Data from: A careful examination of large behavior models for multitask dexterous manipulation

Robot manipulation has seen tremendous progress in recent years, with
imitation learning policies enabling successful performance of dexterous
and hard-to-model tasks. Concurrently, scaling data and model size has led
to the development of capable language and vision foundation models,
motivating large-scale efforts to create general-purpose robot foundation
models. While these models have garnered significant enthusiasm and
investment, meaningful evaluation of real-world performance remains a
challenge, limiting both the pace of development and inhibiting a nuanced
understanding of current capabilities. In this paper, we rigorously
evaluate multitask robot manipulation policies, referred to as Large
Behavior Models (LBMs), by extending the Diffusion Policy paradigm across
a corpus of simulated and real-world robot data. We propose and validate
an evaluation pipeline to rigorously analyze the capabilities of these
models with statistical confidence. We compare against single-task
baselines through blind, randomized trials in a controlled setting, using
both simulation and real-world experiments. We find that multitask
pretraining makes the policies more successful and robust, and enables
teaching.

近年来，机器人操作（robot manipulation）领域取得了长足进步，模仿学习（imitation learning）策略可实现灵巧且难以建模任务的成功执行。与此同时，数据与模型规模的拓展推动了高性能语言与视觉基础模型（foundation models）的发展，进而催生了打造通用机器人基础模型的大规模研究尝试。尽管这类模型收获了大量关注与投入，但对其真实世界性能的严谨评估仍是一项挑战，这既限制了研发进度，也阻碍了对当前模型能力的精细化理解。在本文中，我们通过将扩散策略（Diffusion Policy）范式扩展至模拟与真实机器人数据集合集，对被称为大行为模型（Large Behavior Models, LBMs）的多任务机器人操作策略开展了严格评估。我们提出并验证了一套评估流程，可借助统计置信度严谨分析这类模型的性能。我们在受控环境中通过盲法随机试验，结合仿真与真实世界实验，将其与单任务基准模型进行对比。我们发现，多任务预训练可提升策略的成功率与鲁棒性，并使其具备教学能力。