Naming Objects for Vision-and-Language Manipulation
This addresses a specific problem in robotics for human-robot interaction, but it is incremental as it builds on existing vision-and-language manipulation approaches.
The paper tackles the problem of interpretation ambiguity in robot manipulation tasks with natural language instructions by hypothesizing that naming target objects in advance reduces ambiguity. The result shows that their method increases the success rate of object manipulation tasks by 31% in ambiguous instructions.
Robot manipulation tasks by natural language instructions need common understanding of the target object between human and the robot. However, the instructions often have an interpretation ambiguity, because the instruction lacks important information, or does not express the target object correctly to complete the task. To solve this ambiguity problem, we hypothesize that "naming" the target objects in advance will reduce the ambiguity of natural language instructions. We propose a robot system and method that incorporates naming with appearance of the objects in advance, so that in the later manipulation task, instruction can be performed with its unique name to disambiguate the objects easily. To demonstrate the effectiveness of our approach, we build a system that can memorize the target objects, and show that naming the objects facilitates detection of the target objects and improves the success rate of manipulation instructions. With this method, the success rate of object manipulation task increases by 31% in ambiguous instructions.