# Learning Human-Aware Path Planning with Fully Convolutional Networks

arXiv: https://arxiv.org/abs/1803.00429 · HTML: https://mlsanity.com/paper/1803.00429/

## Key facts

- Cited by 11 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 1 Mar 2018.

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

- [A Survey on Human-aware Robot Navigation](https://mlsanity.com/paper/2106.11650/) (2021)
- [APPLD: Adaptive Planner Parameter Learning from Demonstration](https://mlsanity.com/paper/2004.00116/) (2020)
- [Security Considerations in AI-Robotics: A Survey of Current Methods, Challenges, and Opportunities](https://mlsanity.com/paper/2310.08565/) (2023)
- [Learning Social Navigation from Demonstrations with Conditional Neural Processes](https://mlsanity.com/paper/2210.03582/) (2022)
- [Learning to Predict Navigational Patterns from Partial Observations](https://mlsanity.com/paper/2304.13242/) (2023)
- [Learning a Model for Inferring a Spatial Road Lane Network Graph using Self-Supervision](https://mlsanity.com/paper/2107.01784/) (2021)
- [CURE: Simulation-Augmented Auto-Tuning in Robotics](https://mlsanity.com/paper/2402.05399/) (2024)
- [Dense Crowd Flow-Informed Path Planning](https://mlsanity.com/paper/2206.00705/) (2022)
- [Combining Optimal Path Search With Task-Dependent Learning in a Neural Network](https://mlsanity.com/paper/2201.11104/) (2022)
- [Manipulating Neural Path Planners via Slight Perturbations](https://mlsanity.com/paper/2403.18256/) (2024)
- [Think When It Matters: Conditional VLM Reasoning for Social Navigation with RL Policies](https://mlsanity.com/paper/2607.10991/) (2026)

## Abstract (arXiv)

This work presents an approach to learn path planning for robot social navigation by demonstration. We make use of Fully Convolutional Neural Networks (FCNs) to learn from expert's path demonstrations a map that marks a feasible path to the goal as a classification problem. The use of FCNs allows us to overcome the problem of manually designing/identifying the cost-map and relevant features for the task of robot navigation. The method makes use of optimal Rapidly-exploring Random Tree planner (RRT*) to overcome eventual errors in the path prediction; the FCNs prediction is used as cost-map and also to partially bias the sampling of the configuration space, leading the planner to behave similarly to the learned expert behavior. The approach is evaluated in experiments with real trajectories and compared with Inverse Reinforcement Learning algorithms that use RRT* as underlying planner.