Patrick M. Wensing
YOU?
Author Swipe
View article: Multi-Loco: Unifying Multi-Embodiment Legged Locomotion via Reinforcement Learning Augmented Diffusion
Multi-Loco: Unifying Multi-Embodiment Legged Locomotion via Reinforcement Learning Augmented Diffusion Open
Generalizing locomotion policies across diverse legged robots with varying morphologies is a key challenge due to differences in observation/action dimensions and system dynamics. In this work, we propose Multi-Loco, a novel unified framew…
View article: URDF+: An Enhanced URDF for Robots with Kinematic Loops
URDF+: An Enhanced URDF for Robots with Kinematic Loops Open
Designs incorporating kinematic loops are becoming increasingly prevalent in the robotics community. Despite the existence of dynamics algorithms to deal with the effects of such loops, many modern simulators rely on dynamics libraries tha…
View article: Simultaneous Locomotion Mode Classification and Continuous Gait Phase Estimation for Transtibial Prostheses
Simultaneous Locomotion Mode Classification and Continuous Gait Phase Estimation for Transtibial Prostheses Open
Recognizing and identifying human locomotion is a critical step to ensuring fluent control of wearable robots, such as transtibial prostheses. In particular, classifying the intended locomotion mode and estimating the gait phase are key. I…
View article: Center of mass kinematic reconstruction during steady-state walking using optimized template models
Center of mass kinematic reconstruction during steady-state walking using optimized template models Open
Template models, such as the Bipedal Spring-Loaded Inverted Pendulum and the Virtual Pivot Point, have been widely used as low-dimensional representations of the complex dynamics in legged locomotion. Despite their ability to qualitatively…
View article: Task-Space Riccati Feedback based Whole Body Control for Underactuated Legged Locomotion
Task-Space Riccati Feedback based Whole Body Control for Underactuated Legged Locomotion Open
This manuscript primarily aims to enhance the performance of whole-body controllers(WBC) for underactuated legged locomotion. We introduce a systematic parameter design mechanism for the floating-base feedback control within the WBC. The p…
View article: Cafe-Mpc: A Cascaded-Fidelity Model Predictive Control Framework with Tuning-Free Whole-Body Control
Cafe-Mpc: A Cascaded-Fidelity Model Predictive Control Framework with Tuning-Free Whole-Body Control Open
This work introduces an optimization-based locomotion control framework for on-the-fly synthesis of complex dynamic maneuvers. At the core of the proposed framework is a cascaded-fidelity model predictive controller (Cafe-Mpc). Cafe-Mpc st…
View article: Lower-Limb Myoelectric Calibration Postures for Transtibial Prostheses
Lower-Limb Myoelectric Calibration Postures for Transtibial Prostheses Open
The use of an agonist-antagonist muscle pair for myoelectric control of a transtibial prosthesis requires normalizing the myoelectric signals and identifying their co-contraction signature. Extensive literature has explored the relationshi…
View article: Coriolis Factorizations and their Connections to Riemannian Geometry
Coriolis Factorizations and their Connections to Riemannian Geometry Open
Many energy-based control strategies for mechanical systems require the choice of a Coriolis factorization satisfying a skew-symmetry property. This paper (a) explores if and when a control designer has flexibility in this choice, (b) deve…
View article: A Propagation Perspective on Recursive Forward Dynamics for Systems with Kinematic Loops
A Propagation Perspective on Recursive Forward Dynamics for Systems with Kinematic Loops Open
We revisit the concept of constraint embedding as a means for dealing with kinematic loop constraints during dynamics computations for rigid-body systems. Specifically, we consider the local loop constraints emerging from common actuation …
View article: Robot Model Identification and Learning: A Modern Perspective
Robot Model Identification and Learning: A Modern Perspective Open
In recent years, the increasing complexity and safety-critical nature of robotic tasks have highlighted the importance of accurate and reliable robot models. This trend has led to a growing belief that, given enough data, traditional physi…
View article: Optimization-Based Control for Dynamic Legged Robots
Optimization-Based Control for Dynamic Legged Robots Open
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. The goal of this survey is to cover the recent progress towar…
View article: Hybrid Volitional Control of a Robotic Transtibial Prosthesis using a Phase Variable Impedance Controller
Hybrid Volitional Control of a Robotic Transtibial Prosthesis using a Phase Variable Impedance Controller Open
For robotic transtibial prosthesis control, the global kinematics of the tibia can be used to monitor the progression of the gait cycle and command smooth and continuous actuation. In this work, these global tibia kinematics are used to de…
View article: A Unified Perspective on Multiple Shooting In Differential Dynamic Programming
A Unified Perspective on Multiple Shooting In Differential Dynamic Programming Open
Differential Dynamic Programming (DDP) is an efficient computational tool for solving nonlinear optimal control problems. It was originally designed as a single shooting method and thus is sensitive to the initial guess supplied. This work…
