# Learning to Search in Task and Motion Planning with Streams

arXiv: https://arxiv.org/abs/2111.13144 · HTML: https://mlsanity.com/paper/2111.13144/

## Key facts

- Cited by 10 papers in the map (data through 14 Oct 2026).
- Builds on 14 of its 35 references that are in the map.
- First posted on arXiv 25 Nov 2021.

## Builds on (most cited first, 14 of 14)

- [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)
- [PDDLStream: Integrating Symbolic Planners and Blackbox Samplers via Optimistic Adaptive Planning](https://mlsanity.com/paper/1802.08705/) (2018)
- [Hierarchical Planning for Long-Horizon Manipulation with Geometric and Symbolic Scene Graphs](https://mlsanity.com/paper/2012.07277/) (2020)
- [Online Replanning in Belief Space for Partially Observable Task and Motion Problems](https://mlsanity.com/paper/1911.04577/) (2019)
- [Learning Symbolic Operators for Task and Motion Planning](https://mlsanity.com/paper/2103.00589/) (2021)
- [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)
- [Learning compositional models of robot skills for task and motion planning](https://mlsanity.com/paper/2006.06444/) (2020)
- [Planning with Learned Object Importance in Large Problem Instances using Graph Neural Networks](https://mlsanity.com/paper/2009.05613/) (2020)
- [Object-Centric Task and Motion Planning in Dynamic Environments](https://mlsanity.com/paper/1911.04679/) (2019)
- [Learning to guide task and motion planning using score-space representation](https://mlsanity.com/paper/1807.09962/) (2018)
- [Transferable Task Execution from Pixels through Deep Planning Domain Learning](https://mlsanity.com/paper/2003.03726/) (2020)
- [Extended Tree Search for Robot Task and Motion Planning](https://mlsanity.com/paper/2103.05456/) (2021)
- [Work in Progress -- Automated Generation of Robotic Planning Domains from Observations](https://mlsanity.com/paper/2107.04614/) (2021)

## Built on by (most cited first, 10 of 10)

- [ORGANA: A Robotic Assistant for Automated Chemistry Experimentation and Characterization](https://mlsanity.com/paper/2401.06949/) (2024)
- [Sequence-Based Plan Feasibility Prediction for Efficient Task and Motion Planning](https://mlsanity.com/paper/2211.01576/) (2022)
- [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)
- [Learning Reward Machines from Partially Observed Policies](https://mlsanity.com/paper/2502.03762/) (2025)
- [ELITE: Experiential Learning and Intent-Aware Transfer for Self-improving Embodied Agents](https://mlsanity.com/paper/2603.24018/) (2026)
- [Efficient Skill Acquisition for Complex Manipulation Tasks in Obstructed Environments](https://mlsanity.com/paper/2303.03365/) (2023)
- [Policy-Guided Lazy Search with Feedback for Task and Motion Planning](https://mlsanity.com/paper/2210.14055/) (2022)
- [RobKiNet: Robotic Kinematics Informed Neural Network for Optimal Robot Configuration Prediction](https://mlsanity.com/paper/2402.16281/) (2024)
- [Optimistic Reinforcement Learning-Based Skill Insertions for Task and Motion Planning](https://mlsanity.com/paper/2510.14065/) (2025)
- [Learning Bilevel Policies over Symbolic World Models for Long-Horizon Planning](https://mlsanity.com/paper/2605.15975/) (2026)

## Abstract (arXiv)

Task and motion planning problems in robotics combine symbolic planning over discrete task variables with motion optimization over continuous state and action variables. Recent works such as PDDLStream have focused on optimistic planning with an incrementally growing set of objects until a feasible trajectory is found. However, this set is exhaustively expanded in a breadth-first manner, regardless of the logical and geometric structure of the problem at hand, which makes long-horizon reasoning with large numbers of objects prohibitively time-consuming. To address this issue, we propose a geometrically informed symbolic planner that expands the set of objects and facts in a best-first manner, prioritized by a Graph Neural Network that is learned from prior search computations. We evaluate our approach on a diverse set of problems and demonstrate an improved ability to plan in difficult scenarios. We also apply our algorithm on a 7DOF robotic arm in block-stacking manipulation tasks.