mlsanityData to 7 Oct 2026

RUMI: Rummaging Using Mutual Information

arXiv 2408.10450 ↗First posted 19 Aug 2024cs.RO cs.AIcited by 0

Not on the map. Why?

Abstract (arXiv)

This paper presents Rummaging Using Mutual Information (RUMI), a method for online generation of robot action sequences to gather information about the pose of a known movable object in visually-occluded environments. Focusing on contact-rich rummaging, our approach leverages mutual information between the object pose distribution and robot trajectory for action planning. From an observed partial point cloud, RUMI deduces the compatible object pose distribution and approximates the mutual information of it with workspace occupancy in real time. Based on this, we develop an information gain cost function and a reachability cost function to keep the object within the robot's reach. These are integrated into a model predictive control (MPC) framework with a stochastic dynamics model, updating the pose distribution in a closed loop. Key contributions include a new belief framework for object pose estimation, an efficient information gain computation strategy, and a robust MPC-based control scheme. RUMI demonstrates superior performance in both simulated and real tasks compared to baseline methods.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 19 of its 58 references that are in the map. First posted on arXiv 19 Aug 2024.

Builds on

19 of 58 references.

References · 19

  1. 2017Reinforcement Learning with Deep Energy-Based Policiescited by 659
  2. 2019PoseRBPF: A Rao-Blackwellized Particle Filter for 6D Object Pose Trackingcited by 91
  3. 2016Revisiting Active Perceptioncited by 90
  4. 2016Interactive Perception: Leveraging Action in Perception and Perception in Actioncited by 77
  5. 2022Uncertainty Guided Policy for Active Robotic 3D Reconstruction using Neural Radiance Fieldscited by 53
  6. 2021Active 3D Shape Reconstruction from Vision and Touchcited by 34
  7. 2022MidasTouch: Monte-Carlo inference over distributions across sliding touchcited by 33
  8. 2019Mechanical Search: Multi-Step Retrieval of a Target Object Occluded by Cluttercited by 30
  9. 2021On the Properties of Kullback-Leibler Divergence Between Multivariate Gaussian Distributionscited by 22
  10. 2020Soft-Bubble grippers for robust and perceptive manipulationcited by 18
  11. 2022Active Visuo-Haptic Object Shape Completioncited by 11
  12. 2019A pressure field model for fast, robust approximation of net contact force and moment between nominally rigid objectscited by 8
7 more
  1. 2019Informative Path Planning for Active Field Mapping under Localization Uncertaintycited by 6
  2. 2013Multi-Robot Informative Path Planning for Active Sensing of Environmental Phenomena: A Tale of Two Algorithmscited by 5
  3. 2021Velocity Level Approximation of Pressure Field Contact Patchescited by 5
  4. 2022Soft Tracking Using Contacts for Cluttered Objects to Perform Blind Object Retrievalcited by 5
  5. 2023CHSEL: Producing Diverse Plausible Pose Estimates from Contact and Free Space Datacited by 3
  6. 2018Active Exploration Using Gaussian Random Fields and Gaussian Process Implicit Surfacescited by 1
  7. 2024Spline-Interpolated Model Predictive Path Integral Control with Stein Variational Inference for Reactive Navigationcited by 1

Built on by

Not cited yet.