# Active Learning of Abstract Plan Feasibility

arXiv: https://arxiv.org/abs/2107.00683 · HTML: https://mlsanity.com/paper/2107.00683/

## Key facts

- Cited by 11 papers in the map (data through 14 Oct 2026).
- Builds on 16 of its 43 references that are in the map.
- First posted on arXiv 1 Jul 2021.

## Builds on (most cited first, 16 of 16)

- [Dropout as a Bayesian Approximation: Representing Model Uncertainty in Deep Learning](https://mlsanity.com/paper/1506.02142/) (2015)
- [Graph Neural Networks: A Review of Methods and Applications](https://mlsanity.com/paper/1812.08434/) (2018)
- [Deep Bayesian Active Learning with Image Data](https://mlsanity.com/paper/1703.02910/) (2017)
- [Interaction Networks for Learning about Objects, Relations and Physics](https://mlsanity.com/paper/1612.00222/) (2016)
- [Self-Supervised Exploration via Disagreement](https://mlsanity.com/paper/1906.04161/) (2019)
- [Graph networks as learnable physics engines for inference and control](https://mlsanity.com/paper/1806.01242/) (2018)
- [PDDLStream: Integrating Symbolic Planners and Blackbox Samplers via Optimistic Adaptive Planning](https://mlsanity.com/paper/1802.08705/) (2018)
- [A Compositional Object-Based Approach to Learning Physical Dynamics](https://mlsanity.com/paper/1612.00341/) (2016)
- [Model-Based Active Exploration](https://mlsanity.com/paper/1810.12162/) (2018)
- [Learning Physical Intuition of Block Towers by Example](https://mlsanity.com/paper/1603.01312/) (2016)
- [ShapeStacks: Learning Vision-Based Physical Intuition for Generalised Object Stacking](https://mlsanity.com/paper/1804.08018/) (2018)
- [Relational inductive bias for physical construction in humans and machines](https://mlsanity.com/paper/1806.01203/) (2018)
- [Active model learning and diverse action sampling for task and motion planning](https://mlsanity.com/paper/1803.00967/) (2018)
- [Learning sparse relational transition models](https://mlsanity.com/paper/1810.11177/) (2018)
- [The Provable Virtue of Laziness in Motion Planning](https://mlsanity.com/paper/1710.04101/) (2017)
- [Probabilistic Framework for Constrained Manipulations and Task and Motion Planning under Uncertainty](https://mlsanity.com/paper/2003.04259/) (2020)

## Built on by (most cited first, 11 of 11)

- [Beyond Pick-and-Place: Tackling Robotic Stacking of Diverse Shapes](https://mlsanity.com/paper/2110.06192/) (2021)
- [LLM3:Large Language Model-based Task and Motion Planning with Motion Failure Reasoning](https://mlsanity.com/paper/2403.11552/) (2024)
- [Practice Makes Perfect: Planning to Learn Skill Parameter Policies](https://mlsanity.com/paper/2402.15025/) (2024)
- [A Survey of Optimization-based Task and Motion Planning: From Classical To Learning Approaches](https://mlsanity.com/paper/2404.02817/) (2024)
- [Learning Efficient Abstract Planning Models that Choose What to Predict](https://mlsanity.com/paper/2208.07737/) (2022)
- [Embodied Active Learning of Relational State Abstractions for Bilevel Planning](https://mlsanity.com/paper/2303.04912/) (2023)
- [Graph-based Reinforcement Learning meets Mixed Integer Programs: An application to 3D robot assembly discovery](https://mlsanity.com/paper/2203.04120/) (2022)
- [Task and Motion Planning for Execution in the Real](https://mlsanity.com/paper/2406.03641/) (2024)
- [ORLA*: Mobile Manipulator-Based Object Rearrangement with Lazy A Star](https://mlsanity.com/paper/2309.13707/) (2023)
- [Tactile Estimation of Extrinsic Contact Patch for Stable Placement](https://mlsanity.com/paper/2309.14552/) (2023)
- [Neurosymbolic Reasoning with Incremental Knowledge for Sample Efficient Hierarchical Reinforcement Learning](https://mlsanity.com/paper/2608.02993/) (2026)

## Abstract (arXiv)

Long horizon sequential manipulation tasks are effectively addressed hierarchically: at a high level of abstraction the planner searches over abstract action sequences, and when a plan is found, lower level motion plans are generated. Such a strategy hinges on the ability to reliably predict that a feasible low level plan will be found which satisfies the abstract plan. However, computing Abstract Plan Feasibility (APF) is difficult because the outcome of a plan depends on real-world phenomena that are difficult to model, such as noise in estimation and execution. In this work, we present an active learning approach to efficiently acquire an APF predictor through task-independent, curious exploration on a robot. The robot identifies plans whose outcomes would be informative about APF, executes those plans, and learns from their successes or failures. Critically, we leverage an infeasible subsequence property to prune candidate plans in the active learning strategy, allowing our system to learn from less data. We evaluate our strategy in simulation and on a real Franka Emika Panda robot with integrated perception, experimentation, planning, and execution. In a stacking domain where objects have non-uniform mass distributions, we show that our system permits real robot learning of an APF model in four hundred self-supervised interactions, and that our learned model can be used effectively in multiple downstream tasks.