The challenge will be set in the:centre, Milton Keynes’ smart shopping mall where intelligent agents carry tasks varying from customer assistance to mall management. The smartness of the mall is given by the networked devices, providing static and dynamic information from a number of heterogeneous data sources, e.g. location of shops, current availability of goods and items, audio and visual inputs from CCTV cameras, crowd density sensor information, and many others.
Episodes and Categories
The challenge will be divided into several episodes. An episode places a functionality tested during a specific Functional Benchmarks (FBM) into an operational context. This means that, during an episode, the tested functionality requires the integration with other system components, but limits the efforts for their development (using, for instance, off-the-shelf solutions). Although the goal is to target specifically one functionality (or exceptionally, two), an effort for integrating the main functionality and the other ones might be required in order to complete the episode.
Episodes are organised into categories depending on the task to achieve and the type of robots involved. We refer to three categories:
- HRI&Mobility: episodes involving robots able to show social behaviours, such as verbally interacting with (human) customers or navigating respecting proxemics, in line with the current ERL-Consumer. These are meant for any robot (wheeled, or legged) with navigational and verbal communication.
- Manipulation: episodes requiring robots to achieve manipulation tasks, applying ERL-Professional services to the smart city context. Episodes here are meant for any robot able to navigate and equipped with arms and effectors for the manipulation of objects.
- Emergency: tasks and challenges addressed by small VTOL aerial robots, along the lines of the ERL-Emergency. Any VTOL aerial platform able to carry and deliver items in specific locations, navigate in outdoor and indoor spaces, detect and avoid obstacles can take part to episodes of this category.
In order to maximise the team interests and attendance, the challenge is designed in four steps:
- Episode definition: a number of episodes relevant to the competition are designed
- Episode advertisement: episodes are advertised as part of SciRoc’s dissemination activities, in order to gather episode preferences directly from the teams.
- Final selection: episodes that have raised more preferences will be selected as the official competition episodes.
- Rulebook publication: the rulebook of the competition will be subsequently released.
Episodes list (to be refined and updated)
- (E01) Attract a customer
- (E02) Shopping guide
- (E03) Delivering coffee shop orders
- (E04) Take the elevator
- (E05) Unattended item
- (E06) Wiping a drink poured on the floor
- (E07) Serving goodies
- (E08) At the check-out desk
- (E09) Cart push
- (E10) Open the door
- (E11) Finding a lost dog with a drone
- (E12) Fast delivery of emergency pills
Challenge tentative schedule
A tentative timeline for the challenge is as follows:
- (Sep 1st, 2018) Call for Expression of Interests; we intend here to gather interests around the competition and identify potential teams and the most appealing competition episodes (closing date, October 10th).
- (October 15th, 2018) Publication of the first Call for Participation, after episode selection.
- (December 1st, 2018) Opening of team submissions (closing date January 31st, 2019).
- (December 31st, 2018) Publication of the first draft of the Competition Rulebook: the specific rulebook will be published for the participating teams.
- (February 15th, 2019) Notification of accepted teams.
- (March 1st, 2019) Second Call for Participation (closing date March 31st).
- (April 15th, 2019): Notification of accepted teams.
Note that a dedicated booth will be present at the IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS2018) between Oct 1st and Oct 5th 2018, in order to attract team interests and episode preferences.
A *tentative* schedule of the event is as follows: