Model-Based Control of a Robot Manipulator

By C. An, Christopher G. Atkeson, J. Hollerbach. 1988

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

Citations in the corpus

Reinforcement learning in robotics: A survey (2013, methodology): “If the learning methods require predicting the future or using derivatives, even small inaccuracies can quickly accumulate, significantly amplifying noise and errors (An et al., 1988).”
SOLAR: Deep Structured Representations for Model-Based Reinforcement Learning (2018, unknown): “e still limited to short horizon prediction in more complex domains [27, 30, 13, 42]. Another class of model-based methods rely only on local system models to compute the gradient for a policy update [1, 21, 14, 24, 5]. These methods do not use models for long-term forward prediction, allowing for t”
Autonomous Helicopter Aerobatics through Apprenticeship Learning (2010, background): “Factoring out Demonstration Drift.”
Adaptive Tracking Control for Robots with Unknown Kinematic and Dynamic Properties (2006, methodology): “accuracy by calibrations and identification techniques [ 8 ], [9], it is not flexible to do calibration”
Segmentation of endpoint trajectories does not imply segmented control (1999, methodology): “…the robot employs kinematic trajectory plans (joint position, velocity, and acceleration), converts those to joint torques by an inverse dynamics model based on estimated parameters (An, Atkeson, and Hollerbach, 1988), and executes the torque commands in conjunction with a low gain PID controller.”
Robot juggling: implementation of memory-based learning (1994, methodology): “Using models for control according to the certainty equivalence principle is nothing new and has been supported by many researchers in the last years (e.g., [ 3 , 38, 22, 24]).”