# Exploratory Grasping: Asymptotically Optimal Algorithms for Grasping Challenging Polyhedral Objects

arXiv: https://arxiv.org/abs/2011.05632 · HTML: https://mlsanity.com/paper/2011.05632/

## Key facts

- Cited by 9 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 11 Nov 2020.

## Built on by (most cited first, 9 of 9)

- [Robot Learning with Sensorimotor Pre-training](https://mlsanity.com/paper/2306.10007/) (2023)
- [On Robot Grasp Learning Using Equivariant Models](https://mlsanity.com/paper/2306.06489/) (2023)
- [Uncertainty-driven Exploration Strategies for Online Grasp Learning](https://mlsanity.com/paper/2309.12038/) (2023)
- [Kit-Net: Self-Supervised Learning to Kit Novel 3D Objects into Novel 3D Cavities](https://mlsanity.com/paper/2107.05789/) (2021)
- [Information-driven Affordance Discovery for Efficient Robotic Manipulation](https://mlsanity.com/paper/2405.03865/) (2024)
- [Pseudo-Labeling and Contextual Curriculum Learning for Online Grasp Learning in Robotic Bin Picking](https://mlsanity.com/paper/2403.02495/) (2024)
- [EXOT: Exit-aware Object Tracker for Safe Robotic Manipulation of Moving Object](https://mlsanity.com/paper/2306.05262/) (2023)
- [Connectivity-Aware Exploration of Robotic Grasp Spaces](https://mlsanity.com/paper/2609.22983/) (2026)
- [Continual Learning for 6-DoF Grasp Synthesis via Experience and Demonstrations](https://mlsanity.com/paper/2610.01301/) (2026)

## Abstract (arXiv)

There has been significant recent work on data-driven algorithms for learning general-purpose grasping policies. However, these policies can consistently fail to grasp challenging objects which are significantly out of the distribution of objects in the training data or which have very few high quality grasps. Motivated by such objects, we propose a novel problem setting, Exploratory Grasping, for efficiently discovering reliable grasps on an unknown polyhedral object via sequential grasping, releasing, and toppling. We formalize Exploratory Grasping as a Markov Decision Process, study the theoretical complexity of Exploratory Grasping in the context of reinforcement learning and present an efficient bandit-style algorithm, Bandits for Online Rapid Grasp Exploration Strategy (BORGES), which leverages the structure of the problem to efficiently discover high performing grasps for each object stable pose. BORGES can be used to complement any general-purpose grasping algorithm with any grasp modality (parallel-jaw, suction, multi-fingered, etc) to learn policies for objects in which they exhibit persistent failures. Simulation experiments suggest that BORGES can significantly outperform both general-purpose grasping pipelines and two other online learning algorithms and achieves performance within 5% of the optimal policy within 1000 and 8000 timesteps on average across 46 challenging objects from the Dex-Net adversarial and EGAD! object datasets, respectively. Initial physical experiments suggest that BORGES can improve grasp success rate by 45% over a Dex-Net baseline with just 200 grasp attempts in the real world. See https://tinyurl.com/exp-grasping for supplementary material and videos.