Method to minimize collisions of mobile robotic device

Inventor: Ali Ebrahimi Afrouzi (San Diego, CA)

Assignee: AI Incorporated

B25J9/1666 B25J9/163

View Patent ↗

Loading inventors, assignments & file history…

Monitor This Case

Get email alerts when status or documents change.

Order Certified Copies

Most orders are placed with the USPTO same day — all within 24 business hours.

Order via The Patent Place →

Pre-filled with this patent's details

Quick Facts

Patent No.: US 11,919,172
App. No.: 17/365,225
Granted: Mar 5, 2024
Kind: B1

External Links

USPTO Patent Center↗ Full Patent PDF↗

Abstract

Provided is a mobile robotic device, including at least: a plurality of sensors; a processor; and a tangible, non-transitory, machine readable medium storing instructions that when executed by the processor effectuates operations comprising: selecting, by the processor, one or more actions to navigate through a workspace, wherein each action transitions the mobile robotic device from a current state to a next state; actuating, by the processor, the mobile robotic device to execute the selected one or more actions; detecting, by the processor, whether a collision is incurred by the mobile robotic device for each action executed; and, assigning, by the processor, each collision to a location within a map of the workspace wherein the location corresponds to where the respective collision occurred.

Claims (48)

1. A mobile robotic device, comprising at least:

a plurality of sensors;

a processor; and

a tangible, non-transitory, machine readable medium storing instructions that when executed by the processor effectuates operations comprising:

selecting, by the processor, one or more actions to navigate through a workspace, wherein:

each action transitions the mobile robotic device from a current state to a next state; and

each state of the mobile robotic device comprises at least a location of the mobile robotic device within the workspace;

actuating, by the processor, the mobile robotic device to execute the selected one or more actions;

detecting, by the processor, whether a collision is incurred by the mobile robotic device for each action executed;

detecting, by the processor, whether the mobile robotic device is repeatedly transitioning between a same collection of states;

determining, by the processor, the mobile robotic device is stuck when the mobile robotic device is repeatedly transitioning between the same collection of states; and,

assigning, by the processor, each collision to a location within a map of the workspace wherein the location corresponds to where the respective collision occurred.

2. The mobile robotic device of claim 1 , wherein the collection of states includes two to ten different states.

3. The mobile robotic device of claim 1 , wherein the operations further comprise:

selecting, by the processor, one or more actions to navigate the mobile robotic device to a state not included in the collection of states.

4. The mobile robotic device of claim 3 , wherein the mobile robotic device transitions to one or more states within the collection of states to reach the state not included in the collection of states.

5. The mobile robotic device of claim 1 , wherein the operations further comprise: calculating and assigning, by the processor, a reward for each action executed based on collisions incurred by the mobile robotic device and completion of the action.

6. The mobile robotic device of claim 1 , wherein locations of collisions within the map of the workspace correspond to collisions that occurred during one or more work sessions.

7. The mobile robotic device of claim 1 , wherein the operations further comprise: determining, by the processor, a movement path of the mobile robotic device based on locations of previous collisions and a number of previous collisions at different locations within the map of the workspace.

8. The mobile robotic device of claim 1 , wherein the one or more actions is selected based on at least one of: at least a portion of the data collected by the plurality of sensors, locations of previous collisions, locations of obstacles, level of debris accumulation in different areas, and floor type in different areas.

9. The mobile robotic device of claim 1 , wherein selecting the one or more actions further comprises:

reviewing, by the processor, all previous actions executed from the current state of the mobile robotic device; and

selecting, by the processor, the one or more actions that previously resulted in a highest reward.

10. The mobile robotic device of claim 1 , wherein selecting the one or more actions further comprises:

reviewing, by the processor, all previous actions executed from a collection of states beginning with the current state of the mobile robotic device;

calculating, by the processor, a total reward for different collections of states and actions; and

selecting, by the processor, a collection of states and actions resulting in a highest reward.

11. The mobile robotic device of claim 1 , wherein the operations further comprise:

determining, by the processor, a total reward value for the one or more actions executed and corresponding states visited during the work session;

assigning, by the processor, the total reward value to a policy comprised of the one or more actions executed and corresponding states visited during the work session; and

iteratively generating new policies, by the processor, until a policy that exceeds a predetermined total reward value is generated.

12. A tangible, non-transitory, machine readable medium storing instructions that when executed by a processor of a mobile robotic device effectuates operations comprising: