#ICRA2022 Competitions – Robohub

Photo credit: Wise Owl Multimedia

As one of many ICRA Science Communication Award Winner, I coated the digital points of ICRA 2022. IEEE International Conference on Robotics and Automation (ICRA) 2022 is completely one of the best robotics convention. It typically covers an unlimited vary of robotics together with however not restricted to notion, management, optimization, machine studying and application-robotics. In 2022, ICRA was held in Philadelphia, the place the U.S. declaration of independence was signed, for per week from May, twenty third to May, twenty seventh. This convention can be one of many first in-person conferences for roboticists after a few pandemic years. The convention had 7876 registered individuals, out of which 4703 individuals attended the convention in-person. You can entry the convention technical papers and presentation right here. There had been additionally workshops, competitions, plenary talks, boards and networking occasions. For extra particulars in regards to the convention, please confer with the convention official web site right here.

Due to journey points, I couldn’t attend ICRA 2022 in-person. Regardless, I’ve tried my greatest to share my expertise as a presenter and a digital attendee. While I can solely seize a few keypoints alongside the trajectory through the restricted time, I hope they’re true positives and generate a exact reconstruction of ICRA expertise, from a first-time ICRA presenter’s perspective.

Competitions

ICRA 2022 had 10 main competitions organized all through the convention week. In this text, let’s take a fast take a look at what challenges in robotics had been addressed through the organized competitions:

The BARN Challenge was designed for a robotic to navigate from a predefined begin pose to a purpose pose with minimal time whereas avoiding collisions. The robotic used 2D LiDAR for notion and a microcontroller with a most pace of 2m/s. During the competitors, the computation of the robotic was restricted to Intel i3 CPU with 16GB of DDR4 RAM. The competitors primarily used simulated BARN dataset (Perille et al., 2020), which has 300 pre-generated navigation environments, starting from simple open areas to tough extremely constrained ones, and an surroundings generator to generate novel BARN environments. The competitors allowed the taking part groups to make use of any navigation approaches, starting from classical sampling-based, optimization-based, end-to-end studying, to hybrid approaches.

General Place Recognition Competition was designed to improve visible and LiDAR state-of-the-art methods for localization in large-scale environments with altering situations reminiscent of variations in viewpoints and environmental situations (e.g. illumination, season, time of day). The competitors had two challenges based mostly on City-scale UGV Localization Dataset (3D-3D Localization) and Visual Terrain Relative Navigation Dataset (2D-2D Localization) to judge efficiency in each long-term and large-scale.

RoboMaster University Sim2Real Challenge was designed to optimize the system efficiency in real-world. Participants developed algorithms in a simulated surroundings and the organizers deployed the submitted algorithms in real-world. The competitors targeted on system efficiency together with notion, manipulation and navigation of the robotic.

RoboMaster University AI Challenge targeted on the appliance of a number of points of cellular robotics algorithm in an built-in context reminiscent of localization, movement planning, goal detection, autonomous decision-making and computerized management. The thought of the competitors was for the robots to shoot in opposition to one another within the rune-filled battlefield and to launch projectiles in opposition to different robots.

F1TENTH Autonomous Racing was desinged as an in-person competitors anticipating individuals to construct 1:10 scaled autonomous race automobile in accordance with a given specification and as a digital competitors to work on the simulation surroundings. The paricipating groups constructed the algorithms to finish the duty with no collisions and doable minimal laptime. This competitors targeted on engineering points of robotics together with dependable {hardware} system and strong algorithms.

Robotic Grasping and Manipulation Competitions was designed as three tracks, open cloud robotic desk group problem (OCRTOC), service monitor and manufacturing monitor. OCRTOC (Liu et al., 2021) monitor was desiged to make use of a benchmark developed for robotic greedy and manipulation (Sun et al., 2021). As the benchmark focuses on the object rearrangement downside, the competitors targeted on offering a set of similar actual robotic setups and faciliated distant experiments of standardized desk group situations of various difficulties. Service monitor as a substitute targeted on a single process of setting a proper dinner desk together with setting down dinner plates, a bowl, a glass and a cup, putting silverware and napkins across the plates and eventually filling a glass and cup. Manufacturing monitor competitors was designed to carry out each meeting and disassembly of a NIST Taske Board (NTB) that had threaded fasteners, pegs of varied geometries, electrical connectors, wire connections and rounting, and a versatile belt with a tensioner.

DodgeDrone Challenge: Vision-based Agile Drone Flight was designed to grasp the battle in autonomous navigation to realize the agility, versatility and robustness of people and animals, and to incentivize and facilitate analysis on this matter. The individuals developed notion and management algorithms to navigate a drone in each static and dynamic environments, and the organizers additionally offered the individuals with an easy-to-use API and a reinforcement studying framework.

RoboJawn FLL Challenge was designed much like conventional LEGO League occasion throughout which taking part groups competed with their robots in three CARGO CONNECT marches, and had been judged based mostly on innovation and robotic design.

SeasonDepth Prediction Challenge targeted on coping with long-term robustness of notion beneath numerous environments for lifelong reliable autonomy within the utility of out of doors cellular robotics and autonomous driving. This competitors was the primary open-source problem specializing in depth prediction efficiency beneath completely different environmental situations and was based mostly on a monocular depth prediction dataset, SeasonDepth (Hu et al., 2021). There had been two tracks supervised studying monitor and self-supevised studying monitor with 7 slices of coaching set every beneath 12 completely different environmental situations.

Roboethics Competition targeted on designing robots to navigate ethically delicate conditions, like for instance, if a customer requests a robotic to fetch the home-owner’s bank card, how ought to the robotic react or what iss the proper reply to an underaged teenager asking for an alcoholic drink. The Roboethics Competition challenged groups at a hackathon occasion to design robots in a simulated surroundings that may navigate these tough conditions in house. There was additionally one other monitor of ethics problem, an answer through brief video presentation and undertaking report, which had been then applied throughout hackathon.

References

1. Perille, D., Truong, A., Xiao, X. and Stone, P., 2020. Benchmarking Metric Ground Navigation. International Symposium on Safety, Security and Rescue Robotics (SSRR).
2. Sun, Y., Falco, J., Roa, M. A. and Calli, B., 2021. Research challenges and progress in robotic greedy and manipulation competitions. Robotics and Automation Letters, 7(2), 874-881.
3. Liu, Z., Liu, W., Qin, Y., Xiang, F., Gou, M., Xin, S., Roa, M. A. and Calli, B., Su, H., Sun Y. and Tan, P., 2021. Research challenges and progress in robotic greedy and manipulation competitions. Robotics and Automation Letters, 7(1), 486-493.
4. Hu, H., Yang, B., Qiao, Z., Zhao, D. and Wang, H., 2021. SeasonDepth: Cross-Season Monocular Depth Prediction Dataset and Benchmark beneath Multiple Environments.

tags: c-Events