MuJoCo HAPTIX: A virtual reality system for hand manipulation

By Vikash Kumar, E. Todorov. 2015

124 citations recorded by the source corpus.

Subfields: Cognitive Neuroscience, Control and Systems Engineering, Mechanical Engineering

How researchers see this paper

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

In Cognitive Neuroscience

In Control and Systems Engineering

In Mechanical Engineering

Citations in the corpus

Relay Policy Learning: Solving Long-Horizon Tasks via Imitation and Reinforcement Learning (2019, methodology): “he goals we consider are temporally extended, the setup is fully general. We collect a set of unstructured and unsegmented human demonstrations described in Sec.4.2, using the PUPPET MuJoCo VR system [35]. We provide the algorithm with 400 sequences containing various unstructured demonstrations tha”
Deep Imitation Learning for Complex Manipulation Tasks from Virtual Reality Teleoperation (2017, background): “In a non-learning setting, VR teleoperation has been recently explored for a small humanoid robot called iCub [40], for simulated dexterous manipulation [41], and for communicating motion intent [42].”
Distributed Distributional Deterministic Policy Gradients (2018, methodology): “We ﬁrst consider evaluating performance on a number of simple, physical control tasks by utilizing a suite of benchmark tasks (Tassa et al., 2018) developed in the MuJoCo physics simulator (Todorov et al., 2012).”
Learning Latent Plans from Play (2019, methodology): “1) Training Data: An updated version of the Mujoco HAPTIX system is used to collect teleoperation demonstration data [28].”
Learning Dexterous Manipulation Policies from Experience and Imitation (2016, methodology): “The Mujoco Haptix system (Kumar and Todorov 2015) was developed to facilitate physically-consistent recording of rich hand-object interactions.”
Task-Oriented Hand Motion Retargeting for Dexterous Manipulation Imitation (2018, methodology): “nts of the hand. In order to perform dexterous actions, the hand model needs to be ve-ngered and similar to the human hand. The hand model selected is a modied version of the MPL model presented in [33], which in turn is a virtual model of the Modular Prosthetic Limb developed by Johns Hopkins Unive”
DexPilot: Vision-Based Teleoperation of Dexterous Robotic Hand-Arm System (2019, methodology): “Sometimes these systems still require an external hand pose estimation module as in [21] to enable a freely moving mobile hand as with DexPilot.”