M2R2: MulitModal Robotic Representation for Temporal Action Segmentation

• URL: http://arxiv.org/abs/2504.18662v1
• Date: Fri, 25 Apr 2025 19:36:17 GMT
• Title: M2R2: MulitModal Robotic Representation for Temporal Action Segmentation
• Authors: Daniel Sliwowski, Dongheui Lee,
• Abstract summary: We introduce a novel pretraining strategy that enables the reuse of learned features across multiple TAS models.<n>Our method achieves state-of-the-art performance on the REASSEMBLE dataset, outperforming existing robotic action segmentation models by 46.6%.
• Score: 9.64001633229156
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Temporal action segmentation (TAS) has long been a key area of research in both robotics and computer vision. In robotics, algorithms have primarily focused on leveraging proprioceptive information to determine skill boundaries, with recent approaches in surgical robotics incorporating vision. In contrast, computer vision typically relies on exteroceptive sensors, such as cameras. Existing multimodal TAS models in robotics integrate feature fusion within the model, making it difficult to reuse learned features across different models. Meanwhile, pretrained vision-only feature extractors commonly used in computer vision struggle in scenarios with limited object visibility. In this work, we address these challenges by proposing M2R2, a multimodal feature extractor tailored for TAS, which combines information from both proprioceptive and exteroceptive sensors. We introduce a novel pretraining strategy that enables the reuse of learned features across multiple TAS models. Our method achieves state-of-the-art performance on the REASSEMBLE dataset, a challenging multimodal robotic assembly dataset, outperforming existing robotic action segmentation models by 46.6%. Additionally, we conduct an extensive ablation study to evaluate the contribution of different modalities in robotic TAS tasks.

Related papers

• VidBot: Learning Generalizable 3D Actions from In-the-Wild 2D Human Videos for Zero-Shot Robotic Manipulation [53.63540587160549]
  VidBot is a framework enabling zero-shot robotic manipulation using learned 3D affordance from in-the-wild monocular RGB-only human videos. VidBot paves the way for leveraging everyday human videos to make robot learning more scalable.
  arXiv  Detail & Related papers  (2025-03-10T10:04:58Z)
• RoboBrain: A Unified Brain Model for Robotic Manipulation from Abstract to Concrete [27.814422322892522]
  Multimodal Large Language Models (MLLMs) have shown remarkable capabilities across various multimodal contexts. They lack three essential robotic brain capabilities: Planning Capability, Affordance Perception, and Trajectory Prediction. We introduce ShareRobot, a dataset that labels multi-dimensional information such as task planning, object affordance, and end-effector trajectory. We develop RoboBrain, an MLLM-based model that combines robotic and general multi-modal data, utilizing a multi-stage training strategy.
  arXiv  Detail & Related papers  (2025-02-28T17:30:39Z)
• SKT: Integrating State-Aware Keypoint Trajectories with Vision-Language Models for Robotic Garment Manipulation [82.61572106180705]
  This paper presents a unified approach using vision-language models (VLMs) to improve keypoint prediction across various garment categories. We created a large-scale synthetic dataset using advanced simulation techniques, allowing scalable training without extensive real-world data. Experimental results indicate that the VLM-based method significantly enhances keypoint detection accuracy and task success rates.
  arXiv  Detail & Related papers  (2024-09-26T17:26:16Z)
• LLARVA: Vision-Action Instruction Tuning Enhances Robot Learning [50.99807031490589]
  We introduce LLARVA, a model trained with a novel instruction tuning method to unify a range of robotic learning tasks, scenarios, and environments. We generate 8.5M image-visual trace pairs from the Open X-Embodiment dataset in order to pre-train our model. Experiments yield strong performance, demonstrating that LLARVA performs well compared to several contemporary baselines.
  arXiv  Detail & Related papers  (2024-06-17T17:55:29Z)
• 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)
• Transferring Foundation Models for Generalizable Robotic Manipulation [82.12754319808197]
  We propose a novel paradigm that effectively leverages language-reasoning segmentation mask generated by internet-scale foundation models.<n>Our approach can effectively and robustly perceive object pose and enable sample-efficient generalization learning.<n>Demos can be found in our submitted video, and more comprehensive ones can be found in link1 or link2.
  arXiv  Detail & Related papers  (2023-06-09T07:22:12Z)
• RT-1: Robotics Transformer for Real-World Control at Scale [98.09428483862165]
  We present a model class, dubbed Robotics Transformer, that exhibits promising scalable model properties. We verify our conclusions in a study of different model classes and their ability to generalize as a function of the data size, model size, and data diversity based on a large-scale data collection on real robots performing real-world tasks.
  arXiv  Detail & Related papers  (2022-12-13T18:55:15Z)
• PACT: Perception-Action Causal Transformer for Autoregressive Robotics Pre-Training [25.50131893785007]
  This work introduces a paradigm for pre-training a general purpose representation that can serve as a starting point for multiple tasks on a given robot. We present the Perception-Action Causal Transformer (PACT), a generative transformer-based architecture that aims to build representations directly from robot data in a self-supervised fashion. We show that finetuning small task-specific networks on top of the larger pretrained model results in significantly better performance compared to training a single model from scratch for all tasks simultaneously.
  arXiv  Detail & Related papers  (2022-09-22T16:20:17Z)
• MetaGraspNet: A Large-Scale Benchmark Dataset for Vision-driven Robotic Grasping via Physics-based Metaverse Synthesis [78.26022688167133]
  We present a large-scale benchmark dataset for vision-driven robotic grasping via physics-based metaverse synthesis. The proposed dataset contains 100,000 images and 25 different object types. We also propose a new layout-weighted performance metric alongside the dataset for evaluating object detection and segmentation performance.
  arXiv  Detail & Related papers  (2021-12-29T17:23:24Z)
• AP-MTL: Attention Pruned Multi-task Learning Model for Real-time Instrument Detection and Segmentation in Robot-assisted Surgery [23.33984309289549]
  Training a real-time robotic system for the detection and segmentation of high-resolution images provides a challenging problem with the limited computational resource. We develop a novel end-to-end trainable real-time Multi-Task Learning model with weight-shared encoder and task-aware detection and segmentation decoders. Our model significantly outperforms state-of-the-art segmentation and detection models, including best-performed models in the challenge.
  arXiv  Detail & Related papers  (2020-03-10T14:24:51Z)

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.