Generating Physically Realistic and Directable Human Motions from Multi-Modal Inputs

• URL: http://arxiv.org/abs/2502.05641v1
• Date: Sat, 08 Feb 2025 17:02:11 GMT
• Title: Generating Physically Realistic and Directable Human Motions from Multi-Modal Inputs
• Authors: Aayam Shrestha, Pan Liu, German Ros, Kai Yuan, Alan Fern,
• Abstract summary: This work focuses on generating realistic, physically-based human behaviors from multi-modal inputs, which may only partially specify the desired motion. The input may come from a VR controller providing arm motion and body velocity, partial key-point animation, computer vision applied to videos, or even higher-level motion goals. We introduce the Masked Humanoid Controller (MHC), a novel approach that applies multi-objective imitation learning on augmented and selectively masked motion demonstrations.
• Score: 16.41735119504929
• License:
• Abstract: This work focuses on generating realistic, physically-based human behaviors from multi-modal inputs, which may only partially specify the desired motion. For example, the input may come from a VR controller providing arm motion and body velocity, partial key-point animation, computer vision applied to videos, or even higher-level motion goals. This requires a versatile low-level humanoid controller that can handle such sparse, under-specified guidance, seamlessly switch between skills, and recover from failures. Current approaches for learning humanoid controllers from demonstration data capture some of these characteristics, but none achieve them all. To this end, we introduce the Masked Humanoid Controller (MHC), a novel approach that applies multi-objective imitation learning on augmented and selectively masked motion demonstrations. The training methodology results in an MHC that exhibits the key capabilities of catch-up to out-of-sync input commands, combining elements from multiple motion sequences, and completing unspecified parts of motions from sparse multimodal input. We demonstrate these key capabilities for an MHC learned over a dataset of 87 diverse skills and showcase different multi-modal use cases, including integration with planning frameworks to highlight MHC's ability to solve new user-defined tasks without any finetuning.

Related papers

• ModSkill: Physical Character Skill Modularization [21.33764810227885]
  We introduce a novel skill learning framework, ModSkill, that decouples complex full-body skills into compositional, modular skills for independent body parts. Our results show that this modularized skill learning framework, enhanced by generative sampling, outperforms existing methods in precise full-body motion tracking.
  arXiv  Detail & Related papers  (2025-02-19T22:55:49Z)
• Sitcom-Crafter: A Plot-Driven Human Motion Generation System in 3D Scenes [90.39860012099393]
  Sitcom-Crafter is a system for human motion generation in 3D space. Central to the function generation modules is our novel 3D scene-aware human-human interaction module. Augmentation modules encompass plot comprehension for command generation, motion synchronization for seamless integration of different motion types.
  arXiv  Detail & Related papers  (2024-10-14T17:56:19Z)
• Learning Multi-Modal Whole-Body Control for Real-World Humanoid Robots [13.229028132036321]
  Masked Humanoid Controller (MHC) supports standing, walking, and mimicry of whole and partial-body motions. MHC imitates partially masked motions from a library of behaviors spanning standing, walking, optimized reference trajectories, re-targeted video clips, and human motion capture data. We demonstrate sim-to-real transfer on the real-world Digit V3 humanoid robot.
  arXiv  Detail & Related papers  (2024-07-30T09:10:24Z)
• Motion-Agent: A Conversational Framework for Human Motion Generation with LLMs [67.59291068131438]
  Motion-Agent is a conversational framework designed for general human motion generation, editing, and understanding. Motion-Agent employs an open-source pre-trained language model to develop a generative agent, MotionLLM, that bridges the gap between motion and text.
  arXiv  Detail & Related papers  (2024-05-27T09:57:51Z)
• Taming Diffusion Probabilistic Models for Character Control [46.52584236101806]
  We present a novel character control framework that responds in real-time to a variety of user-supplied control signals. At the heart of our method lies a transformer-based Conditional Autoregressive Motion Diffusion Model. Our work represents the first model that enables real-time generation of high-quality, diverse character animations.
  arXiv  Detail & Related papers  (2024-04-23T15:20:17Z)
• Bridging Language, Vision and Action: Multimodal VAEs in Robotic Manipulation Tasks [0.0]
  In this work, we focus on unsupervised vision-language--action mapping in the area of robotic manipulation. We propose a model-invariant training alternative that improves the models' performance in a simulator by up to 55%. Our work thus also sheds light on the potential benefits and limitations of using the current multimodal VAEs for unsupervised learning of robotic motion trajectories.
  arXiv  Detail & Related papers  (2024-04-02T13:25:16Z)
• MoConVQ: Unified Physics-Based Motion Control via Scalable Discrete Representations [25.630268570049708]
  MoConVQ is a novel unified framework for physics-based motion control leveraging scalable discrete representations. Our approach effectively learns motion embeddings from a large, unstructured dataset spanning tens of hours of motion examples.
  arXiv  Detail & Related papers  (2023-10-16T09:09:02Z)
• 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)
• DiverseMotion: Towards Diverse Human Motion Generation via Discrete Diffusion [70.33381660741861]
  We present DiverseMotion, a new approach for synthesizing high-quality human motions conditioned on textual descriptions. We show that our DiverseMotion achieves the state-of-the-art motion quality and competitive motion diversity.
  arXiv  Detail & Related papers  (2023-09-04T05:43:48Z)
• CALM: Conditional Adversarial Latent Models for Directable Virtual Characters [71.66218592749448]
  We present Conditional Adversarial Latent Models (CALM), an approach for generating diverse and directable behaviors for user-controlled interactive virtual characters. Using imitation learning, CALM learns a representation of movement that captures the complexity of human motion, and enables direct control over character movements.
  arXiv  Detail & Related papers  (2023-05-02T09:01:44Z)
• UniCon: Universal Neural Controller For Physics-based Character Motion [70.45421551688332]
  We propose a physics-based universal neural controller (UniCon) that learns to master thousands of motions with different styles by learning on large-scale motion datasets. UniCon can support keyboard-driven control, compose motion sequences drawn from a large pool of locomotion and acrobatics skills and teleport a person captured on video to a physics-based virtual avatar.
  arXiv  Detail & Related papers  (2020-11-30T18:51:16Z)

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.