# Stranger Danger! Identifying and Avoiding Unpredictable Pedestrians in RL-based Social Robot Navigation

arXiv: https://arxiv.org/abs/2407.06056 · HTML: https://mlsanity.com/paper/2407.06056/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Placed in RL for robot navigation and UAV control, one of 15 directions in Deep reinforcement learning methods.
- Builds on 21 of its 38 references that are in the map.
- First posted on arXiv 8 Jul 2024.

## Placed in

- Deep reinforcement learning methods / [RL for robot navigation and UAV control](https://mlsanity.com/deeprl/rl-for-robot-navigation-and-uav-control/)

## Builds on (most cited first, 21 of 21)

- [You Only Look Once: Unified, Real-Time Object Detection](https://mlsanity.com/paper/1506.02640/) (2015)
- [Crowd-Robot Interaction: Crowd-aware Robot Navigation with Attention-based Deep Reinforcement Learning](https://mlsanity.com/paper/1809.08835/) (2018)
- [Socially Aware Motion Planning with Deep Reinforcement Learning](https://mlsanity.com/paper/1703.08862/) (2017)
- [Decentralized Non-communicating Multiagent Collision Avoidance with Deep Reinforcement Learning](https://mlsanity.com/paper/1609.07845/) (2016)
- [Core Challenges of Social Robot Navigation: A Survey](https://mlsanity.com/paper/2103.05668/) (2021)
- [Learning Navigation Behaviors End-to-End with AutoRL](https://mlsanity.com/paper/1809.10124/) (2018)
- [PRM-RL: Long-range Robotic Navigation Tasks by Combining Reinforcement Learning and Sampling-based Planning](https://mlsanity.com/paper/1710.03937/) (2017)
- [How Should a Robot Assess Risk? Towards an Axiomatic Theory of Risk in Robotics](https://mlsanity.com/paper/1710.11040/) (2017)
- [Intention Aware Robot Crowd Navigation with Attention-Based Interaction Graph](https://mlsanity.com/paper/2203.01821/) (2022)
- [Relational Graph Learning for Crowd Navigation](https://mlsanity.com/paper/1909.13165/) (2019)
- [Probabilistically Safe Robot Planning with Confidence-Based Human Predictions](https://mlsanity.com/paper/1806.00109/) (2018)
- [DenseCAvoid: Real-time Navigation in Dense Crowds using Anticipatory Behaviors](https://mlsanity.com/paper/2002.03038/) (2020)
- [Risk-Sensitive Sequential Action Control with Multi-Modal Human Trajectory Forecasting for Safe Crowd-Robot Interaction](https://mlsanity.com/paper/2009.05702/) (2020)
- [Risk-Conditioned Distributional Soft Actor-Critic for Risk-Sensitive Navigation](https://mlsanity.com/paper/2104.03111/) (2021)
- [Socially Aware Crowd Navigation with Multimodal Pedestrian Trajectory Prediction for Autonomous Vehicles](https://mlsanity.com/paper/2011.11191/) (2020)
- [SHARP: Shielding-Aware Robust Planning for Safe and Efficient Human-Robot Interaction](https://mlsanity.com/paper/2110.00843/) (2021)
- [A Scalable Framework For Real-Time Multi-Robot, Multi-Human Collision Avoidance](https://mlsanity.com/paper/1811.05929/) (2018)
- [SOCIALGYM: A Framework for Benchmarking Social Robot Navigation](https://mlsanity.com/paper/2109.11011/) (2021)
- [Active Uncertainty Reduction for Human-Robot Interaction: An Implicit Dual Control Approach](https://mlsanity.com/paper/2202.07720/) (2022)
- [Enhancing Navigational Safety in Crowded Environments using Semantic-Deep-Reinforcement-Learning-based Navigation](https://mlsanity.com/paper/2109.11288/) (2021)
- [Metrics for Evaluating Social Conformity of Crowd Navigation Algorithms](https://mlsanity.com/paper/2202.01045/) (2022)

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

- [SocialNav-MoE: A Mixture-of-Experts Vision Language Model for Socially Compliant Navigation with Reinforcement Fine-Tuning](https://mlsanity.com/paper/2512.14757/) (2025)
- [Socially aware navigation for mobile robots: a survey on deep reinforcement learning approaches](https://mlsanity.com/paper/2512.00049/) (2025)

## Abstract (arXiv)

Reinforcement learning (RL) methods for social robot navigation show great success navigating robots through large crowds of people, but the performance of these learning-based methods tends to degrade in particularly challenging or unfamiliar situations due to the models' dependency on representative training data. To ensure human safety and comfort, it is critical that these algorithms handle uncommon cases appropriately, but the low frequency and wide diversity of such situations present a significant challenge for these data-driven methods. To overcome this challenge, we propose modifications to the learning process that encourage these RL policies to maintain additional caution in unfamiliar situations. Specifically, we improve the Socially Attentive Reinforcement Learning (SARL) policy by (1) modifying the training process to systematically introduce deviations into a pedestrian model, (2) updating the value network to estimate and utilize pedestrian-unpredictability features, and (3) implementing a reward function to learn an effective response to pedestrian unpredictability. Compared to the original SARL policy, our modified policy maintains similar navigation times and path lengths, while reducing the number of collisions by 82% and reducing the proportion of time spent in the pedestrians' personal space by up to 19 percentage points for the most difficult cases. We also describe how to apply these modifications to other RL policies and demonstrate that some key high-level behaviors of our approach transfer to a physical robot.