Real-time natural language corrections for assistive robotic manipulators

We propose a generalizable natural language interface that allows users to provide corrective instructions to an assistive robotic manipulator in real-time. This work is motivated by the desire to improve collaboration between humans and robots in a home environment. Allowing human operators to modify properties of how their robotic counterpart achieves a goal on-the-fly increases the utility of the system by incorporating the strengths of the human partner (e.g. visual acuity and environmental knowledge). This work is applicable to users with and without disability. Our natural language interface is based on the Distributed Correspondence Graph, a probabilistic graphical model that assigns semantic meaning to user utterances in the context of the robot’s environment and current behavior. We then use the desired corrections to alter the behavior of the robotic manipulator by treating the modifications as constraints on the motion generation (planning) paradigm. In this paper, we highlight four dimensions along which a user may wish to correct the behavior of his or her assistive manipulator. We develop our language model using data collected from Amazon Mechanical Turk to capture a comprehensive sample of terminology that people use to describe desired corrections. We then develop an end-to-end system using open-source speech-to-text software and a Kinova Robotics MICO robotic arm. To demonstrate the efficacy of our approach, we run a pilot study with users unfamiliar with robotic systems and analyze points of failure and future directions.