#RoboCup2019 @Home – competition setup and first day


by
04 July 2019

share this:


I’ll be reporting three sub-leagues of RoboCup @Home (domestic standard, social, and open platform).

Preparation
Yesterday the teams were getting the final details down, acquiring the map information of the arenas, doing safety inspections for all the participating robots and meeting with their team leaders to clarify outstanding details for the competition to begin on Thursday.

As an additional portion of the competition all teams did a 3-minute poster presentation highlighting the research and methods that make it possible for their teams to compete.

First day of competition
Today, across all sub-leagues of @Home, the teams had two major blocks of tests: the first one was related to housekeeping tasks (throwing out the trash, serving breakfast or cleaning up misplaced objects) and the second one were related to tasks under a house party scenario (welcoming new guests, finding them a drink or walking them out). Among the major challenges involved in housekeeping tasks is correctly recognizing and manipulating objects which can be of many sizes. In the social interactions, the teams had to deal with keeping interactions as natural as possible as well as safe for the people acting as volunteer party attendants. Tomorrow there will be one more round of combined tasks (housekeeping and party scenario) before the top teams are selected for the second round.




Maru Cabrera is Research Associate at University of Washington.




            AIhub is supported by:


Related posts :



Radical AI podcast: featuring Kate Crawford

In this episode Jess and Dylan chat to Kate Crawford about the Atlas of AI.
20 April 2021, by

AIhub – leading organisations form new charity to advance public understanding of artificial intelligence

AIhub aims to empower everyone to learn about AI. Learn more about our journey and new charity.
15 April 2021, by

Maximum entropy RL (provably) solves some robust RL problems

Nearly all real-world applications of reinforcement learning involve some degree of shift between the training environment and the testing environment, and it is increasingly important to learn policies that are robust to these changes.
14 April 2021, by


















©2021 - Association for the Understanding of Artificial Intelligence