[RE] MEDIRL Maximum Entropy Deep Inverse Reinforcement Learning for Human Social Navigation

Purdue University ML 2023 Hackathon Reproducibility Challenge Submission5 Authors

Keywords: Human-Robot Interaction, MEDIRL (Maximum Entropy Deep Inverse Reinforcement Learning), Social Navigation, Ablation Study, Markov Decision Process, Model Optimization, Pedestrian Behavior Modeling, Reinforcement Learning, Model Accuracy, Human Behavior Modeling, Autonomous Navigation, Robotics, Deep Learning, Interaction Dynamics, Environment Modeling, Navigation Systems, Human-Robot Coexistence.

TL;DR: Enhanced human-robot interaction achieved by refining the MEDIRL framework, revealing the critical role of model components in replicating human navigation behaviors.

Abstract:

In this study, we enhance the Maximum Entropy Deep Inverse Reinforcement Learning (MEDIRL) framework, targeting its application in human-robot interaction (HRI) for modeling pedestrian behavior in crowded environments. Our work is grounded in the pioneering research by Fahad, Chen, and Guo, and aims to elevate MEDIRL's efficacy in real-world HRI settings.

We replicated the original MEDIRL model and conducted detailed ablation studies, focusing on key model components like learning rates, state dimensions, and network layers. Our findings reveal the effectiveness of a two-dimensional state representation over a three-dimensional approach, significantly improving model accuracy for pedestrian behavior prediction in HRI scenarios.

These results not only demonstrate MEDIRL's enhanced performance but also offer valuable insights for future HRI system development, emphasizing the importance of model customization to specific environmental contexts. Our research contributes to advancing the field of socially intelligent navigation systems, promoting more intuitive and safer human-robot interactions.

Submission Number: 5