Selecting an optimal robot, its base pose, and trajectory for a given task is currently mainly done by human expertise or trial and error. To evaluate automatic approaches to this combined optimization problem, we introduce a benchmark suite encompassing a unified format for robots, environments, and task descriptions. Our benchmark suite is especially useful for modular robots, where the multitude of robots that can be assembled creates a host of additional parameters to optimize. We include tasks such as machine tending and welding in synthetic environments and 3D scans of real-world machine shops. All benchmarks are accessible through https://cobra.cps.cit.tum.de, a platform to conveniently share, reference, and compare tasks, robot models, and solutions.

翻译：针对特定任务选择最优机器人、其基座位姿及运动轨迹，目前主要依赖人工经验或试错法实现。为评估这类组合优化问题的自动化方法，我们提出了一套基准测试套件，统一了机器人、环境及任务描述的格式规范。该套件对模块化机器人尤为适用——由于可组装的机器人种类繁多，由此产生了大量待优化参数。我们在合成环境及真实车间的三维扫描场景中设置了机器看护与焊接等任务。所有基准测试均通过https://cobra.cps.cit.tum.de平台开放访问，该平台提供任务、机器人模型及解决方案的便捷共享、引用与比较功能。