Please fill out the application form here to participate in RGMC 2026. Application deadline: February 9th, 2026 for full consideration. We will continue receiving applications after that date and may consider them based on the availability of the participant spots and the readiness of the solution.If you have any questions, please email bcalli@wpi.edu.

Please see general competition rules here.

RGMC 2026 Tracks

• TRACK 1: Human-to-Robot Handover

The teams will be challenged to design solutions that enable a robot to estimate the physical properties of an object while handed over by a person. The robot then will need to complete the handover by safely and stably receiving the object and delivering it to a predefined location on the table.
Further details, visit: https://corsmal.github.io/events/rgmc/icra2026/ (see also past two editions at ICRA 2024 and ICRA 2025)

• TRACK 2: Picking from Clutter 

The Picking in Clutter track challenges teams to design robotic solutions capable of picking and placing objects from a cluttered environment. Given a mix of known and unknown objects randomly placed inside a transparent box, a robotic arm must pick each object and place it into a second transparent box within a specified time limit, fully clearing the initial box. An additional layer of complexity is introduced by enforcing a predefined grasping order. Teams must adhere to a commanded grasp sequence communicated via a ROS topic or service, emulating PLC-style communication commonly found in industrial settings. As a result, teams must develop advanced strategies such as pushing for decluttering and actively searching for target objects within cluttered scenes.

The goal of this track is to advance the design of vision and manipulation systems capable of handling heterogeneous and novel objects with diverse physical properties under challenging cluttered conditions, particularly in sequential bin-picking scenarios.

Further details: This track corresponds to Stage 3 of the Cluttered Environment Picking Benchmark (CEPB), as described in the reference paper below. Additional information is available on the CEPB website: http://cepbbenchmark.eu/. See also the two past editions at ICRA 2025 and ICRA 2024)

Primary contact: Salvatore D'Avella, salvatore.davella@santannapisa.it

Reference benchmarking protocol: The cluttered environment picking benchmark (CEPB) for advanced warehouse automation: evaluating the perception, planning, control, and grasping of manipulation systems S. D'Avella, M. Bianchi, A. M. Sundaram, C. A. Avizzano, M. A. Roa, P. Tripicchio, IEEE Robotics and Automation Magazine, 2023, https://doi.org/10.1109/MRA.2023.3310861 

• TRACK 3: Mobile Manipulation 

The Mobile Manipulation Track challenges teams to develop integrated robotic solutions that combine manipulation, navigation, and perception on a single platform. Teams will work with a mobile manipulator provided on site—the PAL Robotics TIAGo Pro—a bimanual mobile manipulator equipped with an omnidirectional drive base, designed to support autonomous mobility and dexterous interaction in structured environments. During the challenge, the robot must autonomously navigate between multiple workstations, perform precise docking, and execute an industrially inspired assembly task based on the NIST Assembly Task Boards. Successful completion of the task requires accurate positioning and tightly coordinated manipulation. The task environment encourages the use of advanced manipulation strategies, including coordinated two-arm operation, object hand-offs, and part stabilization during assembly, while still allowing teams flexibility in their approach. In addition to task execution, teams will demonstrate positioning and pose accuracy through standardized evaluation procedures conducted at both the beginning and end of each run. Overall, the track is designed to highlight the versatility, robustness, and adaptability of mobile manipulators in real-world industrial manufacturing scenarios. To support development and preparation, participating teams will be granted access to a practice version of the task setup prior to the competition.

For more information, please see https://pal-robotics.com/event/icra-2026-rgmc/.

• TRACK 4 Cloud Robotics 

Reams will focus on developing robust manipulation solutions using remote access to the cloud robotics platform CloudGripper (cloudgripper.org) at KTH Royal Institute of Technology, where a set of small robotic arm cells will be made available for competing teams to develop and evaluate their solutions. This year's cloud robotics track will focus on two manipulation challenges: a) planar pushing of a variety of objects and b) shape control of linear deformable objects with varying physical properties. More information will be available soon. 

Further details at cloudgripper.org/icra2026. 

Exciting news! Mathworks will provide free Matlab licenses to the RGMC participants! Once your participation is approved, please get in touch with Berk Calli (bcalli@wpi.edu) to start the process.

Photos from the Previous Competition

Organizers