The ever-changing nature of human environments presents great challenges to robot manipulation. Objects that robots must manipulate vary in shape, weight, and configuration. Important properties of the robot, such as surface friction and motor torque constants, also vary over time. Before robot manipulators can work gracefully in homes and businesses, they must be adaptive to such variations. This survey summarizes types of variations that robots may encounter in human environments and categorizes, compares, and contrasts the ways in which learning has been applied to manipulation problems through the lens of adaptability. Promising avenues for future research are proposed at the end.

No abstract

This paper presents the design and initial results of a project involving the robotic assembly of a large segmented structure. This project aims to develop an operator-guided semi-autonomous assembly process using industrial robots integrated with multiple sensors. The goal is to demonstrate the potential of robotic technology to reduce cycle time, enhance assembly quality, and improve worker ergonomics, as compared to the current manual or fixture-based approaches. The focus is primarily on the software framework which is composed of a collection of commercial and customized components for robot positioning, motion planning, low latency teleoperation, visualization and simulation. A foundation step of the implementation is safe teleoperation which allows the user to operate the robot without concern of collision or joint limits. The concept has been demonstrated in RobotStudio, the simulation environment for ABB robots, and a physical ABB robot. While some of the software is specific to the ABB industrial robot used in the project, the framework is readily adapted to other industrial robots that allow externally commanded motion.

No abstract