Search papers, labs, and topics across Lattice.
This paper introduces a closed-loop walking controller for the Poppy Humanoid, leveraging a linear-quadratic regulator (LQR) framework to enhance bipedal locomotion. By learning a quadratic cost function from data collected during open-loop playback, the method significantly improves the reliability of the robot's motion. Empirical validation shows statistically significant enhancements in walking performance over traditional open-loop approaches, addressing a critical gap in reliable bipedal locomotion for this platform.
Learning a cost function for LQR control transforms the Poppy Humanoid into a reliable bipedal walker, achieving significant performance gains.
The Poppy Humanoid is an open-source, low-cost robot suitable for research and education in artificial intelligence. However, we are unaware of any published methodology that achieves reliable, unassisted bipedal locomotion on the standard Poppy hardware. This paper contributes a functional closed-loop walking controller for Poppy, based on the linear-quadratic regulator (LQR) framework for trajectory tracking. Starting with data collected from open-loop playback of a nominal walking trajectory, our proposed method learns a quadratic cost function for an LQR controller that substantially improves the reliability of the motion. The closed-loop controller is validated empirically, demonstrating statistically significant improvements in walking performance compared to open-loop trajectory playback.
