# Ratatouille: Imitation Learning Ingredients for Real-world Social Robot Navigation

arXiv: https://arxiv.org/abs/2509.17204 · HTML: https://mlsanity.com/paper/2509.17204/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Placed in Imitation learning methods, one of 13 directions in Offline RL and imitation learning from data.
- Builds on 20 of its 30 references that are in the map.
- First posted on arXiv 21 Sep 2025.

## Placed in

- Offline RL and imitation learning from data / [Imitation learning methods](https://mlsanity.com/offlinerl/imitation-learning-methods/)

## Builds on (most cited first, 20 of 20)

- [Diffusion Policy: Visuomotor Policy Learning via Action Diffusion](https://mlsanity.com/paper/2303.04137/) (2023)
- [π0.5: a Vision-Language-Action Model with Open-World Generalization](https://mlsanity.com/paper/2504.16054/) (2025)
- [MMDetection: Open MMLab Detection Toolbox and Benchmark](https://mlsanity.com/paper/1906.07155/) (2019)
- [Fine-Tuning Vision-Language-Action Models: Optimizing Speed and Success](https://mlsanity.com/paper/2502.19645/) (2025)
- [Causal Confusion in Imitation Learning](https://mlsanity.com/paper/1905.11979/) (2019)
- [Bigger, Better, Faster: Human-level Atari with human-level efficiency](https://mlsanity.com/paper/2305.19452/) (2023)
- [Socially Compliant Navigation Dataset (SCAND): A Large-Scale Dataset of Demonstrations for Social Navigation](https://mlsanity.com/paper/2203.15041/) (2022)
- [Reinforcement Learning with Action Chunking](https://mlsanity.com/paper/2507.07969/) (2025)
- [Fighting Copycat Agents in Behavioral Cloning from Observation Histories](https://mlsanity.com/paper/2010.14876/) (2020)
- [On the Foundations of Shortcut Learning](https://mlsanity.com/paper/2310.16228/) (2023)
- [SACSoN: Scalable Autonomous Control for Social Navigation](https://mlsanity.com/paper/2306.01874/) (2023)
- [Intention Aware Robot Crowd Navigation with Attention-Based Interaction Graph](https://mlsanity.com/paper/2203.01821/) (2022)
- [Socially Compliant Navigation through Raw Depth Inputs with Generative Adversarial Imitation Learning](https://mlsanity.com/paper/1710.02543/) (2017)
- [A Comprehensive Survey on Data Augmentation](https://mlsanity.com/paper/2405.09591/) (2024)
- [Toward Human-Like Social Robot Navigation: A Large-Scale, Multi-Modal, Social Human Navigation Dataset](https://mlsanity.com/paper/2303.14880/) (2023)
- [The Pitfalls of Imitation Learning when Actions are Continuous](https://mlsanity.com/paper/2503.09722/) (2025)
- [Multi-Transmotion: Pre-trained Model for Human Motion Prediction](https://mlsanity.com/paper/2411.02673/) (2024)
- [NaviSTAR: Socially Aware Robot Navigation with Hybrid Spatio-Temporal Graph Transformer and Preference Learning](https://mlsanity.com/paper/2304.05979/) (2023)
- [DR-MPC: Deep Residual Model Predictive Control for Real-world Social Navigation](https://mlsanity.com/paper/2410.10646/) (2024)
- [DeepMoTIon: Learning to Navigate Like Humans](https://mlsanity.com/paper/1803.03719/) (2018)

## Built on by (most cited first, 2 of 2)

- [Act on What You See: Unlocking Safe Social Navigation in Vision-Language-Action Models](https://mlsanity.com/paper/2606.10495/) (2026)
- [ACME: A Multi-Cultural, Multi-Embodiment Social-Navigation Dataset](https://mlsanity.com/paper/2607.21964/) (2026)

## Abstract (arXiv)

Scaling Reinforcement Learning to in-the-wild social robot navigation is both data-intensive and unsafe, since policies must learn through direct interaction and inevitably encounter collisions. Offline Imitation learning (IL) avoids these risks by collecting expert demonstrations safely, training entirely offline, and deploying policies zero-shot. However, we find that naively applying Behaviour Cloning (BC) to social navigation is insufficient; achieving strong performance requires careful architectural and training choices. We present Ratatouille, a pipeline and model architecture that, without changing the data, reduces collisions per meter by 6 times and improves success rate by 3 times compared to naive BC. We validate our approach in both simulation and the real world, where we collected over 11 hours of data on a dense university campus. We further demonstrate qualitative results in a public food court. Our findings highlight that thoughtful IL design, rather than additional data, can substantially improve safety and reliability in real-world social navigation. Video: https://youtu.be/tOdLTXsaYLQ. Code will be released after acceptance.