SuperPADL: Scaling Language-Directed Physics-Based Control with Progressive Supervised Distillation

• URL: http://arxiv.org/abs/2407.10481v1
• Date: Mon, 15 Jul 2024 07:07:11 GMT
• Title: SuperPADL: Scaling Language-Directed Physics-Based Control with Progressive Supervised Distillation
• Authors: Jordan Juravsky, Yunrong Guo, Sanja Fidler, Xue Bin Peng,
• Abstract summary: We introduce SuperPADL, a scalable framework for physics-based text-to-motion. SuperPADL trains controllers on thousands of diverse motion clips using RL and supervised learning. Our controller is trained on a dataset containing over 5000 skills and runs in real time on a consumer GPU.
• Score: 55.47473138423572
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Physically-simulated models for human motion can generate high-quality responsive character animations, often in real-time. Natural language serves as a flexible interface for controlling these models, allowing expert and non-expert users to quickly create and edit their animations. Many recent physics-based animation methods, including those that use text interfaces, train control policies using reinforcement learning (RL). However, scaling these methods beyond several hundred motions has remained challenging. Meanwhile, kinematic animation models are able to successfully learn from thousands of diverse motions by leveraging supervised learning methods. Inspired by these successes, in this work we introduce SuperPADL, a scalable framework for physics-based text-to-motion that leverages both RL and supervised learning to train controllers on thousands of diverse motion clips. SuperPADL is trained in stages using progressive distillation, starting with a large number of specialized experts using RL. These experts are then iteratively distilled into larger, more robust policies using a combination of reinforcement learning and supervised learning. Our final SuperPADL controller is trained on a dataset containing over 5000 skills and runs in real time on a consumer GPU. Moreover, our policy can naturally transition between skills, allowing for users to interactively craft multi-stage animations. We experimentally demonstrate that SuperPADL significantly outperforms RL-based baselines at this large data scale.

Related papers

• Reinforcement Learning for Versatile, Dynamic, and Robust Bipedal Locomotion Control [106.32794844077534]
  This paper presents a study on using deep reinforcement learning to create dynamic locomotion controllers for bipedal robots. We develop a general control solution that can be used for a range of dynamic bipedal skills, from periodic walking and running to aperiodic jumping and standing. This work pushes the limits of agility for bipedal robots through extensive real-world experiments.
  arXiv  Detail & Related papers  (2024-01-30T10:48:43Z)
• 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)
• 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)
• Advanced Skills through Multiple Adversarial Motion Priors in Reinforcement Learning [10.445369597014533]
  We present an approach to augment the concept of adversarial motion prior-based reinforcement learning. We show that multiple styles and skills can be learned simultaneously without notable performance differences. Our approach is validated in several real-world experiments with a wheeled-legged quadruped robot.
  arXiv  Detail & Related papers  (2022-03-23T09:24:06Z)
• Data-Driven Reinforcement Learning for Virtual Character Animation Control [0.0]
  Social behaviours are challenging to design reward functions for, due to their lack of physical interaction with the world. We propose RLAnimate, a novel data-driven deep RL approach to address this challenge. We formalise a mathematical structure for training agents by refining the conceptual roles of elements such as agents, environments, states and actions. An agent trained using our approach learns versatile animation dynamics to portray multiple behaviours, using an iterative RL training process.
  arXiv  Detail & Related papers  (2021-04-13T17:05:27Z)
• 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)
• 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)
• Learning Agile Robotic Locomotion Skills by Imitating Animals [72.36395376558984]
  Reproducing the diverse and agile locomotion skills of animals has been a longstanding challenge in robotics. We present an imitation learning system that enables legged robots to learn agile locomotion skills by imitating real-world animals.
  arXiv  Detail & Related papers  (2020-04-02T02:56:16Z)

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.