Learning to infer and manipulate through distributed whole-arm interaction in a soft robot

• URL: http://arxiv.org/abs/2608.30773v1
• Date: Mon, 31 Aug 2026 13:35:00 GMT
• Title: Learning to infer and manipulate through distributed whole-arm interaction in a soft robot
• Abstract summary: In animals such as elephants and octopuses, acquiring non-visual information about an object and physically engaging with it are inseparable processes.<n>We introduce a physical intelligence framework in which distributed compliant interactions jointly reveal task-relevant information and organize manipulation behavior.<n>Key innovations making this possible are (i) a pretrained exploration policy that provides a reference for broad workspace exploration, (ii) joint optimization that integrates exploration and grasping objectives within a single recurrent policy, and (iii) a two-stage sim-to-real adaptation including observation mapping and policy fine-tuning.
• Score: 10.64814207190881
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: In animals such as elephants and octopuses, acquiring non-visual information about an object and physically engaging with it are inseparable processes mediated by rich, large-area interactions between compliant appendages and the environment. Soft robots provide a natural platform for translating this principle into engineered systems. Yet current robotic intelligence makes limited use of physical interaction, treating it primarily as a disturbance to be rejected or, at best, as a means of compensating for object misalignment. Here, we introduce a physical intelligence framework in which distributed compliant interactions jointly reveal task-relevant information and organize manipulation behavior. This results in an intrinsically partially observable problem: key task-relevant information is never measured directly, but must instead be inferred from the history of physical interactions. We propose a reinforcement-learning architecture that addresses this challenge by learning a memory-based control policy end-to-end. The key innovations making this possible are (i) a pretrained exploration policy that provides a reference for broad workspace exploration, (ii) joint optimization that integrates exploration and grasping objectives within a single recurrent policy, and (iii) a two-stage sim-to-real adaptation including observation mapping and policy fine-tuning. We demonstrate this principle through blind whole-arm grasping with a hybrid rigid-soft robotic arm that we equip with IMUs embedded directly within its compliant structure, providing its only source of proprioceptive sensing. The learned policy successfully identifies and grasps various objects by autonomously coordinating workspace exploration, object encounter and localization, inference of grasp-relevant properties, and stable whole-arm wrapping.

Related papers

• Learning Physical Interaction: A Survey of Tactile- and Force-aware Robot Learning [128.76135832773102]
  Physically grounded robot intelligence requires robots to perceive, reason about, and regulate their interactions with the physical world.<n>Recent robot learning methods have made substantial progress by integrating force, tactile, vision, language, and proprioceptive sensing into learned manipulation policies.<n>Despite these advances, existing surveys have not explicitly reviewed force- and tactile-aware robot learning from a unified perspective.
  arXiv  Detail & Related papers  (2026-08-02T14:22:01Z)
• OmniUMI: Towards Physically Grounded Robot Learning via Human-Aligned Multimodal Interaction [41.5123936517904]
  UMI-style interfaces enable scalable robot learning, but existing systems remain largely visuomotor.<n>We present OmniUMI, a unified framework for physically grounded robot learning via human-aligned multimodal interaction.
  arXiv  Detail & Related papers  (2026-04-12T13:48:48Z)
• InterReal: A Unified Physics-Based Imitation Framework for Learning Human-Object Interaction Skills [16.31202379413011]
  We develop a unified physics-based imitation learning framework for Real-world human-object Interaction (HOI) control.<n>InterReal enables humanoid robots to track HOI reference motions, facilitating the learning of fine-grained interactive skills.<n>A meta-policy guided by critical tracking error metrics explores and allocates reward signals to the low-level reinforcement learning objective.
  arXiv  Detail & Related papers  (2026-03-08T07:44:35Z)
• InterPrior: Scaling Generative Control for Physics-Based Human-Object Interactions [58.329946838699044]
  Humans rarely plan whole-body interactions with objects at the level of explicit whole-body movements.<n>Scaling such priors is key to enabling humanoids to compose and generalize loco-manipulation skills.<n>We introduce InterPrior, a framework that learns a unified generative controller through large-scale imitation pretraining and post-training by reinforcement learning.
  arXiv  Detail & Related papers  (2026-02-05T18:59:27Z)
• Executable Analytic Concepts as the Missing Link Between VLM Insight and Precise Manipulation [70.8381970762877]
  Vision-Language Models (VLMs) have demonstrated remarkable capabilities in semantic reasoning and task planning.<n>We introduce GRACE, a novel framework that grounds VLM-based reasoning through executable analytic concepts.<n>G GRACE provides a unified and interpretable interface between high-level instruction understanding and low-level robot control.
  arXiv  Detail & Related papers  (2025-10-09T09:08:33Z)
• Learning Video Generation for Robotic Manipulation with Collaborative Trajectory Control [72.00655365269]
  We present RoboMaster, a novel framework that models inter-object dynamics through a collaborative trajectory formulation.<n>Unlike prior methods that decompose objects, our core is to decompose the interaction process into three sub-stages: pre-interaction, interaction, and post-interaction.<n>Our method outperforms existing approaches, establishing new state-of-the-art performance in trajectory-controlled video generation for robotic manipulation.
  arXiv  Detail & Related papers  (2025-06-02T17:57:06Z)
• Learning Where to Look: Self-supervised Viewpoint Selection for Active Localization using Geometrical Information [68.10033984296247]
  This paper explores the domain of active localization, emphasizing the importance of viewpoint selection to enhance localization accuracy. Our contributions involve using a data-driven approach with a simple architecture designed for real-time operation, a self-supervised data training method, and the capability to consistently integrate our map into a planning framework tailored for real-world robotics applications.
  arXiv  Detail & Related papers  (2024-07-22T12:32:09Z)
• Learning Manipulation by Predicting Interaction [85.57297574510507]
  We propose a general pre-training pipeline that learns Manipulation by Predicting the Interaction. The experimental results demonstrate that MPI exhibits remarkable improvement by 10% to 64% compared with previous state-of-the-art in real-world robot platforms.
  arXiv  Detail & Related papers  (2024-06-01T13:28:31Z)
• GEARS: Local Geometry-aware Hand-object Interaction Synthesis [38.75942505771009]
  We introduce a novel joint-centered sensor designed to reason about local object geometry near potential interaction regions. As an important step towards mitigating the learning complexity, we transform the points from global frame to template hand frame and use a shared module to process sensor features of each individual joint. This is followed by a perceptual-temporal transformer network aimed at capturing correlation among the joints in different dimensions.
  arXiv  Detail & Related papers  (2024-04-02T09:18:52Z)
• Learning Extrinsic Dexterity with Parameterized Manipulation Primitives [8.7221770019454]
  We learn a sequence of actions that utilize the environment to change the object's pose. Our approach can control the object's state through exploiting interactions between the object, the gripper, and the environment. We evaluate our approach on picking box-shaped objects of various weight, shape, and friction properties from a constrained table-top workspace.
  arXiv  Detail & Related papers  (2023-10-26T21:28:23Z)
• Physically Plausible Full-Body Hand-Object Interaction Synthesis [32.83908152822006]
  We propose a physics-based method for synthesizing dexterous hand-object interactions in a full-body setting. Existing methods often focus on isolated segments of the interaction process and rely on data-driven techniques that may result in artifacts.
  arXiv  Detail & Related papers  (2023-09-14T17:55:18Z)

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.