Self-actuated cleaning head for an autonomous vacuum
An autonomous cleaning robot (e.g., an autonomous vacuum) may clean an environment using a cleaning head that is self-actuated. The cleaning head includes an actuator assembly comprising an actuator configured to control rotation and vertical movement of a cleaning roller, a controller, and a cleaning roller having an elongated cylindrical length connected to the actuator assembly. The cleaning head also includes a computer processor connected to the actuator assembly and a non-transitory computer-readable storage medium that causes the computer processor to map the environment based on sensor data captured by the autonomous vacuum. The computer processor may determine an optimal height for the cleaning head based on the map and instruct the actuator assembly to adjust the height of the cleaning head.
1 . An autonomous vacuum comprising:
a sensor system comprising one or more sensors configured to capture sensor data of an environment of the autonomous vacuum;
one or more cleaning assemblies including a sweeping assembly and a mopping assembly;
an actuator assembly including one or more actuators configured to engage the one or more cleaning assemblies of the autonomous vacuum;
a computer processor communicatively coupled to the sensor system and the actuator assembly; and
a non-transitory computer-readable storage medium comprising stored instructions, the instructions when executed by the computer processor causes the computer processor to:
receive, from the sensor system, the sensor data;
detect a mess by extracting features relating to the mess from the sensor data;
determine a mess type based on the extracted features;
determine a surface type of a surface which the mess is on top of based on the sensor data;
determine a cleaning mode for the autonomous vacuum based on the determined mess type and the surface type; and
instruct the actuator assembly to engage the sweeping assembly or the mopping assembly corresponding to the determined cleaning mode.
2 . The autonomous vacuum of claim 1 , wherein the instructions to determine the surface type of the surface which the mess is on top of based on the sensor data, when executed, further cause the computer processor to:
retreive a three-dimensional map of the environment based on the sensor data; and
determine the surface type of the surface based on the three-dimensional map of the environment.
3 . The autonomous vacuum of claim 1 , wherein the instructions causing the computer processor to determine the mess type comprises causing the computer processor to determine the mess type from a wet mess type and a dry mess type, and wherein the instructions causing the computer processor to determine the cleaning mode based on the mess type comprises causing the computer processor to select the sweeping mode for the dry mess type and to select the mopping mode for the wet mess type.
4 . The autonomous vacuum of claim 1 , wherein the instructions, when executed, further cause the computer processor to:
retreive a three-dimensional map of the environment based on the sensor data;
determine, based on the three-dimensional map of the environment, a ground plane of the environment; and
determining an optimal height of the sweeping assembly or the mopping assembly of the autonomous vacuum based on the ground plane.
5 . The autonomous vacuum of claim 1 , wherein the instructions, when executed, further cause the computer processor to:
determine a height of the surface based on the sensor data; and
determine an optimal height of the sweeping assembly or the mopping assembly of the autonomous vacuum based on the cleaning mode, the surface type, and the height of the surface.
6 . The autonomous vacuum of claim 1 , wherein the instructions, when executed, further cause the computer processor to:
detect an obstacle in the environment based on the sensor data;
determine a height of the obstacle based on the sensor data; and
instruct the actuator assembly to adjust a height of the sweeping assembly or the mopping assembly of the autonomous vacuum based on the height of the obstacle to clear the obstacle in the environment.
7 . The autonomous vacuum of claim 1 , wherein the mess type is determined by extracting features from real-time visual data captured by a camera or an infrared system.
8 . The autonomous vacuum of claim 1 , wherein instructing a first set of actuators to engage the sweeping assembly is a different set of actuators from a set of actuators to engage the mopping assembly.
9 . The autonomous vacuum of claim 1 , wherein the mopping assembly comprises:
a mop pad configured to contact a ground of the environment; and
a spray system to spray solvent on the mop pad for mopping.
10 . The autonomous vacuum of claim 1 , wherein the sweeping assembly comprises:
a brush roller configured to contact a ground of the environment; and
a brush motor coupled to the brush roller and configured to rotate the brush roller.
11 . A non-transitory computer-readable storage medium comprising instructions that, when executed by a computer processor, cause the computer processor to:
receive, from a sensor system, sensor data;
detect a mess by extracting features relating to the mess from the sensor data;
determine a mess type based on the extracted features;
determine a surface type of a surface which the mess is on top of based on the sensor data;
determine a cleaning mode for an autonomous vacuum based on the determined mess type and the surface type; and
instruct an actuator assembly to engage a sweeping assembly or a mopping assembly corresponding to the determined cleaning mode.
12 . The non-transitory computer-readable storage medium of claim 11 , wherein the instructions to determine the surface type of the surface which the mess is on top of based on the sensor data, when executed, further cause the computer processor to:
retreive a three-dimensional map of an environment based on the sensor data; and
determine the surface type of the surface based on the three-dimensional map of the environment.
13 . The non-transitory computer-readable storage medium of claim 11 , wherein the instructions causing the computer processor to determine the mess type comprises causing the computer processor to determine the mess type from a wet mess type and a dry mess type, and wherein the instructions causing the computer processor to determine the cleaning mode based on the mess type comprises causing the computer processor to select the sweeping mode for the dry mess type and to select the mopping mode for the wet mess type.
14 . The non-transitory computer-readable storage medium of claim 11 , wherein the instructions, when executed, further cause the computer processor to:
retreive a three-dimensional map of an environment based on the sensor data;
determine, based on the three-dimensional map of the environment, a ground plane of the environment; and
determining an optimal height of the sweeping assembly or the mopping assembly of the autonomous vacuum based on the ground plane.
15 . The non-transitory computer-readable storage medium of claim 11 , wherein the instructions, when executed, further cause the computer processor to:
determine a height of the surface based on the sensor data; and
determine an optimal height of the sweeping assembly or the mopping assembly of the autonomous vacuum based on the cleaning mode, the surface type, and the height of the surface.
16 . The non-transitory computer-readable storage medium of claim 11 , wherein the instructions, when executed, further cause the computer processor to:
detect an obstacle in an environment based on the sensor data;
determine a height of the obstacle based on the sensor data; and
instruct the actuator assembly to adjust a height of the sweeping assembly or the mopping assembly of the autonomous vacuum based on the height of the obstacle to clear the obstacle in the environment.
17 . A method for determining a cleaning mode for an autonomous vacuum, the method comprising:
receiving, from a sensor system, sensor data;
detecting a mess by extracting features relating to the mess from the sensor data;
determining a mess type based on the extracted features;
determining a surface type of a surface which the mess is on top of based on the sensor data;
determining a cleaning mode for the autonomous vacuum based on the determined mess type and the surface type; and
instructing an actuator assembly to engage a sweeping assembly or a mopping assembly corresponding to the determined cleaning mode.
18 . The method of claim 17 , wherein determining the cleaning mode based on the mess type comprises selecting the sweeping mode for a dry mess type and selecting the mopping mode for a wet mess type.
19 . The method of claim 17 , wherein the mess type is determined by extracting features from real-time visual data captured by a camera or an infrared system.
20 . The method of claim 17 , wherein instructing a first set of actuators to engage the sweeping assembly is a different set of actuators from a set of actuators to engage the mopping assembly.