Dynamic vision system for robot fleet management
A dynamic vision system for robot fleet management includes an optical assembly including a lens containing a liquid. The lens is deformable to generate variable focus for the lens. The optical assembly is configured to capture optical data. The dynamic vision system includes a robot fleet management platform having a control system configured to adjust one or more optical parameters. The one or more optical parameters modify the variable focus of the lens while the optical assembly captures current optical data relating to a robotic fleet. The dynamic vision system includes a processing system configured to train a machine learning model to recognize an object relating to the robotic fleet using training data generated from the optical data captured by the optical assembly. The optical data includes the current optical data relating to the robotic fleet.
1 . A dynamic vision system for robot fleet management, comprising:
an optical assembly including a lens containing a liquid, wherein the lens is deformable to generate variable focus for the lens, and wherein the optical assembly is configured to capture optical data;
a robot fleet management platform having a control system configured to adjust one or more optical parameters, wherein the one or more optical parameters modify the variable focus of the lens while the optical assembly captures current optical data relating to a robotic fleet; and
a processing system configured to train a machine learning model to recognize an object relating to the robotic fleet using training data generated from the optical data captured by the optical assembly, wherein the optical data includes the current optical data relating to the robotic fleet, and wherein the optical data captured by the optical assembly includes optical data that is out-of-focus with respect to an object being optically captured by the optical assembly.
2 . The system of claim 1 , wherein the one or more optical parameters adjust the variable focus of the lens from a first focal state to a second focal state different than the first focal state, wherein the training data includes optical data captured in the first focal state, and wherein the training data incorporates feedback data such that the training data includes optical data captured in the first focal state and the second focal state.
3 . The system of claim 1 , wherein the recognition of the object relating to the robotic fleet is compared to a stored fleet resource configuration comprised of a plurality of objects.
4 . The system of claim 3 , wherein the comparison of the recognized object to the stored fleet resource configuration is quantified as a numeric score, and wherein the numeric score represents a degree of match between the recognized object and that object type's position in the stored fleet resource configuration.
5 . The system of claim 4 , wherein the numeric score is compared against a stored numeric score threshold, and wherein the stored numeric score threshold represents a minimum degree of match between the recognized object and that object type's position in the stored fleet resource configuration.
6 . The system of claim 5 , wherein the robot fleet management platform generates an alert upon detection of the numeric score not meeting or exceeding the stored numeric score threshold.
7 . The system of claim 1 , wherein the robot fleet management platform pauses robotic activity of at least one robotic apparatus upon detection of a numeric score not meeting or exceeding a stored numeric score threshold.
8 . The system of claim 1 , wherein the one or more optical parameters deform the lens from an original state by applying an electrical current to the lens.
9 . The system of claim 1 , wherein the one or more optical parameters adjust the variable focus of the lens at a predetermined frequency.
10 . A dynamic vision system for robot fleet management, comprising:
an optical assembly including a lens containing a liquid, wherein the lens is deformable to generate variable focus for the lens, and wherein the optical assembly is configured to capture optical data;
a robot fleet management platform having a control system configured to adjust one or more optical parameters, wherein the one or more optical parameters modify the variable focus of the lens while the optical assembly captures current optical data relating to a robotic fleet, and wherein the robot fleet management platform pauses robotic activity of at least one robotic apparatus upon detection of a numeric score not meeting or exceeding a stored numeric score threshold; and
a processing system configured to train a machine learning model to recognize an object relating to the robotic fleet using training data generated from the optical data captured by the optical assembly, wherein the optical data includes the current optical data relating to the robotic fleet.
11 . The system of claim 10 , wherein the robot fleet management platform generates an alert upon detection of the numeric score not meeting or exceeding the stored numeric score threshold.
12 . The system of claim 10 , wherein the optical data captured by the optical assembly includes optical data that is out-of-focus with respect to an object being optically captured by the optical assembly.
13 . The system of claim 10 , wherein the recognition of the object relating to the robotic fleet is compared to a stored fleet resource configuration comprised of a plurality of objects.
14 . The system of claim 13 , wherein the comparison of the recognized object to the stored fleet resource configuration is quantified as the numeric score, and wherein the numeric score represents a degree of match between the recognized object and that object type's position in the stored fleet resource configuration.
15 . The system of claim 10 , wherein the numeric score is compared against the stored numeric score threshold, and wherein the stored numeric score threshold represents a minimum degree of match between the recognized object and that object type's position in a stored fleet resource configuration.
16 . A computer-implemented method for robot fleet management, comprising:
capturing optical data using an optical assembly including a lens containing a liquid, wherein the lens is deformable to generate variable focus for the lens;
adjusting one or more optical parameters to modify the variable focus of the lens while the optical assembly captures current optical data relating to a robotic fleet;
generating training data from the optical data captured by the optical assembly, wherein the optical data includes the current optical data relating to the robotic fleet, and wherein the optical data captured by the optical assembly includes optical data that is out-of-focus with respect to an object being optically captured by the optical assembly; and
training a machine learning model to recognize an object relating to the robotic fleet using the training data.
17 . The method of claim 16 , further comprising comparing the recognition of the object relating to the robotic fleet to a stored fleet resource configuration including a plurality of objects, wherein the comparison of the recognized object to the stored fleet resource configuration is quantified as a numeric score, and wherein the numeric score represents a degree of match between the recognized object and that object type's position in the stored fleet resource configuration.
18 . The method of claim 16 , wherein the adjusting the one or more optical parameters to modify the variable focus of the lens includes modifying the variable focus of the lens from a first focal state to a second focal state different than the first focal state, wherein the training data includes optical data captured in the first focal state, and wherein the training data incorporates feedback data such that the training data includes optical data captured in the first focal state and the second focal state.
19 . A computer-implemented method for robot fleet management, comprising:
capturing optical data using an optical assembly including a lens containing a liquid, wherein the lens is deformable to generate variable focus for the lens;
adjusting one or more optical parameters to modify the variable focus of the lens while the optical assembly captures current optical data relating to a robotic fleet;
generating training data from the optical data captured by the optical assembly, wherein the optical data includes the current optical data relating to the robotic fleet;
training a machine learning model to recognize an object relating to the robotic fleet using the training data; and
pausing robotic activity of at least one robotic apparatus upon detection of a numeric score not meeting or exceeding a stored numeric score threshold.
20 . The method of claim 19 , further comprising comparing the recognition of the object relating to the robotic fleet to a stored fleet resource configuration including a plurality of objects, wherein the comparison of the recognized object to the stored fleet resource configuration is quantified as the numeric score, and wherein the numeric score represents a degree of match between the recognized object and that object type's position in the stored fleet resource configuration.
21 . The method of claim 19 , further comprising:
comparing the numeric score against the stored numeric score threshold, wherein the numeric score threshold represents a minimum degree of match between the recognized object and that object type's position in a stored fleet resource configuration; and
generating an alert upon the detection of the numeric score not meeting or exceeding the stored numeric score threshold.