Robotic vehicle decontaminator

Abstract

Aspects of the disclosure are directed towards decontamination of a target object. A method includes a device registering a target object by identifying corresponding pairs of data points from the first set of data points of the three-dimensional representation and a second set of data points associated with a reference three-dimensional representation. The device localizes a position of the target object with respect to a position of a robotic arm based at least in part on the three-dimensional representation. The device generates a set of waypoints based on a subset of the first set of data points, the waypoints being arranged on the three-dimensional representation. The device determining a first path for the robotic arm to traverse over the surface of the target object based on the waypoints. The device receives a location on the surface of the target object that comprises a contaminant.

What is claimed is: 
     
         1 . A method performed by a robotic system, the method comprising:
 generating, based on sensor data generated by a robotic system, a three-dimensional representation of a surface of a target object, the three-dimensional representation comprising a first set of data points;   localizing the target object in a coordinate system of the robotic system;   generating waypoints based on a subset of the first set of data points, the waypoints being arranged on the three-dimensional representation;   determining a path for an end effector of the robotic system to traverse over the surface based on the waypoints, the end effector mounted on a robotic arm of the robotic system;   determining a trajectory for the robotic arm to traverse based on the path; and   initializing a movement of the robotic arm based on the trajectory.   
     
     
         2 . The method of  claim 1 , wherein generation of the three-dimensional representation comprises:
 emitting a laser pulse toward the target object from a sensor arranged on the robotic arm;   collecting a reflection signal from a point on the surface of the target object, the reflection signal being based on the laser pulse; and   calculating a distance between the robotic arm and the point on the surface of the target object based on a time elapsed between emitting the laser pulse and the collecting the reflection signal.   
     
     
         3 . The method of  claim 1 , wherein determining the path comprises using an optimization technique to identify a minimum length between a first waypoint of the waypoints and a second waypoint of the waypoints. 
     
     
         4 . The method of  claim 3 , wherein the optimization technique is constrained to find a solution in which the first waypoint is to be visited before the second waypoint based on a position of the first waypoint relative to the second waypoint. 
     
     
         5 . The method of  claim 1 , wherein determining the trajectory comprises:
 determining a pose of the robotic arm at the end of the trajectory;   determining a movement of a component of the robotic arm to reach the pose using an inverse kinematic technique;   generating the trajectory based on the movement;   comparing the trajectory to a collision data to determine whether the trajectory results in a collision with the target object; and   determining the trajectory based on the comparison of the trajectory to the collision data.   
     
     
         6 . The method of  claim 1 , wherein the method further comprises:
 identifying a location on the surface of the target object comprising a contaminant; and   determining the trajectory based on the identification of the contaminant.   
     
     
         7 . The method of  claim 6 , wherein the method further comprises determining a local trajectory for a tool connected to the robotic arm to move along while dispensing or applying a decontamination solution on the location on the surface of the target object comprising the contaminant. 
     
     
         8 . The method of  claim 7 , wherein the method further comprises verifying that the location on the surface of the target object has been decontaminated. 
     
     
         9 . A robotic system comprising:
 a robotic arm;   an end effector connected to the robotic arm;   a transport platform;   a memory configured to store computer-executable instructions; and   one or more processors configured to access the memory and execute the computer-executable instructions to cause the robotic system to:   generate, based on sensor data generated by a robotic system, a three-dimensional representation of a surface of a target object, the three-dimensional representation comprising a first set of data points;   localize the target object in a coordinate system of the robotic system;   generate waypoints based on a subset of the first set of data points, the waypoints being arranged on the three-dimensional representation;   determine a path for an end effector of the robotic system to traverse over the surface based on the waypoints, the end effector mounted on a robotic arm of the robotic system;   determine a trajectory for the robotic arm to traverse based on the path; and   initialize a movement of the robotic arm based on the trajectory.   
     
     
         10 . The robotic system of  claim 9 , wherein localizing the target object in the coordinate system of the robotic system comprises:
 retrieving a reference point cloud of a surface of a reference target object;   matching the reference point cloud to the generated three-dimensional representation, wherein the generated three-dimensional representation is a generated point cloud; and   localizing the target object in the coordinate system of the robotic system based on the matching.   
     
     
         11 . The robotic system of  claim 9 , wherein localizing the target object in the coordinate system of the robotic system comprises:
 retrieving a reference model of a surface of a reference target object;   matching the reference model to the generated three-dimensional representation, wherein the generated three-dimensional representation is a generated model; and   localizing the target object in the coordinate system of the robotic system based on the matching.   
     
     
         12 . The robotic system of  claim 9 , wherein localizing the target object in the coordinate system of the robotic system comprises:
 arranging a set of synthetic markers on the surface of the target object;   scanning the target object to determine a respective location of each synthetic marker of the set of synthetic markers and a respective distance between the robotic system and each marker of the set of the set of synthetic markers; and   localizing the target object in the coordinate system of the robotic system based on the respective location of each synthetic marker of the set of synthetic markers and the respective distance between the robotic system and each marker of the set of the set of synthetic markers.   
     
     
         13 . The robotic system of  claim 9 , wherein a density of the waypoints is based on the surface of the target object, a size of the target object, or a projected contaminant. 
     
     
         14 . The robotic system of  claim 9 , wherein determining the path comprises using an optimization technique to identify a minimum length between a first waypoint of the set of waypoints and a second waypoint of the set of waypoints. 
     
     
         15 . The robotic system of  claim 14 , wherein the optimization technique is constrained to find a solution in which the first waypoint is to be visited before the second waypoint based on a position of the first waypoint relative to the second waypoint. 
     
     
         16 . The robotic system of  claim 14 , wherein the trajectory is a first trajectory, and wherein the one or more processors configured to access the memory and execute the computer-executable instructions to further cause the robotic system to:
 detect a contaminant on the surface of the target object along the first trajectory;   storing an identity of a closest waypoint to the contaminant; and   determining a second trajectory to guide a tool to the closest waypoint, wherein the path is determined via inverse kinematics and configured to avoid collisions with the target object.   
     
     
         17 . The robotic system of  claim 16 , wherein the one or more processors configured to access the memory and execute the computer-executable instructions to further cause the robotic system to verify that contaminant has been removed in response to the tool applying or dispensing a decontamination solution on the contaminant. 
     
     
         18 . The robotic system of  claim 16 , wherein the one or more processors configured to access the memory and execute the computer-executable instructions to further cause the robotic system to generate a local trajectory about the closest waypoint for the tool follow while applying or dispensing a decontamination solution on the contaminant. 
     
     
         19 . A non-transitory computer-readable medium including stored thereon instructions that, that when executed by a processor, cause the processor to:
 generating, based on sensor data generated by a robotic system, a three-dimensional representation of a surface of a target object, the three-dimensional representation comprising a first set of data points;   localize the target object in a coordinate system of the robotic system;   generate waypoints based on a subset of the first set of data points, the waypoints being arranged on the three-dimensional representation;   determine a path for an end effector of the robotic system to traverse over the surface based on the waypoints, the end effector mounted on a robotic arm of the robotic system;   determine a trajectory for the robotic arm to traverse based on the path; and   initialize a movement of the robotic arm based on the trajectory.   
     
     
         20 . The non-transitory computer-readable medium of  claim 19 , wherein the instructions that, that when executed by a processor, further cause the processor to:
 emit a laser pulse toward the target object from a sensor arranged on the robotic arm;   collect a reflection signal from a point on the surface of the target object, the reflection signal being based on the laser pulse; and   calculate a distance between the robotic arm and the point on the surface of the target object based on a time elapsed between emitting the laser pulse and the collecting the reflection signal.