Due to Covid-19, the competition is formatted to be remote and up to ten teams will be selected to compete. There will be two manufacturing sub-tasks in the competition, disassembly and assembly using a NIST Task Board (NTB). A pre-competition NTB design will be made available for selected teams to continue development of their systems leading up to the competition. A new NTB with modified assembly positions (very similar to the pre-competition task board), and new parts (identical to all parts used in practice), will be supplied prior to a team’s scheduled on-line competition run. Competition NTBs must not be opened until the start of the scheduled run as instructed by a judge via video conferencing software.
Teams must apply to compete in this competition. Please send a one to two-page text description of the robotic assembly system that you will use to compete by August 31, 2020 to Yu Sun (yusun [at] mail.usf.edu (yusun[at]mail[dot]usf[dot]edu)). Include descriptions of your autonomous assembly strategies and robotic assembly system; robot manipulators, end effector technology, sensors used for perception, control software and any plans for incorporating the use of supplied CAD data. Solutions that rely primarily on teaching (also called lead through programming) are not recommended. Images and Videos that help describe your system and operating principles are encouraged, but not required. Also include shipping information for sending NTBs in the case that your team is selected as follows:
City or Town:
* It’s very important that a person’s name is included in the Attention field.
Note: The organizers cannot guarantee the shipping times of the NTBs. Therefore, we have also included all sources and instructions for producing the practice board (pre-competition NTB) on the manufacturing track web site.
The goal of the competition is to test the capabilities of a robot system in performing assembly operations relative to a small-parts manufacturing process using assembly task boards. The task board for this competition was designed based on similar task boards that have been developed as part of a NIST project to support the advancement of robotic systems for variable small-batch production runs in future manufacturing systems (see: https://www.nist.gov/el/intelligent-systems-division-73500/robotic-grasping-and-manipulation-assembly/assembly).
Competition parts have been selected to replicate typical manufacturing assembly operations. Competing robot systems should recognize, grasp, and assemble/disassemble various parts including flexible ones, and assemble/disassemble a new product by quickly reconfiguring the system. The limited competition time and bonus applied remaining time should encourage autonomous system designs where the use of perception (machine vision and force sensing) will eliminate the time associated with teaching (also called lead through programming) and the need for jigs (also called fixturing). The principles of design & manufacture make part data readily available to the automated systems in the form of Computer-Aided Design (CAD) data. Therefore, all CAD models will be made available to competitors.
The manufacturing track of the IROS 2020 Robotic Grasping and Manipulation Competition will consist of two subtasks; an assembly subtask and a disassembly subtask using a task board. Figure 1 shows the design used for the IROS 2019 task board. Both the 2020 practice and competition task boards use the same components as the 2019 task board shown below. When the competition task board is removed from a sealed box at the start of the competition run, an example kit layout is also provided to present parts for the assembly subtask. During the competition the location of the parts on the task board and the kit will change.
In this remote format, each team’s competition run will be recorded by teams in their respective robot laboratory and viewed live using video conferencing by a remote judge. Each team is responsible for video recording their entire competition period and must send this video to the competition organizer. The locations of the task board and kit must be randomly defined using Velcro attachment points at the start of the competition under the supervision of the remote judge. Random board placement and part position changes are used to highly encourage the use of autonomous system designs. More detail is provided in the rules document below.