Project Overview

Gymnastics has inspired the development of robots that mimic human movements and algorithms for robots to perform dynamic maneuvers. Inspired by gymnastics, we focus on developing a sequence of motions for a humanoid robot: walking, transitioning to running, leaping to grasp a horizontal bar, and performing a swing-up as if executed by a skilled gymnast. We use operational space control for the walking, leaping and running gaits and apply energy shaping control for the swing-up maneuver of the humanoid.

 Report     Video     Code     MEAM 5170, Penn   

Project Overview

In the growing field of legged robotics, the integration of locomotion and manipulation—loco-manipulation—poses a significant challenge. This work presents an open-source framework that facilitates planning through contact, enhancing robots’ capabilities in logistics, construction, and even planetary exploration. We validate our framework’s effectiveness on the Unitree Go1 equipped with a custom arm, demonstrating its application across various gaits and jumping maneuvers.

Publication

Bimodal Quadruped Robot (Senior Capstone)
Ethan Chandler*, Akshay Jaitly*, Lehong Wang*, Puen Xu*, Yifu Yuan*, Tao Zou*, Digital WPI, 2024. (* Equal Contribution)
RBE Department MQP Award Honorable Mention, WPI, May 2024.

 Paper     Code     ALMaS Group, WPI