Demonstrating Arena 3.0: Advancing Social Navigation in Collaborative and Highly Dynamic Environments

摘要

Building upon our previous contributions, this paper introduces Arena 3.0, an extension of Arena-Bench [1], Arena 1.0 [2], and Arena 2.0 [3].Arena 3.0 is a comprehensive software stack containing multiple modules and simulation environments focusing on the development, simulation, and benchmarking of social navigation approaches in collaborative environments.We significantly enhance the realism of human behavior simulation by incorporating a diverse array of new social force models and interaction patterns, encompassing both human-human and human-robot dynamics.The platform provides a comprehensive set of new task modes, designed for extensive benchmarking and testing and is capable of generating realistic and human-centric environments dynamically, catering to a broad spectrum of social navigation scenarios.In addition, the platform's functionalities have been abstracted across three widely used simulators, each tailored for specific training and testing purposes.The platform's efficacy has been validated through an extensive benchmark and user evaluations of the platform by a global community of researchers and students, which noted the substantial improvement compared to previous versions and expressed interests to utilize the platform for future research and development.Arena 3.0 is openly available at https://github.com/Arena-Rosnav. I. INTRODUCTIONAs the integration of human-robot collaboration becomes increasingly essential in fields such as healthcare, logistics, and delivery, the necessity for robots to navigate through dynamic and human-centric environments is paramount.The realm of social navigation, where robots maneuver and interact in human-populated settings, is rapidly gaining attention.Critical factors in navigation include not just safety, but also operational smoothness, user stress, acceptance, interaction, and maintaining efficiency.Recent years have seen strides in social robotics [4],[5],[6] with numerous research works proposing platforms and approaches for social navigation and benchmarking.However, many existing platforms are constrained to specific planning approaches, either learning-based or traditional, and exhibit limited extensibility [5].Simulations