Competition

Dialogue robot competition 2022 is the first international competition for the communication capability of conversational robots. A very human-like android robot is used. The competition has two rounds, a preliminary round and the final round. At IROS, the top teams in the preliminary round will compete to decide the winning team.

The task for the robot is to recommend tourist spots around a certain facility. The robot needs to use language, gestures, and other multimodal behavior in order to make the user interested in the recommended spots. In the preliminary round, the conversational robot of each team is placed in a shopping mall or at a public facility, where the people visiting these places talk to the robot and evaluate its performance by questionnaire. In the final round at the IROS venue, designated dialogue researchers as well as those working in the tourist industry talk to the robot for evaluation. Through this event, we can cultivate knowledge as to how a dialogue robot should provide dialogue service in the future.

Chairs:

• Ryuichiro Higashinaka (Professor, Nagoya University, Japan)
• Takashi Minato (Team leader, RIKEN Guardian Robot Project, Japan)
• Hiromitsu Nishizaki (Associate professor, University of Yamanashi, Japan)
• Takayuki Nagai (Professor, Osaka University, Japan)

https://sites.google.com/view/drc2022

This competition evaluates how well intelligent robots can engage in natural and friendly communication with users and achieve various support behaviors in daily-life environments. The competition is designed based on the SIGVerse simulator, which enables robots to make embodied and social interactions in virtual reality (VR) environments. Competitors submit their software of service robot on AWS (Amazon Web Service). Human test subjects in the real space interacts with a robot in the virtual space to evaluate the interactive support ability. By discussing and examining the fusion and interface between robotics and the metaverse, digital twin, and cyber-physical systems that have been attracting attention in recent years, we believe that this event will provide a valuable opportunity to explore the direction of further development in robotics research.

• Tetsunari Inamura (National Institute of Informatics, Japan)
• Yoshiaki Mizuchi (Tamagawa Univ., Japan)

https://sites.google.com/view/robocup-athome-sim/competition-at-iros2022

This challenge aims to develop technologies to automate the stocking of products and the collection of expired items in a convenience store. Participants in this competition will develop a robot system that autonomously moves and performs these tasks, as well as the infrastructure they deem necessary to install inside the convenience store. In this challenge, the participants will use their developed robots and infrastructure to compete in stock and disposal demonstrations inside a simulated convenience store.

The following tasks will be performed in the demonstration:

• Stock task: Place the products stored in the container into the designated place on the display cases.
• Disposal task: Straighten the products already placed in a display case, collect the disposal items.

Chairs:

• Kazuyoshi Wada (Tokyo Metropolitan University)
• Kenichi Ohara (Meijo University)

https://f-csc.org/2022-wrs-fcsc/

This competition consists of two tracks, a service robotics track and a manufacturing robotics track. The service robotics track consists of several tasks with the ultimate goal for the competing robot system to autonomously create a table setting for four. The manufacturing track consists of several manufacturing assembly tasks with the goal of supporting the advancement of robotic systems for variable small-batch production runs.

Char:

• Yu Sun (Berk Calli, Joseph Falco, Cindy Grimm, Kenny Kimble, Maximo A. Roa, Yasuyoshi Yokokohji)

https://rpal.cse.usf.edu/rgmc_iros2022/

1st task: the robot should balance its weight immovable, carrying an additional weight of 500 gr (a plastic bottle of water) on a completely flat surface. The robot will have 2 opportunities to balance and the total time of the effort could be up to 3mins. The point it earns is one point/sec and it doesn’t count after the 3 mins of the effort.

2nd task: the robot should be balanced on an inclined ramp, at least 15o, without the bottle. The robot will have 2 opportunities to balance and the total time of the effort could be up to 3mins. The point it earns is two points/sec and it doesn’t count after the 3 mins of the effort.

3rd task: the robot should carry a bottle of 500 gr at a distance of 1m, on a completely flat surface. It has 100 seconds to complete the task. It earns one point per second, for the remaining time until the completion of 100 seconds.

In each of the two first task, the user gives the sign for start, while at the 3rd task the start and finish point will be designed on the ground.

Chair:

• Ergina Kavallieratou

https://icsdweb.aegean.gr/aegeanrbtcs/competion_IROS

　　

The METRICS HEART-MET (Healthcare Robotics Technologies – Metrified) Assistive Robot Challenge targets robots operating in a healthcare or domestic environment in an assistive capacity.

The competition will take place online and will consist of two rounds, each of which targets three benchmarks.

The benchmarks are 1) Activity Recognition, 2) Gesture Recognition, and 3) Handover Failure Detection, all of which are important skills for an assistive robot that interacts with humans.

