多任务足式导航的统一方法：时序逻辑与强化学习的结合
A Unified Approach to Multi-task Legged Navigation: Temporal Logic Meets Reinforcement Learning
AI总结：
针对跳跃机器人需同时完成LTL强制目标任务与可选探索任务且存在动力学扰动的问题，提出动力学抽象、MT-PIMDP模型与统一策略综合算法，形式化证明任务权衡关系并通过仿真验证。
摘要：
本研究针对跳跃机器人导航规划问题展开，旨在同时完成目标导向与环境探索任务。研究考虑的场景为：机器人需完成由线性时序逻辑（Linear Temporal Logic, LTL）规范定义的强制性目标导向任务，以及由奖励函数表征的可选探索任务，且机器人动力学存在不确定性会引发运动扰动。研究首先提出三维跳跃机器人动力学的抽象方法，支撑高层规划，同时设计基于神经网络的优化方法用于底层控制；随后构建系统与任务的多任务乘积区间马尔可夫决策过程（Multi-task Product IMDP, MT-PIMDP）模型，提出统一控制策略综合算法，既能实现任务导向的目标到达行为，也能开展无任务偏好的探索以学习扰动与奖励。研究还对优先选择LTL动作或RL动作所产生的权衡关系给出了形式化证明，最终在二维世界导航环境中通过仿真案例验证了所提方法的有效性。
英文摘要：
This study examines the problem of hopping robot navigation planning to achieve simultaneous goal-directed and environment exploration tasks. We consider a scenario in which the robot has mandatory goal-directed tasks defined using Linear Temporal Logic (LTL) specifications as well as optional exploration tasks represented using a reward function. Additionally, there exists uncertainty in the robot dynamics which results in motion perturbation. We first propose an abstraction of 3D hopping robot dynamics which enables high-level planning and a neural-network-based optimization for low-level control. We then introduce a Multi-task Product IMDP (MT-PIMDP) model of the system and tasks. We propose a unified control policy synthesis algorithm which enables both task-directed goal-reaching behaviors as well as task-agnostic exploration to learn perturbations and reward. We provide a formal proof of the trade-off induced by prioritizing either LTL or RL actions. We demonstrate our methods with simulation case studies in a 2D world navigation environment.
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。