View article: Towards Continuous Time Finite Horizon LQR Control in SE(3)
Towards Continuous Time Finite Horizon LQR Control in SE(3) Open
The control of free-floating robots requires dealing with several challenges. The motion of such robots evolves on a continuous manifold described by the Special Euclidean Group of dimension 3, known as SE(3). Methods from finite horizon L…
View article: Multi-Shooting Differential Dynamic Programming for Hybrid Systems using Analytical Derivatives
Multi-Shooting Differential Dynamic Programming for Hybrid Systems using Analytical Derivatives Open
Differential Dynamic Programming (DDP) is a popular technique used to generate motion for dynamic-legged robots in the recent past. However, in most cases, only the first-order partial derivatives of the underlying dynamics are used, resul…
View article: Whole-Body Dynamic Telelocomotion: A Step-to-Step Dynamics Approach to Human Walking Reference Generation
Whole-Body Dynamic Telelocomotion: A Step-to-Step Dynamics Approach to Human Walking Reference Generation Open
Teleoperated humanoid robots hold significant potential as physical avatars for humans in hazardous and inaccessible environments, with the goal of channeling human intelligence and sensorimotor skills through these robotic counterparts. P…
View article: CACTO: Continuous Actor-Critic With Trajectory Optimization—Towards Global Optimality
CACTO: Continuous Actor-Critic With Trajectory Optimization—Towards Global Optimality Open
This letter presents a novel algorithm for the continuous control of dynamical systems that combines Trajectory Optimization (TO) and Reinforcement Learning (RL) in a single framework. The motivations behind this algorithm are the two main…
View article: On Second-Order Derivatives of Rigid-Body Dynamics: Theory & Implementation
On Second-Order Derivatives of Rigid-Body Dynamics: Theory & Implementation Open
Model-based control for robots has increasingly been dependent on optimization-based methods like Differential Dynamic Programming and iterative LQR (iLQR). These methods can form the basis of Model-Predictive Control (MPC), which is commo…
View article: Finite-State Impedance and Direct Myoelectric Control for Robotic Ankle Prostheses: Comparing Their Performance and Exploring Their Combination
Finite-State Impedance and Direct Myoelectric Control for Robotic Ankle Prostheses: Comparing Their Performance and Exploring Their Combination Open
Non-volitional control, such as finite-state machine (FSM) impedance control, does not directly incorporate user intent signals, while volitional control, like direct myoelectric control (DMC), relies on these signals. This paper compares …
View article: Data-efficient human walking speed intent identification
Data-efficient human walking speed intent identification Open
The ability to accurately identify human gait intent is a challenge relevant to the success of many applications in robotics, including, but not limited to, assistive devices. Most existing intent identification approaches, however, are ei…
View article: Second-Order Differential Dynamic Programming for Whole-Body MPC of Legged Robots
Second-Order Differential Dynamic Programming for Whole-Body MPC of Legged Robots Open
This paper presents the first use-case of full second-order Differential Dynamic Programming (DDP) with a whole-body model for model predictive control on legged robot hardware. Recent advances in the literature show that DDP can be simpli…
View article: Optimization-Based Control for Dynamic Legged Robots
Optimization-Based Control for Dynamic Legged Robots Open
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. The goal of this survey is to cover the recent progress towar…
View article: CACTO: Continuous Actor-Critic with Trajectory Optimization -- Towards global optimality
CACTO: Continuous Actor-Critic with Trajectory Optimization -- Towards global optimality Open
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 framework. The motivations behind this algorithm are the two main …
View article: Versatile Real-Time Motion Synthesis via Kino-Dynamic MPC with Hybrid-Systems DDP
Versatile Real-Time Motion Synthesis via Kino-Dynamic MPC with Hybrid-Systems DDP Open
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 controller. This approach is in parallel with Model Predictive Contr…
View article: Zero-Shot Retargeting of Learned Quadruped Locomotion Policies Using Hybrid Kinodynamic Model Predictive Control
Zero-Shot Retargeting of Learned Quadruped Locomotion Policies Using Hybrid Kinodynamic Model Predictive Control Open
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 challenge to reuse a policy on another robot, which could sav…
View article: Analytical Second-Order Partial Derivatives of Rigid-Body Inverse Dynamics
Analytical Second-Order Partial Derivatives of Rigid-Body Inverse Dynamics Open
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 to the costly second-order partial derivatives of the dyna…
View article: Details of Second-Order Partial Derivatives of Rigid-Body Inverse Dynamics
Details of Second-Order Partial Derivatives of Rigid-Body Inverse Dynamics Open
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, along with their detailed derivations. The expressions build up…