2 papers
cs.RO2024
Evaluating MEDIRL: A Replication and Ablation Study of Maximum Entropy Deep Inverse Reinforcement Learning for Human Social Navigation
Vinay Gupta, Nihal Gunukula
In this study, we enhance the Maximum Entropy Deep Inverse Reinforcement Learning (MEDIRL) framework, targeting its application in human robot interaction (HRI) for modeling pedest…
cs.RO2023
MIRACLE: Inverse Reinforcement and Curriculum Learning Model for Human-inspired Mobile Robot Navigation
Nihal Gunukula, Kshitij Tiwari, Aniket Bera
In emergency scenarios, mobile robots must navigate like humans, interpreting stimuli to locate potential victims rapidly without interfering with first responders. Existing social…