# Gated Path Planning Networks

arXiv: https://arxiv.org/abs/1806.06408 · HTML: https://mlsanity.com/paper/1806.06408/

## Key facts

- Cited by 31 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 17 Jun 2018.

## Built on by (most cited first, 30 of 31)

- [Structured Scene Memory for Vision-Language Navigation](https://mlsanity.com/paper/2103.03454/) (2021)
- [Symphony: Learning Realistic and Diverse Agents for Autonomous Driving Simulation](https://mlsanity.com/paper/2205.03195/) (2022)
- [Towards Versatile Embodied Navigation](https://mlsanity.com/paper/2210.16822/) (2022)
- [Differentiable Spatial Planning using Transformers](https://mlsanity.com/paper/2112.01010/) (2021)
- [Neural Algorithmic Reasoners are Implicit Planners](https://mlsanity.com/paper/2110.05442/) (2021)
- [Collaborative Visual Navigation](https://mlsanity.com/paper/2107.01151/) (2021)
- [Reducing Collision Checking for Sampling-Based Motion Planning Using Graph Neural Networks](https://mlsanity.com/paper/2210.08864/) (2022)
- [Horizon Generalization in Reinforcement Learning](https://mlsanity.com/paper/2501.02709/) (2025)
- [Hierarchies of Planning and Reinforcement Learning for Robot Navigation](https://mlsanity.com/paper/2109.11178/) (2021)
- [A modular vision language navigation and manipulation framework for long horizon compositional tasks in indoor environment](https://mlsanity.com/paper/2101.07891/) (2021)
- [PathBench: A Benchmarking Platform for Classical and Learned Path Planning Algorithms](https://mlsanity.com/paper/2105.01777/) (2021)
- [Integrating Symmetry into Differentiable Planning with Steerable Convolutions](https://mlsanity.com/paper/2206.03674/) (2022)
- [Scaling up and Stabilizing Differentiable Planning with Implicit Differentiation](https://mlsanity.com/paper/2210.13542/) (2022)
- [E(2)-Equivariant Graph Planning for Navigation](https://mlsanity.com/paper/2309.13043/) (2023)
- [Learning-based Motion Planning in Dynamic Environments Using GNNs and Temporal Encoding](https://mlsanity.com/paper/2210.08408/) (2022)
- [Towards real-world navigation with deep differentiable planners](https://mlsanity.com/paper/2108.05713/) (2021)
- [Continuous Neural Algorithmic Planners](https://mlsanity.com/paper/2211.15839/) (2022)
- [Equivariant Action Sampling for Reinforcement Learning and Planning](https://mlsanity.com/paper/2412.12237/) (2024)
- [Scaling Value Iteration Networks to 5000 Layers for Extreme Long-Term Planning](https://mlsanity.com/paper/2406.08404/) (2024)
- [Deep Learning for Embodied Vision Navigation: A Survey](https://mlsanity.com/paper/2108.04097/) (2021)
- [ExPoSe: Combining State-Based Exploration with Gradient-Based Online Search](https://mlsanity.com/paper/2202.01461/) (2022)
- [Highway Value Iteration Networks](https://mlsanity.com/paper/2406.03485/) (2024)
- [Learning to Navigate in Mazes with Novel Layouts using Abstract Top-down Maps](https://mlsanity.com/paper/2412.12024/) (2024)
- [Can Euclidean Symmetry be Leveraged in Reinforcement Learning and Planning?](https://mlsanity.com/paper/2307.08226/) (2023)
- [Differentiable Tree Search Network](https://mlsanity.com/paper/2401.11660/) (2024)
- [SOAP-RL: Sequential Option Advantage Propagation for Reinforcement Learning in POMDP Environments](https://mlsanity.com/paper/2407.18913/) (2024)
- [DAA*: Deep Angular A Star for Image-based Path Planning](https://mlsanity.com/paper/2507.09305/) (2025)
- [Systematic Comparison of Path Planning Algorithms using PathBench](https://mlsanity.com/paper/2203.03092/) (2022)
- [[Reproducibility Report] Path Planning using Neural A* Search](https://mlsanity.com/paper/2208.04153/) (2022)
- [[Re] Differentiable Spatial Planning using Transformers](https://mlsanity.com/paper/2208.09536/) (2022)

## Abstract (arXiv)

Value Iteration Networks (VINs) are effective differentiable path planning modules that can be used by agents to perform navigation while still maintaining end-to-end differentiability of the entire architecture. Despite their effectiveness, they suffer from several disadvantages including training instability, random seed sensitivity, and other optimization problems. In this work, we reframe VINs as recurrent-convolutional networks which demonstrates that VINs couple recurrent convolutions with an unconventional max-pooling activation. From this perspective, we argue that standard gated recurrent update equations could potentially alleviate the optimization issues plaguing VIN. The resulting architecture, which we call the Gated Path Planning Network, is shown to empirically outperform VIN on a variety of metrics such as learning speed, hyperparameter sensitivity, iteration count, and even generalization. Furthermore, we show that this performance gap is consistent across different maze transition types, maze sizes and even show success on a challenging 3D environment, where the planner is only provided with first-person RGB images.