Human-to-Robot Handovers

The competition will be held in Atlanta on Thursday May 22. Teams will execute the human-to-robot handover configurations with unknown objects that organizers will provide on-site only once.


Objects

The set of objects for the competition consists of 6 containers that are unknown to the teams to test the generalisation capabilities of the system to adapt to novel and unseen objects. These containers may range between drinking cups and food containers. These containers may be filled with a content different from rice and with a different amount from the set used for the qualification phase.


Logistics
  • Teams are expected to bring their own setup. This includes robotic arm, end effector (e.g., 2-finger gripper, such as Robotiq), laptop/workstation (tower PC with monitor), cameras (with tripods, USB-C cables), digital scale, calibration pattern, sockets extension lead, ethernet cable connecting PCs and robotic arm, socket adapter.
  • Teams are expected to mount their own setup configuration.
  • For safety, a second person (e.g., from the team) must be ready to stop the robot in case of an anomalous behaviour.
  • See setting up instructions for more details on how to prepare your setup at the conference site.
  • WiFi on the conference site might be unstable and unreliable. We encourage teams to take this aspect in account when designing their solution if calls to API via the Internet is needed.
  • We remind teams that illumination conditions can differ at the conference site and hence affecting the perception system.
Shipping information

RGMC is assigned to Booth # C03.
Please use booth # if you need to ship to Atlanta or order any additional services/equipment.

Further information and all additional services can be found here.


Procedure
The following are instructions for each handover configuration (predefined combination of a container with a content type and amount).

For the operator (or second team member)
Before starting the handover configuration:
  1. Prepare the container either empty or filled with its predefined content type and amount
  2. Weight the (filled) container before the execution of the task
  3. Place the container at the centre of the table, at a distance not reachable by the robotic arm (safety)
After the handover configuration is executed:
  1. Measure the distance between the initial and the delivery location of the container (if not failed)
  2. Weight the (filled) container after the execution of the task
  3. Report the measures in the .csv file to submit for evaluation (including handover timing)
During the handover execution:
  • Controls the start and end of the robotic control and perceptions
  • Ready to stop the robot in case of an anomalous behaviour
For the volunteer
During the handover execution:
  1. The volunteer grasps the container from its location with a natural grasp
  2. The volunteer carries the container with the intention of handing it over to the robot
  3. The robot should track and predict the pose of the container to move the arm towards the handover area
  4. The volunteer hands the container over to the robot
  5. The robot closes the end effector and grasps the container
  6. The robot delivers the container upright within the predefined area.

Note that the volunteer should avoid assisting the robot (i.e., remaining still at a location until the robot can pick up the container) or assuming an adversarial behaviour (i.e., making it harder for the robot to reach the object).
The handover is supposed to be dynamic: robot starts moving and approaching as soon as the volunteer grasps the container.

This procedure has been revised from the CORSMAL Human-to-Robot Handover Protocol document.



Submission
After completing the set of configurations, teams will send a .csv file with the results for each configuration by email.
Template for submitting the results: here.
The .csv file must be named according to the following format: rgmc-icra2025_handovers_teamname_vX.csv (replace teamname with the name of your team, and X with the submission number).

For each configuration, the file must provide the results for the following columns:
  • Target location [mm]: the position (x,y) where the robot should deliver the object. We recommed to provide a picture clearly showing the location of this point.
  • Final location [mm]: the position (x,y) of the centre of the base of the container at the end of the task.
  • Handover time [ms]: the total execution time from the moment the person is instructed to grasp the container to the moment the robot releases the gripper at the delivery location to place the container after the handover (unless the handover failed)
  • Initial mass [g]: the measured mass of the (filled) container before the execution of the configuration.
  • Final mass [g]: the measured mass of the (filled) container after the execution of the configuration.

Organizers will provide the set of handovers configurations to fill the submission file on the competition day.