Robotic Behavior Prediction Using Hidden Markov Models

TL;DR

This paper introduces a method for robots to predict and identify the behaviors of dynamic agents in real time using hidden Markov models, enhancing collaborative and obstacle avoidance capabilities.

Contribution

It presents a novel application of hidden Markov models for real-time behavior prediction and identification of dynamic agents by robots.

Findings

Successful simulation of behavior prediction in static environments

Effective real-time behavior identification demonstrated

Potential for improved robot-human interaction and navigation

Abstract

There are many situations in which it would be beneficial for a robot to have predictive abilities similar to those of rational humans. Some of these situations include collaborative robots, robots in adversarial situations, and for dynamic obstacle avoidance. This paper presents an approach to modeling behaviors of dynamic agents in order to empower robots with the ability to predict the agent's actions and identify the behavior the agent is executing in real time. The method of behavior modeling implemented uses hidden Markov models (HMMs) to model the unobservable states of the dynamic agents. The background and theory of the behavior modeling is presented. Experimental results of realistic simulations of a robot predicting the behaviors and actions of a dynamic agent in a static environment are presented.