Humanoid robots hold great promise in assisting humans in diverse environments and tasks, due to their flexibility and adaptability leveraging human-like morphology. However, research in humanoid robots is often bottlenecked by the costly and fragile hardware setups. To accelerate algorithmic research in humanoid robots, we present a high-dimensional, simulated robot learning benchmark, HumanoidBench, featuring a humanoid robot equipped with dexterous hands and a variety of challenging whole-body manipulation and locomotion tasks. Our findings reveal that state-of-the-art reinforcement learning algorithms struggle with most tasks, whereas a hierarchical learning baseline achieves superior performance when supported by robust low-level policies, such as walking or reaching. With HumanoidBench, we provide the robotics community with a platform to identify the challenges arising when solving diverse tasks with humanoid robots, facilitating prompt verification of algorithms and ideas. The open-source code is available at https://sferrazza.cc/humanoidbench_site.

翻译：仿人机器人凭借其类人形态的灵活性和适应性，在协助人类完成多样化环境与任务方面展现出巨大潜力。然而，仿人机器人研究常受限于昂贵且脆弱的硬件设备。为加速仿人机器人算法研究，我们提出一个高维度的模拟机器人学习基准——HumanoidBench，该基准包含配备灵巧手的仿人机器人以及一系列具有挑战性的全身操控与运动任务。研究发现，现有最先进的强化学习算法在多数任务上表现不佳，而基于稳健低级策略（如行走或抓取）的分层学习基线方法则能取得更优性能。通过HumanoidBench，我们为机器人学界提供了一个能识别仿人机器人解决多样化任务时所面临挑战的平台，从而促进算法与理念的快速验证。开源代码详见https://sferrazza.cc/humanoidbench_site。