演示增强的自适应多目标机器人导航
Demonstration-Enhanced Adaptable Multi-Objective Robot Navigation
AI总结：
针对用户偏好随情境变化的问题，提出融合演示学习与MORL的框架，使机器人无需重训即可动态调节导航策略，并在双机器人仿真到真实实验中验证其适应性与导航性能。
摘要：
在人类环境中，偏好对齐的机器人导航通常通过基于学习的方法实现，利用用户反馈或演示进行个性化。然而，个人偏好会发生变化，甚至可能依赖于情境。但采用静态奖励函数的传统强化学习（RL）方法往往难以适应不断演变的用户偏好，训练完成后不可避免地只能固化对演示的反映。本文提出一种结构化框架，将基于演示的学习与多目标强化学习（MORL）相结合。为确保真实世界适用性，我们的方法允许机器人导航策略在无需重新训练的情况下动态适应用户不断变化的偏好。它能够流畅调节演示数据反映程度以及其他与偏好相关的目标。通过严格评估，包括基线比较以及在两台机器人上进行的仿真到真实迁移，我们证明了该框架能够准确适应用户偏好，同时在避障和目标追寻方面实现高导航性能。
英文摘要：
Preference-aligned robot navigation in human environments is typically achieved through learning-based approaches, utilizing user feedback or demonstrations for personalization. However, personal preferences are subject to change and might even be context-dependent. Yet traditional reinforcement learning (RL) approaches with static reward functions often fall short in adapting to evolving user preferences, inevitably reflecting demonstrations once training is completed. This paper introduces a structured framework that combines demonstration-based learning with multi-objective reinforcement learning (MORL). To ensure real-world applicability, our approach allows for dynamic adaptation of the robot navigation policy to changing user preferences without retraining. It fluently modulates the amount of demonstration data reflection and other preference-related objectives. Through rigorous evaluations, including a baseline comparison and sim-to-real transfer on two robots, we demonstrate our framework's capability to adapt to user preferences accurately while achieving high navigational performance in terms of collision avoidance and goal pursuance.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
