Learning Robot Manipulation from Audio World Models

• URL: http://arxiv.org/abs/2512.08405v1
• Date: Tue, 09 Dec 2025 09:36:51 GMT
• Title: Learning Robot Manipulation from Audio World Models
• Abstract summary: We propose a generative latent flow matching model to anticipate future audio observations.<n>We demonstrate the superior capabilities of our system through two manipulation tasks.
• Score: 7.51335919610328
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: World models have demonstrated impressive performance on robotic learning tasks. Many such tasks inherently demand multimodal reasoning; for example, filling a bottle with water will lead to visual information alone being ambiguous or incomplete, thereby requiring reasoning over the temporal evolution of audio, accounting for its underlying physical properties and pitch patterns. In this paper, we propose a generative latent flow matching model to anticipate future audio observations, enabling the system to reason about long-term consequences when integrated into a robot policy. We demonstrate the superior capabilities of our system through two manipulation tasks that require perceiving in-the-wild audio or music signals, compared to methods without future lookahead. We further emphasize that successful robot action learning for these tasks relies not merely on multi-modal input, but critically on the accurate prediction of future audio states that embody intrinsic rhythmic patterns.

Related papers

• $π_0$: A Vision-Language-Action Flow Model for General Robot Control [77.32743739202543]
  We propose a novel flow matching architecture built on top of a pre-trained vision-language model (VLM) to inherit Internet-scale semantic knowledge. We evaluate our model in terms of its ability to perform tasks in zero shot after pre-training, follow language instructions from people, and its ability to acquire new skills via fine-tuning.
  arXiv  Detail & Related papers  (2024-10-31T17:22:30Z)
• RoboPack: Learning Tactile-Informed Dynamics Models for Dense Packing [38.97168020979433]
  We introduce an approach that combines visual and tactile sensing for robotic manipulation by learning a neural, tactile-informed dynamics model. Our proposed framework, RoboPack, employs a recurrent graph neural network to estimate object states. We demonstrate our approach on a real robot equipped with a compliant Soft-Bubble tactile sensor on non-prehensile manipulation and dense packing tasks.
  arXiv  Detail & Related papers  (2024-07-01T16:08:37Z)
• ManiWAV: Learning Robot Manipulation from In-the-Wild Audio-Visual Data [28.36623343236893]
  We introduce ManiWAV: an 'ear-in-hand' data collection device to collect in-the-wild human demonstrations with synchronous audio and visual feedback. We show that our system can generalize to unseen in-the-wild environments by learning from diverse in-the-wild human demonstrations.
  arXiv  Detail & Related papers  (2024-06-27T18:06:38Z)
• Mastering Robot Manipulation with Multimodal Prompts through Pretraining and Multi-task Fine-tuning [49.92517970237088]
  We tackle the problem of training a robot to understand multimodal prompts. This type of task poses a major challenge to robots' capability to understand the interconnection and complementarity between vision and language signals. We introduce an effective framework that learns a policy to perform robot manipulation with multimodal prompts.
  arXiv  Detail & Related papers  (2023-10-14T22:24:58Z)
• Play it by Ear: Learning Skills amidst Occlusion through Audio-Visual Imitation Learning [62.83590925557013]
  We learn a set of challenging partially-observed manipulation tasks from visual and audio inputs. Our proposed system learns these tasks by combining offline imitation learning from tele-operated demonstrations and online finetuning. In a set of simulated tasks, we find that our system benefits from using audio, and that by using online interventions we are able to improve the success rate of offline imitation learning by 20%.
  arXiv  Detail & Related papers  (2022-05-30T04:52:58Z)
• Lifelong Robotic Reinforcement Learning by Retaining Experiences [61.79346922421323]
  Many multi-task reinforcement learning efforts assume the robot can collect data from all tasks at all times. In this work, we study a practical sequential multi-task RL problem motivated by the practical constraints of physical robotic systems. We derive an approach that effectively leverages the data and policies learned for previous tasks to cumulatively grow the robot's skill-set.
  arXiv  Detail & Related papers  (2021-09-19T18:00:51Z)
• Future Frame Prediction for Robot-assisted Surgery [57.18185972461453]
  We propose a ternary prior guided variational autoencoder (TPG-VAE) model for future frame prediction in robotic surgical video sequences. Besides content distribution, our model learns motion distribution, which is novel to handle the small movements of surgical tools.
  arXiv  Detail & Related papers  (2021-03-18T15:12:06Z)
• Learning from Demonstration with Weakly Supervised Disentanglement [19.292205450379996]
  We treat the task of interpretable learning from demonstration as an optimisation problem over a probabilistic generative model. We show that such alignment is best achieved through the use of labels from the end user, in an appropriately restricted vocabulary. Our approach is evaluated in the context of two table-top robot manipulation tasks performed by a PR2 robot.
  arXiv  Detail & Related papers  (2020-06-16T12:29:51Z)
• Understanding Contexts Inside Robot and Human Manipulation Tasks through a Vision-Language Model and Ontology System in a Video Stream [4.450615100675747]
  We present a vision dataset under a strictly constrained knowledge domain for both robot and human manipulations. We propose a scheme to generate a combination of visual attentions and an evolving knowledge graph filled with commonsense knowledge. The proposed scheme allows the robot to mimic human-like intentional behaviors by watching real-time videos.
  arXiv  Detail & Related papers  (2020-03-02T19:48:59Z)
• Learning Predictive Models From Observation and Interaction [137.77887825854768]
  Learning predictive models from interaction with the world allows an agent, such as a robot, to learn about how the world works. However, learning a model that captures the dynamics of complex skills represents a major challenge. We propose a method to augment the training set with observational data of other agents, such as humans.
  arXiv  Detail & Related papers  (2019-12-30T01:10:41Z)

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.