Grounding Video Models to Actions through Goal Conditioned Exploration

• URL: http://arxiv.org/abs/2411.07223v1
• Date: Mon, 11 Nov 2024 18:43:44 GMT
• Title: Grounding Video Models to Actions through Goal Conditioned Exploration
• Authors: Yunhao Luo, Yilun Du,
• Abstract summary: We propose a framework that uses trajectory level action generation in combination with video guidance to enable an agent to solve complex tasks. We show how our approach is on par with or even surpasses multiple behavior cloning baselines trained on expert demonstrations.
• Score: 29.050431676226115
• License:
• Abstract: Large video models, pretrained on massive amounts of Internet video, provide a rich source of physical knowledge about the dynamics and motions of objects and tasks. However, video models are not grounded in the embodiment of an agent, and do not describe how to actuate the world to reach the visual states depicted in a video. To tackle this problem, current methods use a separate vision-based inverse dynamic model trained on embodiment-specific data to map image states to actions. Gathering data to train such a model is often expensive and challenging, and this model is limited to visual settings similar to the ones in which data are available. In this paper, we investigate how to directly ground video models to continuous actions through self-exploration in the embodied environment -- using generated video states as visual goals for exploration. We propose a framework that uses trajectory level action generation in combination with video guidance to enable an agent to solve complex tasks without any external supervision, e.g., rewards, action labels, or segmentation masks. We validate the proposed approach on 8 tasks in Libero, 6 tasks in MetaWorld, 4 tasks in Calvin, and 12 tasks in iThor Visual Navigation. We show how our approach is on par with or even surpasses multiple behavior cloning baselines trained on expert demonstrations while without requiring any action annotations.

Related papers

• AICL: Action In-Context Learning for Video Diffusion Model [124.39948693332552]
  We propose AICL, which empowers the generative model with the ability to understand action information in reference videos. Extensive experiments demonstrate that AICL effectively captures the action and achieves state-of-the-art generation performance.
  arXiv  Detail & Related papers  (2024-03-18T07:41:19Z)
• 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)
• Learning to Act from Actionless Videos through Dense Correspondences [87.1243107115642]
  We present an approach to construct a video-based robot policy capable of reliably executing diverse tasks across different robots and environments. Our method leverages images as a task-agnostic representation, encoding both the state and action information, and text as a general representation for specifying robot goals. We demonstrate the efficacy of our approach in learning policies on table-top manipulation and navigation tasks.
  arXiv  Detail & Related papers  (2023-10-12T17:59:23Z)
• Look, Remember and Reason: Grounded reasoning in videos with language models [5.3445140425713245]
  Multi-temporal language models (LM) have recently shown promising performance in high-level reasoning tasks on videos. We propose training an LM end-to-end on low-level surrogate tasks, including object detection, re-identification, tracking, to endow the model with the required low-level visual capabilities. We demonstrate the effectiveness of our framework on diverse visual reasoning tasks from the ACRE, CATER, Something-Else and STAR datasets.
  arXiv  Detail & Related papers  (2023-06-30T16:31:14Z)
• Dense Video Object Captioning from Disjoint Supervision [77.47084982558101]
  We propose a new task and model for dense video object captioning. This task unifies spatial and temporal localization in video. We show how our model improves upon a number of strong baselines for this new task.
  arXiv  Detail & Related papers  (2023-06-20T17:57:23Z)
• Learn the Force We Can: Enabling Sparse Motion Control in Multi-Object Video Generation [26.292052071093945]
  We propose an unsupervised method to generate videos from a single frame and a sparse motion input. Our trained model can generate unseen realistic object-to-object interactions. We show that YODA is on par with or better than state of the art video generation prior work in terms of both controllability and video quality.
  arXiv  Detail & Related papers  (2023-06-06T19:50:02Z)
• Multi-Task Learning of Object State Changes from Uncurated Videos [55.60442251060871]
  We learn to temporally localize object state changes by observing people interacting with objects in long uncurated web videos. We show that our multi-task model achieves a relative improvement of 40% over the prior single-task methods. We also test our method on long egocentric videos of the EPIC-KITCHENS and the Ego4D datasets in a zero-shot setup.
  arXiv  Detail & Related papers  (2022-11-24T09:42:46Z)
• Model-Based Visual Planning with Self-Supervised Functional Distances [104.83979811803466]
  We present a self-supervised method for model-based visual goal reaching. Our approach learns entirely using offline, unlabeled data. We find that this approach substantially outperforms both model-free and model-based prior methods.
  arXiv  Detail & Related papers  (2020-12-30T23:59:09Z)

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.