Serving Innovation: Seamless Service by Advancing Food Runners with Mobile Manipulation
Sankalp Yamsani, Kevin Gim, Tyler Smithline, Richard Qiu, Roman Mineyev, Kenta Hirashima, Sungmin Kang, Kyungseo Park, Yoon-Koo Kang, Seulbi An, SungHwan Ahn, Joohyung Kim
AI summary
Problem
Current food delivery robots lack manipulation capabilities and still require human intervention for retrieval and placement, limiting their autonomy and utility in dynamic environments like restaurants.
Approach
The authors developed MOMO, a modular mobile manipulator built on a standard serving robot base, featuring three pluggable ports for arms or sensors and independent motorized shoulder lifts to expand vertical reach and workspace.
Key results
- Plug-and-play modular torso with three independent mounting ports
- Independent linear shoulder lifts enabling multi-level manipulation
- CoM-aware ZMP motion controller preventing tipping during dynamic maneuvers
- Validated positioning accuracy (≤10 mm RMSE) and autonomous task adaptation
Why it matters
Enables restaurant and service industries to upgrade existing delivery fleets into fully autonomous manipulators, reducing labor costs and expanding operational capabilities.
Abstract
The Mobile Object Manipulation Operator (MOMO) is an innovative and reconfigurable robotic system that transforms traditional serving robots into mobile manipulators. Leveraging the form factor and mobility of serving robots, MOMO integrates up to three pluggable devices, including six-DoF manipulators of varying sizes or a three-DoF sensor head. Its design incorporates two independent shoulder lifts to enhance vertical reach. The adaptability of the system tailors its capabilities to tasks beyond simple object transportation. As opposed to current food delivery robots, MOMO showcases its ability to remove obstructions from the floor and deliver items to recipients without human intervention.