This paper describes a novel methodology to reduce the effort in automating manual surface finishing processes by bridging the knowledge transfer gap of the manual operator's skills to a robot program. Key process variables (KPVs), i.e., contact force, tool path, and feed rate, of the manual operator performing the task are captured with a "sensorized" hand-held belt grinder, while the changes to the work-piece geometry is captured using a 3-D scanner. The entire manual tool-path strategy is segmented into its primitives or primary strategies before programming an equivalent robotic tool-path and strategy. The manual tool-path primitives are imported into computer-aided-manufacturing software where boundary splines are created to generate the robotic tool-paths. An analytical material removal rate (MRR) model is used to scale the extracted manual KPVs such that the parameters can be executed by the robotic platform, while still maintaining an equivalent material removal profile. In the first experimental trial with the designed robotic finishing strategy using this approach, the work-piece could be finished to within 0.7 mm of the desired shape. Note to Practitioners-This paper was motivated by the difficulty of automating manual grinding processes for complex shaped components. These processes would involve grinding a feature on the component to a freeform complex shape, where the final shape can be drastically different from the initial shape. The manual operators performing the manual grinding would be highly skilled in the process. Typically, many rounds of trial and error are required to arrive at a suitable set of grinding parameters and toolpath strategy. This paper describes a novel approach to tap on the skills and experience of the manual operator to generate a robot program for grinding the component to the desired geometry. A handheld grinding tool was modified to capture the motions, contact force and spindle speed. An algorithm is introduced to calculate the instantaneous contact points between the tool and the work-piece to determine the manual toolpath. Next, the manual toolpath is broken down into "bite sized" segments to generate its corresponding robotic toolpath. The robot may not be able to replicate the force and feed-rate parameters of the manual operator due to their different inertia and kinematic properties. Thus, an analytical model for simulating the material removal of the process is used to scale the captured manual operator parameters for the robot to execute. This methodology can be applied to other handheld grinding tools; the flexible contact grinding wheel is used as an example. In future research, a method to map the orientations of the hand-held tool to the orientations of the robotic tool will be developed.
