Feed forward

Related papers: 20

About

Feedforward control is a proactive control strategy that uses a model of the system to compute and apply control actions in advance, rather than waiting for errors to occur before responding. Unlike feedback control, which reacts to measured deviations, feedforward anticipates disturbances or desired trajectories and generates compensating commands preemptively based on known system dynamics or learned models. In robotics and AI, feedforward control is widely applied in manipulator trajectory tracking, exoskeleton assistance, force control, vibration suppression, and neural network-based learning controllers. A robot arm, for example, might use a dynamic model to precompute the torques needed for a desired motion, with feedback handling residual errors. Neural networks can serve as feedforward components that approximate complex nonlinear dynamics, enabling accurate real-time control without full analytical models. Feedforward control matters because it dramatically improves tracking performance and responsiveness, especially for fast or complex motions where feedback alone introduces unacceptable lag or instability. By reducing the burden on feedback loops, it enables smoother, more energy-efficient operation and is essential for high-performance tasks such as human-robot interaction, prosthetic limb control, and precision manufacturing.

Top Cited Papers

Zero Phase Error Tracking Algorithm for Digital Control

Masayoshi Tomizuka

Citations: 1470 • 1987

The attitude control problem

John T. Wen, Kenneth Kreutz-Delgado

Citations: 1053 • 1991

An integrated friction model structure with improved presliding behavior for accurate friction compensation

Jan Swevers, Farid Al‐Bender, Chris Ganseman, T. Projogo

Citations: 664 • 2000

Genetic evolution of the topology and weight distribution of neural networks

Vittorio Maniezzo

Citations: 438 • 1994

Underactuated mechanical systems

Mark W. Spong

Citations: 429 • 2005

Control of Rotary Series Elastic Actuator for Ideal Force-Mode Actuation in Human–Robot Interaction Applications

Kyoungchul Kong, Joonbum Bae, Masayoshi Tomizuka

Citations: 428 • 2009

Human-Like Adaptation of Force and Impedance in Stable and Unstable Interactions

Chenguang Yang, Gowrishankar Ganesh, Sami Haddadin, Sven Parusel, Alin Albu‐Schäffer, Etienne Burdet

Citations: 392 • 2011

Real-time dynamic control of an industrial manipulator using a neural network-based learning controller

Wallace T. Miller, R.P. Hewes, Filson H. Glanz, L.G. Kraft

Citations: 320 • 1990

Conventional controller design for industrial robots — A tutorial

J.Y.S. Luh

Citations: 280 • 1983

Robot-Assisted Adaptive Training: Custom Force Fields for Teaching Movement Patterns

James L. Patton, Ferdinando A. Mussa-Ivaldi

Citations: 268 • 2004

Neural Network Control of a Class of Nonlinear Systems With Actuator Saturation

Wenzhong Gao, Rastko R. Šelmić

Citations: 252 • 2006

Nonlinear Disturbance Observer-Based Control Design for a Robotic Exoskeleton Incorporating Fuzzy Approximation

Zhijun Li, Chun‐Yi Su, Liangyong Wang, Ziting Chen, Tianyou Chai

Citations: 248 • 2015

Repetitive learning control: a Lyapunov-based approach

Warren E. Dixon, Erkan Zergeroğlu, D.M. Dawson, B.T. Costic

Citations: 225 • 2002

An adaptive input shaping control scheme for vibration suppression in slewing flexible structures

Anthony Tzes, Stephen Yurkovich

Citations: 220 • 1993

Compliant Robot Motion I. A Formalism for Specifying Compliant Motion Tasks

Joris De Schutter, H. Van Brussel

Citations: 218 • 1988

Decentralized adaptive control of manipulators: theory, simulation, and experimentation

H. Seraji

Citations: 216 • 1989

Contribution of Feedback and Feedforward Strategies to Locomotor Adaptations

Tania Lam, Martin Anderschitz, Volker Dietz

Citations: 213 • 2006

Fast nonlinear Model Predictive Control for unified trajectory optimization and tracking

Michael Neunert, Cedric de Crousaz, Fadri Furrer, Mina Kamel, Farbod Farshidian, Roland Siegwart, Jonas Buchli

Citations: 205 • 2016

Motion planning for anguilliform locomotion

Kenneth McIsaac, J.P. Ostrowski

Citations: 203 • 2003

The role of feed-forward and feedback processes for closed-loop prosthesis control

Ian Saunders, Sethu Vijayakumar

Citations: 195 • 2011