143 citations · 378 across the 39 of their papers we have counts for
8 papers · 1 filter
Optimization-Based Control for Dynamic Legged Robots
Patrick M. Wensing, Michael Posa, Yue Hu +3
In a world designed for legs, quadrupeds, bipeds, and humanoids have the opportunity to impact emerging robotics applications from logistics, to agriculture, to home assistance. Th…
CACTO: Continuous Actor-Critic with Trajectory Optimization -- Towards global optimality
Gianluigi Grandesso, Elisa Alboni, Gastone P. Rosati Papini +2
This paper presents a novel algorithm for the continuous control of dynamical systems that combines Trajectory Optimization (TO) and Reinforcement Learning (RL) in a single framewo…
Versatile Real-Time Motion Synthesis via Kino-Dynamic MPC with Hybrid-Systems DDP
He Li, Tingnan Zhang, Wenhao Yu +1
Specialized motions such as jumping are often achieved on quadruped robots by solving a trajectory optimization problem once and executing the trajectory using a tracking controlle…
Zero-Shot Retargeting of Learned Quadruped Locomotion Policies Using Hybrid Kinodynamic Model Predictive Control
He Li, Tingnan Zhang, Wenhao Yu +1
Reinforcement Learning (RL) has witnessed great strides for quadruped locomotion, with continued progress in the reliable sim-to-real transfer of policies. However, it remains a ch…
Analytical Second-Order Partial Derivatives of Rigid-Body Inverse Dynamics
Shubham Singh, Ryan P. Russell, Patrick M. Wensing
Optimization-based robot control strategies often rely on first-order dynamics approximation methods, as in iLQR. Using second-order approximations of the dynamics is expensive due…
Details of Second-Order Partial Derivatives of Rigid-Body Inverse Dynamics
Shubham Singh, Ryan P. Russell, Patrick M. Wensing
The details of second-order partial derivatives of rigid-body Inverse/Forward dynamics are provided. Several properties and identities using Spatial Vector Algebra are listed, alon…
Quadruped Capturability and Push Recovery via a Switched-Systems Characterization of Dynamic Balance
Hua Chen, Zejun Hong, Shunpeng Yang +2
This paper studies capturability and push recovery for quadrupedal locomotion. Despite the rich literature on capturability analysis and push recovery control for legged robots, ex…
Generalization in Supervised Learning Through Riemannian Contraction
Leo Kozachkov, Patrick M. Wensing, Jean-Jacques Slotine
We prove that Riemannian contraction in a supervised learning setting implies generalization. Specifically, we show that if an optimizer is contracting in some Riemannian metric wi…