Generating machine-executable plans from end-user's natural-language instructions
This addresses the NL-based human-machine communication problem in advanced manufacturing, enabling machines to execute tasks from end-user instructions, though it appears incremental as it builds on existing semantic analysis and parameter specification techniques.
The researchers tackled the problem of machines misunderstanding ambiguous natural language instructions by developing the exePlan method, which generated machine-executable plans and was proven effective in experiments with an industrial robot performing tasks like drilling and cleaning.
It is critical for advanced manufacturing machines to autonomously execute a task by following an end-user's natural language (NL) instructions. However, NL instructions are usually ambiguous and abstract so that the machines may misunderstand and incorrectly execute the task. To address this NL-based human-machine communication problem and enable the machines to appropriately execute tasks by following the end-user's NL instructions, we developed a Machine-Executable-Plan-Generation (exePlan) method. The exePlan method conducts task-centered semantic analysis to extract task-related information from ambiguous NL instructions. In addition, the method specifies machine execution parameters to generate a machine-executable plan by interpreting abstract NL instructions. To evaluate the exePlan method, an industrial robot Baxter was instructed by NL to perform three types of industrial tasks {'drill a hole', 'clean a spot', 'install a screw'}. The experiment results proved that the exePlan method was effective in generating machine-executable plans from the end-user's NL instructions. Such a method has the promise to endow a machine with the ability of NL-instructed task execution.