The first round will be conducted using datasets, and the second round will be evaluated by execution on a remotely accessible robot.

The competition will tentatively start in August, and end during IROS in October. The exact schedule will be announced later.

Chairs:

• Nico Hochgeschwender (Hochschule Bonn-Rhein-Sieg)
• Praminda Caleb-Solly (University of Nottingham)
• Mauro Dragone (Heriot-Watt University)
• Filippo Cavallo (University of Florence)
• Santosh Thoduka (Hochschule Bonn-Rhein-Sieg)

https://metricsproject.eu/healthcare/2022-cascade-campaign/

The development of mobile manipulators increases significantly, and we see first real-life installations, specifically in the manufacturing industry. However, the realworld environment constraint cannot be sufficiently solved in many cases, limiting these systems’ utility. Thus, although also manufacturers see the promises of these systems, many possible use cases from manufacturing practice are still not
easily feasible.

IMMC will deal with this problem with participants treating industrial-related roblems and making progress into the field of human-machine co-working topics with manufacturing to positively influence the mobile manipulator development. At IROS2022, heterogeneous teams from different countries will compete in virtual exercises using a prefabricated mobile manipulator by means of ROS and Gazebo to solve a real industry problem.

The participants need some knowledge in the area of robotics but will be supported by professionals and learning material to solve the problem in time. Each participating team will present their solution to this challenge at the end of the day, followed by an award ceremony.

Chairs:

• Doris Aschenbrenner (Aalen University, TU Delft)
• Ing. Dipl.-Ing. Sebastian Schlund (TU Wien)
• Maximilian Papa (TU Wien)
• Matteucci Matteo (Politecnico di Milano)
• Manuel Silva (Instituto Politecnico do Porto, INESC TEC Porto)

This competition is designed to test the capabilities of learning-based robot decision-making algorithms to safely cope with events or uncertainties that are not known at design time. The task we consider is based on a nano quadrotor platform (Bitcraze’s Crazyflie). The quadrotor is required to navigate, as fast as possible, through an environment with a set of obstacles. Uncertainties the quadrotor may encounter include model uncertainties (e.g., parametric uncertainty in the robot’s mass and inertia), stochastic initial conditions, and external disturbances applied to states, inputs (e.g., noisy or biased sensing and actuation), and to the dynamics (e.g., wind). The participating teams are required to show that their algorithms can safely navigate the quadrotor through increasingly cluttered environments and can learn to cope with uncertainties.

The task execution is considered unsafe if it violates any of the safety constraints (e.g., violating a minimum safety distance from the obstacles, flying too close to the ground, leaving the boundaries of the flight arena, etc.). The evaluation criteria will be based on (1) the robot’s task performance (e.g., measured by its task completion time), (2) the satisfaction of the safety constraints, and (3) the maximal level of clutteredness in the environment that the algorithm can withstand.

The competition includes two simulation phases (virtual) and one experimental phase (through remote access). The fully virtual simulation components of the competition will be based on an open-source software benchmark suite. In the final experimental phase of the competition, we will provide remote access to our Flight Arena at the University of Toronto Institute for Aerospace Studies in Toronto, Canada.

Chairs:

• Angela Schoellig (University of Toronto, Vector Institute)
• Davide Scaramuzza (University of Zurich)
• Vijay Kumar (University of Pennsylvania)
• Nicholas Roy (Massachusetts Institute of Technology)
• Todd Murphey (Northwestern University)
• Sebastian Trimpe (RWTH Aachen University)
• Wolfgang Hönig (TU Berlin)
• Mark Muller (University of California Berkeley)
• Jose Martinez-Carranza (INAOE)
• SiQi Zhou (University of Toronto, Vector Institute)
• Melissa Greeff (University of Toronto, Vector Institute)
• Jacopo Panerati (University of Toronto, Vector Institute)
• Yunlong Song (University of Zurich)
• Leticia Oyuki Rojas Pérez (INAOE)
• Adam W. Hall (University of Toronto, Vector Institute)
• Justin Yuan (University of Toronto, Vector Institute)
• Lukas Brunke (University of Toronto, Vector Institute)
• Antonio Loquercio (UC Berkeley)

https://www.dynsyslab.org/iros-2022-safe-robot-learning-competition/

To facilitate the deployment of robust autonomous vehicles systems, we introduce the SeasonDepth Prediction Challenge as the first open-source challenge focusing on depth prediction performance under different environmental conditions for lifelong trustworthy autonomy in the application of outdoor mobile robotics and autonomous driving.

Chair:

• Hanjiang Hu

https://seasondepth.github.io/

More details will be updated for IROS 2022 after May.