SwapBot system enables robots to quickly swap tools for everyday tasks
SwapBot: Tool-Centric Robot Manipulation via Interchangeable End-Effectors and Tactile Sensing
Robotics
Summary
Robots often need to use different tools to do everyday tasks like cooking, which involves cutting, stirring, or flipping. The authors built SwapBot, a robot hand system that can quickly change tools using simple adapters that have built-in touch sensors. This design lets robots handle many different household tools and work on various robots. They showed that using touch sensors helps robots learn to do these tasks better and faster, reducing the effort needed from human operators during teaching.
What this means in practice
- •For industrial automation teams: Equip robots to quickly switch and use common tools for diverse manufacturing tasks requiring contact and precision.
- •For restaurant kitchen staff: Enable robotic kitchen assistants to perform cooking tasks like stirring and flipping by swapping utensil tools autonomously.
Authors
Yunchu Zhang, Ray Song, Junhan Jiao, Liyiming Ke, Yuchen Yang, Ruihan Gao, Emma Romig, Siddhartha Srinivasa, Yiyue Luo
Abstract
Robot manipulation in everyday environments inherently involves substantial tool usage. Seemingly simple household tasks, such as cooking pan-fried tofu, require forceful cutting, delicate brushing, and precise placement using different tools under contact-rich interaction. Thus, the ability to autonomously swap and use task-appropriate tools is important for tool-centric manipulation. We introduce SwapBot, a modular, tool-centric end effector system featuring low-cost adapters that quickly convert common household tools into robot end effectors. Rather than pursuing a single universal gripper, SwapBot adopts a unified design principle that combines a fixed robot-side coupling interface with low-cost, tool-side adapters, enabling compatibility with diverse tools, including articulated ones, and multiple robot platforms. Each adapter integrates compact tactile sensors, supports fast autonomous swapping, and interfaces with an intuitive teleoperation system for efficient demonstration collection. User studies show that, during teleoperation, SwapBot reduces task completion time and operator workload. Using collected demonstrations on the robot, we train imitation learning policies to successfully perform tool-centric tasks like cooking tofu, stirring salad, flipping meat. Our ablation study shows that using tactile-augmented demonstrations improves policy performance across contact-rich skills, increasing success rates by 15 to 25 percentage points over RGB-only policies. These results highlight modular, tactile-equipped tools as a practical and extensible pathway toward robust and capable robot manipulation. Project website https://personalrobotics.github.io/SwapBot.