MIRACLE: Inverse Reinforcement and Curriculum Learning Model for Human-inspired Mobile Robot Navigation
This addresses the challenge of human-inspired navigation for mobile robots in emergency situations, representing an incremental improvement over existing socially-aware algorithms.
The paper tackles the problem of enabling mobile robots to navigate emergency scenarios with human-like perception by developing MIRACLE, an inverse reinforcement and curriculum learning model that uses gamified learning to gather stimuli-driven human navigational data, achieving a low loss of 2.7717 in a 400-sized environment.
In emergency scenarios, mobile robots must navigate like humans, interpreting stimuli to locate potential victims rapidly without interfering with first responders. Existing socially-aware navigation algorithms face computational and adaptability challenges. To overcome these, we propose a solution, MIRACLE -- an inverse reinforcement and curriculum learning model, that employs gamified learning to gather stimuli-driven human navigational data. This data is then used to train a Deep Inverse Maximum Entropy Reinforcement Learning model, reducing reliance on demonstrator abilities. Testing reveals a low loss of 2.7717 within a 400-sized environment, signifying human-like response replication. Current databases lack comprehensive stimuli-driven data, necessitating our approach. By doing so, we enable robots to navigate emergency situations with human-like perception, enhancing their life-saving capabilities.