# Representation, learning, and planning algorithms for geometric task and motion planning

arXiv: https://arxiv.org/abs/2203.04605 · HTML: https://mlsanity.com/paper/2203.04605/

## Key facts

- Cited by 8 papers in the map (data through 14 Oct 2026).
- Builds on 19 of its 59 references that are in the map.
- First posted on arXiv 9 Mar 2022.

## Builds on (most cited first, 19 of 19)

- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [Semi-Supervised Classification with Graph Convolutional Networks](https://mlsanity.com/paper/1609.02907/) (2016)
- [Generative Adversarial Networks](https://mlsanity.com/paper/2203.00667/) (2022)
- [Auto-Encoding Variational Bayes](https://mlsanity.com/paper/1312.6114/) (2013)
- [Neural Message Passing for Quantum Chemistry](https://mlsanity.com/paper/1704.01212/) (2017)
- [Continuous control with deep reinforcement learning](https://mlsanity.com/paper/1509.02971/) (2015)
- [A Comprehensive Survey on Graph Neural Networks](https://mlsanity.com/paper/1901.00596/) (2019)
- [Improved Training of Wasserstein GANs](https://mlsanity.com/paper/1704.00028/) (2017)
- [Graph Neural Networks: A Review of Methods and Applications](https://mlsanity.com/paper/1812.08434/) (2018)
- [Relational inductive biases, deep learning, and graph networks](https://mlsanity.com/paper/1806.01261/) (2018)
- [Integrated Task and Motion Planning](https://mlsanity.com/paper/2010.01083/) (2020)
- [MMD GAN: Towards Deeper Understanding of Moment Matching Network](https://mlsanity.com/paper/1705.08584/) (2017)
- [Online Replanning in Belief Space for Partially Observable Task and Motion Problems](https://mlsanity.com/paper/1911.04577/) (2019)
- [Deep Visual Reasoning: Learning to Predict Action Sequences for Task and Motion Planning from an Initial Scene Image](https://mlsanity.com/paper/2006.05398/) (2020)
- [FFRob: Leveraging Symbolic Planning for Efficient Task and Motion Planning](https://mlsanity.com/paper/1608.01335/) (2016)
- [Learning to guide task and motion planning using score-space representation](https://mlsanity.com/paper/1807.09962/) (2018)
- [Learning to Rank for Synthesizing Planning Heuristics](https://mlsanity.com/paper/1608.01302/) (2016)
- [CAMPs: Learning Context-Specific Abstractions for Efficient Planning in Factored MDPs](https://mlsanity.com/paper/2007.13202/) (2020)
- [Learning Quickly to Plan Quickly Using Modular Meta-Learning](https://mlsanity.com/paper/1809.07878/) (2018)

## Built on by (most cited first, 8 of 8)

- [Text2Motion: From Natural Language Instructions to Feasible Plans](https://mlsanity.com/paper/2303.12153/) (2023)
- [ORGANA: A Robotic Assistant for Automated Chemistry Experimentation and Characterization](https://mlsanity.com/paper/2401.06949/) (2024)
- [Human-in-the-Loop Task and Motion Planning for Imitation Learning](https://mlsanity.com/paper/2310.16014/) (2023)
- [Embodied Lifelong Learning for Task and Motion Planning](https://mlsanity.com/paper/2307.06870/) (2023)
- [NOD-TAMP: Generalizable Long-Horizon Planning with Neural Object Descriptors](https://mlsanity.com/paper/2311.01530/) (2023)
- [Prime the search: Using large language models for guiding geometric task and motion planning by warm-starting tree search](https://mlsanity.com/paper/2506.07062/) (2025)
- [Improving Reliable Navigation under Uncertainty via Predictions Informed by Non-Local Information](https://mlsanity.com/paper/2307.14501/) (2023)
- [OrbitTAMP: Grounding Language Models for Task and Motion Planning in Spacecraft Rendezvous](https://mlsanity.com/paper/2610.01093/) (2026)

## Abstract (arXiv)

We present a framework for learning to guide geometric task and motion planning (GTAMP). GTAMP is a subclass of task and motion planning in which the goal is to move multiple objects to target regions among movable obstacles. A standard graph search algorithm is not directly applicable, because GTAMP problems involve hybrid search spaces and expensive action feasibility checks. To handle this, we introduce a novel planner that extends basic heuristic search with random sampling and a heuristic function that prioritizes feasibility checking on promising state action pairs. The main drawback of such pure planners is that they lack the ability to learn from planning experience to improve their efficiency. We propose two learning algorithms to address this. The first is an algorithm for learning a rank function that guides the discrete task level search, and the second is an algorithm for learning a sampler that guides the continuous motionlevel search. We propose design principles for designing data efficient algorithms for learning from planning experience and representations for effective generalization. We evaluate our framework in challenging GTAMP problems, and show that we can improve both planning and data efficiency