7 papers
Preference-Based Long-Horizon Robotic Stacking with Multimodal Large Language Models
Wanming Yu, Adrian Röfer, Abhinav Valada +1
Pretrained large language models (LLMs) can work as high-level robotic planners by reasoning over abstract task descriptions and natural language instructions, etc. However, they h…
GeCCo -- a Generalist Contact-Conditioned Policy for Loco-Manipulation Skills on Legged Robots
Vassil Atanassov, Wanming Yu, Siddhant Gangapurwala +2
Most modern approaches to quadruped locomotion focus on using Deep Reinforcement Learning (DRL) to learn policies from scratch, in an end-to-end manner. Such methods often fail to…
Reference Free Platform Adaptive Locomotion for Quadrupedal Robots using a Dynamics Conditioned Policy
David Rytz, Suyoung Choi, Wanming Yu +3
This article presents Platform Adaptive Locomotion (PAL), a unified control method for quadrupedal robots with different morphologies and dynamics. We leverage deep reinforcement l…
Improving Trajectory Stitching with Flow Models
Reece O'Mahoney, Wanming Yu, Ioannis Havoutis
Generative models have shown great promise as trajectory planners, given their affinity to modeling complex distributions and guidable inference process. Previous works have succes…
Offline Adaptation of Quadruped Locomotion using Diffusion Models
Reece O'Mahoney, Alexander L. Mitchell, Wanming Yu +2
We present a diffusion-based approach to quadrupedal locomotion that simultaneously addresses the limitations of learning and interpolating between multiple skills and of (modes) o…
Discovery of skill switching criteria for learning agile quadruped locomotion
Wanming Yu, Fernando Acero, Vassil Atanassov +4
This paper develops a hierarchical learning and optimization framework that can learn and achieve well-coordinated multi-skill locomotion. The learned multi-skill policy can switch…