Abstract: The embodiments of the disclosure provide a space recognition method, an electronic device and a non-transitory computer-readable storage medium. The method includes the following steps. Sensor data for detecting obstacle positions is obtained from a sensor associated with an electronic device. A plurality of coordinates respectively corresponding to the obstacle positions are generated based on the sensor data. Boundary line information of a space surrounding the electronic device is updated according to the coordinates until an optimization condition is met for each boundary line. A spatial range of the space surrounding the electronic device is identified based on the boundary line information. The spatial range is used to guide a movement of the electronic device.

Abstract: Disclosed are a trapped state detection method and a mobile platform. The trapped state detection method is applied to the mobile platform including an actuator, and includes: selectively acquiring first signal characteristic or second signal characteristic in an external environment in a process in which the actuator drives the mobile platform to move; determining whether an abnormality occurs according to the first signal characteristic acquired in a first default time interval; controlling the actuator to perform a default verification behavior to change a position or a posture of the mobile platform when an occurrence of the abnormality is determined; determining whether another abnormality occurs according to the first signal characteristic or the second signal characteristic acquired in a second default time interval after the actuator performs the default verification behavior; and confirming that the mobile platform is in a trapped state when an occurrence of the another abnormality is determined.

Abstract: Disclosed are a method for simultaneous localization and mapping and a mobile platform using the same. The method for simultaneous localization and mapping is applied to the mobile platform, and includes: continuously collecting and storing odometer data and environment sensing data of the mobile platform when the mobile platform moves based on a motion trajectory; combining a certain amount of the odometer data and the environmental sensing data to obtain environmental information whenever the certain amount of odometer data and environmental sensing data is reached and stored; performing a simultaneous localization and mapping procedure according to a current map and the odometer data and environmental information continuously obtained; repeating the above steps until the mobile platform completes the motion according to the motion trajectory. Therefore, the mobile platform can synthesize the environmental information similar to sensing data of the lidar while moving without installing a high-cost lidar.

Abstract: The invention relates to a cleaning robot and a material identification method thereof, which is suitable for cleaning robots. The cleaning robot is pre-set with a threshold comparison table and comprises a plurality of comparison thresholds, wherein each comparison threshold defines an interval of accumulated energy information accumulated by the moving plane of different materials within a predetermined period of time. The cleaning robot generates accumulated energy information during the movement, so that the cleaning robot can find the comparison threshold corresponding to the accumulated energy information from the threshold comparison table, and then determines the material of the moving plane contacted by the cleaning robot.

Abstract: The embodiments of the disclosure provide a space recognition method, an electronic device and a non-transitory computer-readable storage medium. The method includes the following steps. Sensor data for detecting obstacle positions is obtained from a sensor associated with an electronic device. A plurality of coordinates respectively corresponding to the obstacle positions are generated based on the sensor data. Boundary line information of a space surrounding the electronic device is updated according to the coordinates until an optimization condition is met for each boundary line. A spatial range of the space surrounding the electronic device is identified based on the boundary line information. The spatial range is used to guide a movement of the electronic device.

Abstract: The invention relates to a cleaning robot and a material identification method thereof, which is suitable for cleaning robots. The cleaning robot is pre-set with a threshold comparison table and comprises a plurality of comparison thresholds, wherein each comparison threshold defines an interval of accumulated energy information accumulated by the moving plane of different materials within a predetermined period of time. The cleaning robot generates accumulated energy information during the movement, so that the cleaning robot can find the comparison threshold corresponding to the accumulated energy information from the threshold comparison table, and then determines the material of the moving plane contacted by the cleaning robot.

Abstract: A cleaning path guidance method combined with a dirt detection mechanism is performed in an automatic cleaning device to generate a cleaning path, so as to guide the automatic cleaning device to clean an area to be cleaned, in which plural grids are defined in the area. The method includes: moving the automatic cleaning device in the area to clear dirt away, and continuously detecting a flow of the dirt cleared away to obtain a dirt level of a current gird; if the dirt level of the current gird exceeds a threshold, marking the grid as a dirty grid; performing an algorithm and finding a shortest path passing through all dirty grids as a cleaning path according to the marked dirty grids; and moving the automatic cleaning device to pass through each dirty grid according to the clean path, so as to clean each dirty gird sequentially.

Abstract: A cleaning robot including a roller unit, a sensing unit, a first control unit and a second control unit is disclosed. The roller unit includes a plurality of rollers. The sensing unit receives a reflection signal and generates a detection signal according to the reflection signal. When the detection signal is less than or equal to a reference signal, the first control unit controls the traveling direction of the rollers according to the detection signal such that a distance between the cleaning robot and a wall is equal to a first distance. When the detection signal is larger than the reference signal, the second control unit controls the traveling direction of the rollers according to the detection signal such that a distance between the cleaning robot and a wall is equal to a second distance larger then the first distance.

Abstract: A cleaning system is provided. The cleaning system includes at least one sign object and a cleaning robot. The cleaning robot detects and records a position of the sign object to generate a recorded result. The cleaning robot has a locking function. When the locking function has been activated, the cleaning robot performs a cleaning operation according to the recorded result. When the locking function has been activated and the sign object has been removed, the cleaning robot is capable of performing the cleaning operation according to the position of the sign object before it was removed.

Abstract: A cleaning system including a first virtual wall, a second virtual wall and a cleaning robot is disclosed. The first virtual wall includes a first specific pattern. When a light emits the first specific pattern, a first specific reflected light is generated. The second virtual wall includes a second specific pattern. When the light emits the second specific pattern, a second specific reflected light is generated. The cleaning robot, based on the first and the second specific reflected lights, obtains and records positions of the first and the second virtual walls. The cleaning robot defines a first virtual line according to the recorded positions. A traveling path of the cleaning robot is limited by the first virtual line.

Abstract: A cleaning path guidance method combined with a dirt detection mechanism is performed in an automatic cleaning device to generate a cleaning path, so as to guide the automatic cleaning device to clean an area to be cleaned, in which plural grids are defined in the area. The method includes: moving the automatic cleaning device in the area to clear dirt away, and continuously detecting a flow of the dirt cleared away to obtain a dirt level of a current gird; if the dirt level of the current gird exceeds a threshold, marking the grid as a dirty grid; performing an algorithm and finding a shortest path passing through all dirty grids as a cleaning path according to the marked dirty grids; and moving the automatic cleaning device to pass through each dirty grid according to the clean path, so as to clean each dirty gird sequentially.

Abstract: A cleaning robot including a roller unit, a sensing unit, a first control unit and a second control unit is disclosed. The roller unit includes a plurality of rollers. The sensing unit receives a reflection signal and generates a detection signal according to the reflection signal. When the detection signal is less than or equal to a reference signal, the first control unit controls the traveling direction of the rollers according to the detection signal such that a distance between the cleaning robot and a wall is equal to a first distance. When the detection signal is larger than the reference signal, the second control unit controls the traveling direction of the rollers according to the detection signal such that a distance between the cleaning robot and a wall is equal to a second distance larger then the first distance.