# Learning to Double Guess: An Active Perception Approach for Estimating the Center of Mass of Arbitrary Objects

arXiv: https://arxiv.org/abs/2502.02663 · HTML: https://mlsanity.com/paper/2502.02663/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 15 of its 30 references that are in the map.
- First posted on arXiv 4 Feb 2025.

## Builds on (most cited first, 15 of 15)

- [On the Variance of the Adaptive Learning Rate and Beyond](https://mlsanity.com/paper/1908.03265/) (2019)
- [Weight Uncertainty in Neural Networks](https://mlsanity.com/paper/1505.05424/) (2015)
- [Pyro: Deep Universal Probabilistic Programming](https://mlsanity.com/paper/1810.09538/) (2018)
- [TossingBot: Learning to Throw Arbitrary Objects with Residual Physics](https://mlsanity.com/paper/1903.11239/) (2019)
- [Active Clothing Material Perception using Tactile Sensing and Deep Learning](https://mlsanity.com/paper/1711.00574/) (2017)
- [SwingBot: Learning Physical Features from In-hand Tactile Exploration for Dynamic Swing-up Manipulation](https://mlsanity.com/paper/2101.11812/) (2021)
- [TANDEM3D: Active Tactile Exploration for 3D Object Recognition](https://mlsanity.com/paper/2209.08772/) (2022)
- [Grasp Stability Prediction with Sim-to-Real Transfer from Tactile Sensing](https://mlsanity.com/paper/2208.02885/) (2022)
- [Understanding Dynamic Tactile Sensing for Liquid Property Estimation](https://mlsanity.com/paper/2205.08771/) (2022)
- [Interactive Learning of Physical Object Properties Through Robot Manipulation and Database of Object Measurements](https://mlsanity.com/paper/2404.07344/) (2024)
- [PoseIt: A Visual-Tactile Dataset of Holding Poses for Grasp Stability Analysis](https://mlsanity.com/paper/2209.05022/) (2022)
- [An Intelligent Robotic System for Perceptive Pancake Batter Stirring and Precise Pouring](https://mlsanity.com/paper/2407.01755/) (2024)
- [Estimating Properties of Solid Particles Inside Container Using Touch Sensing](https://mlsanity.com/paper/2307.15646/) (2023)
- [Kitchen Artist: Precise Control of Liquid Dispensing for Gourmet Plating](https://mlsanity.com/paper/2311.12185/) (2023)
- [Active Exploration for Real-Time Haptic Training](https://mlsanity.com/paper/2405.11776/) (2024)

## Abstract (arXiv)

Manipulating arbitrary objects in unstructured environments is a significant challenge in robotics, primarily due to difficulties in determining an object's center of mass. This paper introduces U-GRAPH: Uncertainty-Guided Rotational Active Perception with Haptics, a novel framework to enhance the center of mass estimation using active perception. Traditional methods often rely on single interaction and are limited by the inherent inaccuracies of Force-Torque (F/T) sensors. Our approach circumvents these limitations by integrating a Bayesian Neural Network (BNN) to quantify uncertainty and guide the robotic system through multiple, information-rich interactions via grid search and a neural network that scores each action. We demonstrate the remarkable generalizability and transferability of our method with training on a small dataset with limited variation yet still perform well on unseen complex real-world objects.