4 papers
DASH Robot: Minimalistic Design and Optimal Aerial-Terrestrial Locomotion via Contact-Implicit Control
Ryan Gomes Paiva, Conrad Ho, Jiarong Kang +3
We present a novel and minimalistic design of an aerial-terrestrial robot DASH: Ducted Aerial Spring Hopper. The goal is to enable both aerial and ground locomotion capabilities on…
PRIME: Physically-consistent Robotic Inertial and Motion Estimation for Legged and Humanoid Robots
Jiarong Kang, Kunzhao Ren, Tao Pang +1
Humanoid and legged robots interact with the environment through intermittent contacts, making accurate motion estimation fundamentally dependent on reasoning about contact dynamic…
Articulated-Body Dynamics Network: Dynamics-Grounded Prior for Robot Learning
Sangwoo Shin, Kunzhao Ren, Xiaobin Xiong +1
Recent work in reinforcement learning has shown that incorporating structural priors for articulated robots, such as link connectivity, into policy networks improves learning effic…
SPARK: Skeleton-Parameter Aligned Retargeting on Humanoid Robots with Kinodynamic Trajectory Optimization
Hanwen Wang, Qiayuan Liao, Bike Zhang +3
Human motion provides rich priors for training general-purpose humanoid control policies, but raw demonstrations are often incompatible with a robot's kinematics and dynamics, limi…