Large language models (LLMs) have shown significant potential for robotics applications, particularly task planning, by harnessing their language comprehension and text generation capabilities. However, in applications such as household robotics, a critical gap remains in the personalization of these models to individual user preferences. We introduce LLM-Personalize, a novel framework with an optimization pipeline designed to personalize LLM planners for household robotics. Our LLM-Personalize framework features an LLM planner that performs iterative planning in multi-room, partially-observable household scenarios, making use of a scene graph constructed with local observations. The generated plan consists of a sequence of high-level actions which are subsequently executed by a controller. Central to our approach is the optimization pipeline, which combines imitation learning and iterative self-training to personalize the LLM planner. In particular, the imitation learning phase performs initial LLM alignment from demonstrations, and bootstraps the model to facilitate effective iterative self-training, which further explores and aligns the model to user preferences. We evaluate LLM-Personalize on Housekeep, a challenging simulated real-world 3D benchmark for household rearrangements, and show that LLM-Personalize achieves more than a 30 percent increase in success rate over existing LLM planners, showcasing significantly improved alignment with human preferences. Project page: https://gdg94.github.io/projectllmpersonalize/.

翻译：大型语言模型（LLM）凭借其语言理解和文本生成能力，在机器人学应用中展现出巨大潜力，尤其在任务规划方面。然而，在诸如家政机器人等应用中，这些模型针对个体用户偏好的个性化定制仍存在关键空白。我们提出了LLM-Personalize，这是一个具有优化流程的新型框架，旨在为家政机器人实现LLM规划器的个性化。我们的LLM-Personalize框架采用一个LLM规划器，在多房间、部分可观察的家居场景中执行迭代规划，并利用基于局部观察构建的场景图。生成的规划由一系列高层级动作序列组成，随后由控制器执行。我们方法的核心是结合模仿学习与迭代自训练的优化流程，以实现LLM规划器的个性化。具体而言，模仿学习阶段通过演示对LLM进行初始对齐，并引导模型以促进有效的迭代自训练；该自训练过程进一步探索用户偏好并使模型与之对齐。我们在Housekeep（一个用于家居重排的具有挑战性的模拟真实世界3D基准测试）上评估LLM-Personalize，结果表明，相较于现有LLM规划器，LLM-Personalize的成功率提高了超过30%，显著提升了与人类偏好的对齐程度。项目页面：https://gdg94.github.io/projectllmpersonalize/。