SocialGym: A Framework for Benchmarking Social Robot Navigation
SocialGym: A Framework for Benchmarking Social Robot Navigation
复制标题
DOI：
10.1109/iros47612.2022.9982021
复制
发表时间：
2021-09
期刊：
影响因子：
--
通讯作者：
Jarrett Holtz;Joydeep Biswas
中科院分区：
文献类型：
--
作者：
Jarrett Holtz;Joydeep Biswas
机器人在动态的人类环境中安全地移动，并以符合社会要求的方式移动，是机器人长期自主的重要基准。然而，完全在真实的世界中学习和基准测试社交导航行为是不可行的，因为学习是数据密集型的，并且在训练期间做出安全保证具有挑战性。因此，需要提供社交导航抽象的基于模拟的基准测试。这些基准的框架需要支持各种各样的学习方法，可扩展到广泛的社交导航场景，并抽象出感知问题，以明确地关注社交导航。虽然已经提出了许多解决方案，包括高保真3D模拟器和网格世界近似，但没有现有的解决方案满足所有上述用于学习和评估社交导航行为的属性。在这项工作中，我们提出了SocialGym，一个轻量级的2D仿真环境，机器人社会导航设计的可扩展性，并建立在SocialGym的基准场景。此外，我们提出了基准测试结果，比较和对比人类工程和基于模型的学习方法，一套现成的学习演示（LfD）和强化学习（RL）方法应用于社会机器人导航。这些结果表明，数据效率，任务性能，社会合规性和环境转移能力的评估，为未来的社会导航研究提供了坚实的基础。
Robots moving safely and in a socially compliant manner in dynamic human environments is an essential benchmark for long-term robot autonomy. However, it is not feasible to learn and benchmark social navigation behaviors entirely in the real world, as learning is data-intensive, and it is challenging to make safety guarantees during training. Therefore, simulation-based benchmarks that provide abstractions for social navigation are required. A framework for these benchmarks would need to support a wide variety of learning approaches, be extensible to the broad range of social navigation scenarios, and abstract away the perception problem to focus on social navigation explicitly. While there have been many proposed solutions, including high fidelity 3D simulators and grid world approximations, no existing solution satisfies all of the aforementioned properties for learning and evaluating social navigation behaviors. In this work, we propose SocialGym, a lightweight 2D simulation environment for robot social navigation designed with extensibility in mind, and a benchmark scenario built on SocialGym. Further, we present benchmark results that compare and contrast human-engineered and model-based learning approaches to a suite of off-the-shelf Learning from Demonstration (LfD) and Reinforcement Learning (RL) approaches applied to social robot navigation. These results demonstrate the data efficiency, task performance, social compliance, and environment transfer capabilities for each of the policies evaluated to provide a solid grounding for future social navigation research.