Drexel University’s design focuses on a mature, open-architecture, bipedal robot called Hubo. Each member on Drexel’s team will be equipped with a stock Hubo, a complete, full-sized humanoid. This infrastructure will catalyze a multi-university effort to “hit the ground running” and successfully address all anticipated DRC events in a “program-test-perfect” model.
Team DRC-Hubo’s approach was to separate hardware and software tasks. Specifically, KAIST/Rainbow took inputs from other partners to retrofit Hubo to make the humanoid suitable for the DRC events. To collect appropriate inputs and address retrofitting, 7 Hubo humanoids (acquired from previous NSF grants) and open-source simulator (OpenHubo) were distributed to partners during the first 3-months of the DRC. Computer models and beta DRC-Hubo were tested-and-evaluated in the second 3-months of the DRC. Verification of the beta DRC-Hubo was executed in the third 3-months. Currently, validation through mock-trials is being executed by the team in preparation for the Miami trials to be held Dec. 20-21, 2013.
Developing a Robot for DRC:
The 15-month timeline (Oct 2012 Kickoff to Dec 2013 Miami trials) is very compressed. To avoid starting from scratch and hacking, the team used a “divide-and-conquer” approach: 7 Hubo humanoids and simulator were quickly distributed to partners. Furthermore, each partner was responsible to handle only one event. Such division of events and resources enabled partners to rapid-prototype algorithms and test-and-evaluate limitations of the current Hubo. Such division also helped the team avoid “hacking” and focus design effort on meeting DRC requirements.
Involvement in Prior DARPA Challenges:
Prof. Rasmussen (University of Delaware) has participated in DARPA Grand and Urban Challenges.