Automatic in-situ registration and calibration of robotic arm/sensor/workspace system

Abstract

Various technologies described herein pertain to automatic in-situ calibration and registration of a depth sensor and a robotic arm, where the depth sensor and the robotic arm operate in a workspace. The robotic arm can include an end effector. A non-parametric technique for registration between the depth sensor and the robotic arm can be implemented. The registration technique can utilize a sparse sampling of the workspace (e.g., collected during calibration or recalibration). A point cloud can be formed over calibration points and interpolation can be performed within the point cloud to map coordinates in a sensor coordinate frame to coordinates in an arm coordinate frame. Such technique can automatically incorporate intrinsic sensor parameters into transformations between the depth sensor and the robotic arm. Accordingly, an explicit model of intrinsics or biases of the depth sensor need not be utilized.

Description

Background technique [0001] Manipulation of objects can be a function of a large class of robotic systems (eg, manipulation systems). For example, a typical closed-loop manipulation system may include at least one optical sensor (e.g., a depth sensor) that senses and interprets a real-world scene and a physical manipulator (e.g., actuators, robotic arms, etc.). The ability to perform a useful task with a physical object may depend on the ability of a robotic arm to manipulate the object with sufficient accuracy for that task. This accuracy may depend on the mapping between the coordinate system of the depth sensor and the coordinate system of the robot arm. For example, a mapping may be created between coordinates extracted from a depth image generated by a depth sensor and the Cartesian position of the robot arm in the workspace. Such mapping between coordinate systems may also be referred to as registration. Precise and accurate mapping between depth sensors and robotic ...

AI Technical Summary

Problems solved by technology

According to yet another example, a robotic arm may have a less than ideal ability to achieve precise placement of the end effector of such a robotic arm at desired Cartesian coordinates

Also, depth sensors or robotic arms (even those from the same vendor) may have slightly different biases, which can further complicate typical approaches for registration

Images