Fast, strong and compliant pneumatic actuation for dexterous tendon-driven hands

By Vikash Kumar, Zhe Xu, E. Todorov. 2013

80 citations recorded by the source corpus.

Subfields: Biomedical Engineering, Control and Systems Engineering

How researchers see this paper

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

In Biomedical Engineering

In Control and Systems Engineering

Citations in the corpus

Learning Complex Dexterous Manipulation with Deep Reinforcement Learning and Demonstrations (2017, methodology): “1) ADROIT hand: We use a simulated analogue of a highly dexterous manipulator – ADROIT [27], which is a 24-DoF anthropomorphic platform designed for addressing challenges in dynamic and dexterous manipulation [26], [24].”
Dexterous Manipulation with Deep Reinforcement Learning: Efficient, General, and Low-Cost (2018, neutral): “The majority of these manipulators [2], [3]”
Learning Dexterous Manipulation Policies from Experience and Imitation (2016, methodology): “We use our ADROIT platform Kumar, Xu and Todorov (2013), which is a ShadowHand skeleton augmented with high-performance pneumatic actuators.”
Real-time behaviour synthesis for dynamic hand-manipulation (2014, methodology): “In [6] we developed a general purpose universal pneumatic actuation for tendons driven systems.”
Manipulators and Manipulation in high dimensional spaces (2016, methodology): “Adroit manipulation platform [48] is a 28 dof robotic system being developed with an aim to achieve complex human-like object manipulation.”
Learning Dexterous Grasping with Object-Centric Visual Affordances (2020, methodology): “We demonstrate our idea with the 30 DoF AdroitHand model [21]”
A low-cost and modular, 20-DOF anthropomorphic robotic hand: design, actuation and modeling (2013, methodology): “In order to investigate the characteristics of the force and compliance of the actuation system, we conducted experiments using a Shadow hand in our previous work [17].”
DDPG++: Striving for Simplicity in Continuous-control Off-Policy Reinforcement Learning (2020, methodology): “1 Dexterous hand manipulation We next evaluate the DDPG++ algorithm on a challenging robotic task where a simulated anthropomorphic ADROIT hand [20] with 24 degrees-of-freedom is used to open a door Fig.”
Demonstration-Guided Deep Reinforcement Learning of Control Policies for Dexterous Human-Robot Interaction (2019, background): “Dexterous humanoid hands are a highly complex mechanical systems [15].”
Optimal control with learned local models: Application to dexterous manipulation (2016, methodology): “We use our Adroit platform [2], which is a ShadowHand skeleton augmented with high-performance pneumatic actuators .”