RoboTool Benchmark

该数据集对RoboTool在模拟环境和真实世界环境中的创造性工具使用能力进行了评估，涵盖了需要长期规划的多种机器人任务。该基准测试包括了与基线方法的比较，以及针对模拟和真实世界任务的性能指标。该数据集的规模涉及多个机器人平台（如Kinova Gen3和Unitree Go1）上的多种任务，旨在评估机器人在执行任务时的创造性工具使用能力。

This dataset evaluates the creative tool use capabilities of RoboTool in both simulated and real-world environments, covering a variety of robotic tasks that require long-term planning. This benchmark includes comparisons with baseline methods, as well as performance metrics for both simulated and real-world robotic tasks. This dataset encompasses diverse tasks across multiple robotic platforms (e.g., Kinova Gen3 and Unitree Go1), aiming to assess robots’ creative tool use capabilities during task execution.