Reinforcement Learning-Based Path Following for Robots: A Survey of Reward Functions

• Jardel dos Santos Dyonisio FURG https://orcid.org/0009-0003-7722-7203
• Stephanie Loi Brião FURG https://orcid.org/0000-0001-9345-2038
• Kristofer Stift Kappel FURG https://orcid.org/0000-0002-9124-8540
• Rodrigo Silva Guerra FURG https://orcid.org/0000-0003-4011-0901
• Emanuel da Silva Diaz Estrada FURG https://orcid.org/0000-0003-4088-5002
• Paulo Lilles Jorge Drews FURG https://orcid.org/0000-0002-7519-0502

Resumo

Reward functions define an agent's behavior in reinforcement learning by determining actions based on the feedback received. In the domain of path following, reward functions guide the agent toward successfully following the desired path. This paper presents a survey of reward functions focused on path-following tasks for mobile robots. The characteristics, strategies, and challenges associated with creating feedback mechanisms in various domains are highlighted. Components of the reward functions that can be controlled are explored and discussed. Furthermore, for each reward function, scenarios and mobile robots are indicated. Thus, this study provides insights into the reward components that influence reinforcement learning systems in robotic navigation.

Palavras-chave: Surveys, Reviews, Shape, Navigation, Conferences, Taxonomy, Education, Reinforcement learning, Mobile robots, Motion control, Reinforcement Learning, Reward Design, Motion Control, Autonomous Robots