the data, the map may be updated to include a modification to the predicted future locations of at least some of the robotic devices. One or more robotic devices may then be caused to perform at least one other task in accordance with the updated map.

First claim

What is claimed is:

1 . A method comprising:
determining a map of a plurality of robotic devices within a physical environment, wherein the map includes predicted future locations of at least some of the plurality of robotic devices; causing one or more robotic devices of the plurality to perform a task comprising one or more task phases; during a performance of at least one of the one or more task phases by the one or more robotic devices, receiving, from the one or more robotic devices, task progress data indicative of which of the one or more task phases have been performed by the one or more robotic devices; based on the received task progress data, updating the map of the plurality of robotic devices within the physical environment, wherein the updated map includes at least one modification to the predicted future locations of at least some of the plurality of robotic devices; and causing the one or more robotic devices to perform at least one other task phase in accordance with the updated map.

2 . The method of claim 1 , wherein performance of the task involves a manipulation of at least one object by the one or more robotic devices,
wherein the physical environment includes a plurality of objects including the at least one object, wherein the map further includes predicted future locations of at least some of the plurality of objects, and wherein the updated map includes at least one modification to the predicted future locations of at least some of the plurality of objects.

3 . The method of claim 1 , wherein the predicted future locations of at least some of the plurality of robotic devices include predicted future trajectories of at least some of the plurality of robotic devices, and
wherein the at least one modification to the predicted future locations of at least some of the plurality of robotic devices includes at least one modification to the predicted future trajectories.

4 . The method of claim 1 , wherein the predicted future locations of at least some of the plurality of robotic devices include predicted future sets of joint variables of one or more appendages of at least some of the plurality of robotic devices, and
wherein the at least one modification to the predicted future locations of at least some of the plurality of robotic devices includes at least one modification to the predicted future sets of joint variables of the one or more appendages.

5 . The method of claim 1 , further comprising:
based on the determined map, determining an anticipated completion time of a performance of the task by the one or more robotic devices; and based on the updated map, updating the anticipated completion time of the performance of the task.

6 . The method of claim 5 , wherein the performance of the task involves at least one object being delivered by the one or more robotic devices to a target location.

7 . The method of claim 1 , further comprising:
based on the determined map, determining anticipated completion times of performances of the one or more task phases by the one or more robotic devices; and based on the updated map, updating the anticipated completion time of the performance of the at least one other task phase.

8 . The method of claim 1 , performed by a cloud computing system that is in communication with at least a portion of the plurality of robotic devices, wherein the portion includes the one or more robotic devices, the method further comprising:
maintaining a queue of updates to the map, wherein each update to the map in the queue includes data specifying a time at which to publish the update to a given robotic device of the plurality of robotic devices; and publishing updates maintained in the queue in accordance with the specified times.

9 . The method of claim 1 , wherein the one or more robotic devices controlled to perform the task include at least two different types of robotic devices, and wherein the performance of the at least one of the one or more task phases by the one or more robotic devices involves a coordinated manipulation of at least one object in the physical environment by robotic devices of the at least two different types.

10 . The method of claim 1 , wherein the map includes data representative of predicted future times corresponding to respective predicted future locations of the predicted future locations, wherein the predicted future times indicate points in time at which at least some of the plurality of robotic devices will be located at the respective predicted future locations, wherein updating the map of the plurality of robotic devices based on the received task progress data comprises:
based on the received task progress data, determining the at least one modification to the predicted future locations of at least some of the plurality of robotic devices, wherein the determined at least one modification to the predicted future locations includes at least one modification to the predicted future times corresponding to the respective predicted future locations; and updating the map to include data representative of the determined at least one modification to the predicted future locations and to further include data representative of the at least one modification to the predicted future times.

11 . A system comprising:
a plurality of robotic devices within a physical environment; at least one processor; and data storage comprising instructions executable by the at least one processor to cause the system to perform operations comprising:
determining a map of the plurality of robotic devices within the physical environment, wherein the map includes predicted future locations of at least some of the plurality of robotic devices;
causing one or more robotic devices of the plurality to perform a task comprising one or more task phases;
during a performance of at least one of the one or more task phases by the one or more robotic devices, receiving, from the one or more robotic devices, task progress data indicative of which of the one or more task phases have been performed by the one or more robotic devices;
based on the received task progress data, updating the map of the plurality of robotic devices within the physical environment, wherein the updated map includes at least one modification to the predicted future locations of at least some of the plurality of robotic devices; and
causing the one or more robotic devices to perform at least one other task phase in accordance with the updated map.

12 . The system of claim 11 , wherein the plurality of robotic devices includes at least one static robotic device fixed at given location within the physical environment and further includes at least one dynamic robotic device configured to travel to multiple locations within the physical environment,
wherein the map includes predicted future locations of at least one static robotic device and at least one dynamic robotic device; wherein the performance of the at least one of the one or more task phases involves a performance of at least one of the one or more task phases by at least one static robotic device in coordination with at least one dynamic robotic device; and wherein the updated map includes at least one modification to the predicted future locations of the at least one static robotic device and the at least one dynamic robotic device involved in the performance of the at least one of the one or more task phases.

13 . The system of claim 11 , wherein causing the one or more robotic devices to perform at least one other task phase in accordance with the updated map comprises, transmitting, to the one or more robotic devices, at least

Assignees

• Google Inc

Inventors

• Saboo Rohit Ramesh
• Kuffner James Joseph
• Mason Julian

Classifications

• B25J9/0084

  comprising a plurality of manipulators · CPC title

• G05B2219/45056

  Handling cases, boxes · CPC title

• G05B2219/31006

  Monitoring of vehicle · CPC title

• B25J9/1674

  characterised by safety, monitoring, diagnostic · CPC title

• B25J19/021

  Optical sensing devices · CPC title