Quantcast

Team WPI-CMU: Achieving Reliable Humanoid Behavior in the DARPA Robotics Challenge

Research paper by Mathew DeDonato, Felipe Polido, Kevin Knoedler, Benzun P. W. Babu, Nandan Banerjee, Christoper P. Bove, Xiongyi Cui, Ruixiang Du, Perry Franklin, Joshua P. Graff, Peng He, Aaron Jaeger, Lening Li, Dmitry Berenson, Michael A. Gennert, et al.

Indexed on: 24 Jan '17Published on: 23 Jan '17Published in: Journal of Field Robotics



Abstract

In the DARPA Robotics Challenge (DRC), participating human-robot teams were required to integrate mobility, manipulation, perception, and operator interfaces to complete a simulated disaster mission. We describe our approach using the humanoid robot Atlas Unplugged developed by Boston Dynamics. We focus on our approach, results, and lessons learned from the DRC Finals to demonstrate our strategy, including extensive operator practice, explicit monitoring for robot errors, adding additional sensing, and enabling the operator to control and monitor the robot at varying degrees of abstraction. Our safety-first strategy worked: we avoided falling, and remote operators could safely recover from difficult situations. We were the only team in the DRC Finals that attempted all tasks, scored points (14/16), did not require physical human intervention (a reset), and did not fall in the two missions during the two days of tests. We also had the most consistent pair of runs.