Recent advancements in robotics have underscored the need for effective collaboration between humans and robots. Traditional interfaces often struggle to balance robot autonomy with human oversight, limiting their practical application in complex tasks like mobile manipulation. This study aims to develop an intuitive interface that enables a mobile manipulator to autonomously interpret user-provided sketches, enhancing user experience while minimizing burden. We implemented a web-based application utilizing machine learning algorithms to process sketches, making the interface accessible on mobile devices for use anytime, anywhere, by anyone. In the first validation, we examined natural sketches drawn by users for 27 selected manipulation and navigation tasks, gaining insights into trends related to sketch instructions. The second validation involved comparative experiments with five grasping tasks, showing that the sketch interface reduces workload and enhances intuitiveness compared to conventional axis control interfaces. These findings suggest that the proposed sketch interface improves the efficiency of mobile manipulators and opens new avenues for integrating intuitive human-robot collaboration in various applications.

To use assistive robots in everyday life, a remote control system with common devices, such as 2D devices, is helpful to control the robots anytime and anywhere as intended. Hand-drawn sketches are one of the intuitive ways to control robots with 2D devices. However, since similar sketches have different intentions from scene to scene, existing work requires additional modalities to set the sketches' semantics. This requires complex operations for users and leads to decreasing usability. In this paper, we propose Sketch-MoMa, a teleoperation system using user-given hand-drawn sketches as instructions to control a robot. We use Vision-Language Models (VLMs) to understand the user-given sketches superimposed on an observation image and infer drawn shapes and low-level tasks of the robot. We utilize sketches and the generated shapes for recognition and motion planning of the generated low-level tasks for precise and intuitive operations. We validate our approach using state-of-the-art VLMs with 7 tasks and 5 sketch shapes. We also demonstrate that our approach effectively specifies more detailed intentions, such as how to grasp and how much to rotate. Moreover, we show the competitive usability of our approach compared with the existing 2D interface through a user experiment with 14 participants. Our videos and results are available at this link.