MoCapAct: A Multi-Task Dataset for Simulated Humanoid Control
- URL: http://arxiv.org/abs/2208.07363v1
- Date: Mon, 15 Aug 2022 17:57:33 GMT
- Title: MoCapAct: A Multi-Task Dataset for Simulated Humanoid Control
- Authors: Nolan Wagener, Andrey Kolobov, Felipe Vieira Frujeri, Ricky Loynd,
Ching-An Cheng, Matthew Hausknecht
- Abstract summary: We release MoCapAct, a dataset of expert agents and their rollouts, which contain proprioceptive observations and actions.
We demonstrate the utility of MoCapAct by using it to train a single hierarchical policy capable of tracking the entire MoCap dataset within dm_control.
- Score: 15.848947335588301
- License: http://creativecommons.org/licenses/by/4.0/
- Abstract: Simulated humanoids are an appealing research domain due to their physical
capabilities. Nonetheless, they are also challenging to control, as a policy
must drive an unstable, discontinuous, and high-dimensional physical system.
One widely studied approach is to utilize motion capture (MoCap) data to teach
the humanoid agent low-level skills (e.g., standing, walking, and running) that
can then be re-used to synthesize high-level behaviors. However, even with
MoCap data, controlling simulated humanoids remains very hard, as MoCap data
offers only kinematic information. Finding physical control inputs to realize
the demonstrated motions requires computationally intensive methods like
reinforcement learning. Thus, despite the publicly available MoCap data, its
utility has been limited to institutions with large-scale compute. In this
work, we dramatically lower the barrier for productive research on this topic
by training and releasing high-quality agents that can track over three hours
of MoCap data for a simulated humanoid in the dm_control physics-based
environment. We release MoCapAct (Motion Capture with Actions), a dataset of
these expert agents and their rollouts, which contain proprioceptive
observations and actions. We demonstrate the utility of MoCapAct by using it to
train a single hierarchical policy capable of tracking the entire MoCap dataset
within dm_control and show the learned low-level component can be re-used to
efficiently learn downstream high-level tasks. Finally, we use MoCapAct to
train an autoregressive GPT model and show that it can control a simulated
humanoid to perform natural motion completion given a motion prompt.
Videos of the results and links to the code and dataset are available at
https://microsoft.github.io/MoCapAct.
Related papers
- FreeMotion: MoCap-Free Human Motion Synthesis with Multimodal Large Language Models [19.09048969615117]
We explore open-set human motion synthesis using natural language instructions as user control signals based on MLLMs.
Our method can achieve general human motion synthesis for many downstream tasks.
arXiv Detail & Related papers (2024-06-15T21:10:37Z) - DexCap: Scalable and Portable Mocap Data Collection System for Dexterous Manipulation [28.37054959647664]
Imitation learning from human hand motion data presents a promising avenue for imbuing robots with human-like dexterity in real-world manipulation tasks.
We introduce DexCap, a portable hand motion capture system, alongside DexIL, a novel imitation algorithm for training dexterous robot skills directly from human hand mocap data.
arXiv Detail & Related papers (2024-03-12T16:23:49Z) - Humanoid Locomotion as Next Token Prediction [84.21335675130021]
Our model is a causal transformer trained via autoregressive prediction of sensorimotor trajectories.
We show that our model enables a full-sized humanoid to walk in San Francisco zero-shot.
Our model can transfer to the real world even when trained on only 27 hours of walking data, and can generalize commands not seen during training like walking backward.
arXiv Detail & Related papers (2024-02-29T18:57:37Z) - Any-point Trajectory Modeling for Policy Learning [64.23861308947852]
We introduce Any-point Trajectory Modeling (ATM) to predict future trajectories of arbitrary points within a video frame.
ATM outperforms strong video pre-training baselines by 80% on average.
We show effective transfer learning of manipulation skills from human videos and videos from a different robot morphology.
arXiv Detail & Related papers (2023-12-28T23:34:43Z) - H-GAP: Humanoid Control with a Generalist Planner [45.50995825122686]
Humanoid Generalist Autoencoding Planner (H-GAP) is a generative model trained on humanoid trajectories derived from human motioncaptured data.
For 56 degrees of freedom humanoid, we empirically demonstrate that H-GAP learns to represent and generate a wide range of motor behaviours.
We also do a series of empirical studies on the scaling properties of H-GAP, showing the potential for performance gains via additional data but not computing.
arXiv Detail & Related papers (2023-12-05T11:40:24Z) - Universal Humanoid Motion Representations for Physics-Based Control [71.46142106079292]
We present a universal motion representation that encompasses a comprehensive range of motor skills for physics-based humanoid control.
We first learn a motion imitator that can imitate all of human motion from a large, unstructured motion dataset.
We then create our motion representation by distilling skills directly from the imitator.
arXiv Detail & Related papers (2023-10-06T20:48:43Z) - Masked Motion Predictors are Strong 3D Action Representation Learners [143.9677635274393]
In 3D human action recognition, limited supervised data makes it challenging to fully tap into the modeling potential of powerful networks such as transformers.
We show that instead of following the prevalent pretext to perform masked self-component reconstruction in human joints, explicit contextual motion modeling is key to the success of learning effective feature representation for 3D action recognition.
arXiv Detail & Related papers (2023-08-14T11:56:39Z) - Perpetual Humanoid Control for Real-time Simulated Avatars [77.05287269685911]
We present a physics-based humanoid controller that achieves high-fidelity motion imitation and fault-tolerant behavior.
Our controller scales up to learning ten thousand motion clips without using any external stabilizing forces.
We demonstrate the effectiveness of our controller by using it to imitate noisy poses from video-based pose estimators and language-based motion generators in a live and real-time multi-person avatar use case.
arXiv Detail & Related papers (2023-05-10T20:51:37Z) - DeXtreme: Transfer of Agile In-hand Manipulation from Simulation to
Reality [64.51295032956118]
We train a policy that can perform robust dexterous manipulation on an anthropomorphic robot hand.
Our work reaffirms the possibilities of sim-to-real transfer for dexterous manipulation in diverse kinds of hardware and simulator setups.
arXiv Detail & Related papers (2022-10-25T01:51:36Z) - AirCapRL: Autonomous Aerial Human Motion Capture using Deep
Reinforcement Learning [38.429105809093116]
We introduce a deep reinforcement learning (RL) based multi-robot formation controller for the task of autonomous aerial human motion capture (MoCap)
We focus on vision-based MoCap, where the objective is to estimate the trajectory of body pose and shape a single moving person using multiple aerial vehicles.
arXiv Detail & Related papers (2020-07-13T12:30:31Z) - Residual Force Control for Agile Human Behavior Imitation and Extended
Motion Synthesis [32.22704734791378]
Reinforcement learning has shown great promise for realistic human behaviors by learning humanoid control policies from motion capture data.
It is still very challenging to reproduce sophisticated human skills like ballet dance, or to stably imitate long-term human behaviors with complex transitions.
We propose a novel approach, residual force control (RFC), that augments a humanoid control policy by adding external residual forces into the action space.
arXiv Detail & Related papers (2020-06-12T17:56:16Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.