POMHDP: Search-Based Belief Space Planning Using Multiple Heuristics
POMHDP: Search-Based Belief Space Planning Using Multiple Heuristics
复制标题
DOI：
10.1609/icaps.v29i1.3542
复制
发表时间：
2019-07
期刊：
影响因子：
--
通讯作者：
Sung-Kyun Kim;Oren Salzman;M. Likhachev
中科院分区：
文献类型：
--
作者：
Sung-Kyun Kim;Oren Salzman;M. Likhachev
在现实世界中运行的机器人遇到了大量的不确定性，这些不确定性在实际执行之前无法确定地建模。这就产生了不确定性环境下的鲁棒运动规划，也称为信念空间规划。信念空间规划可以表示为部分可观测马尔可夫决策过程(POMDP)。然而，为非平凡的POMDP计算最优策略在计算上是困难的。基于搜索界的最新进展，我们提出了一种新颖的Anytime POMDP求解器，部分可观察的多启发式动态规划(POMHDP)，它利用多个启发式算法来高效地计算高质量的解，同时保证渐近收敛到最优策略。通过迭代正向搜索，POMHDP利用领域知识来求解具有特定目标和无限视野的POMDP。我们在一个真实的、高度复杂的卡车卸货应用程序上展示了我们所提出的框架的有效性。
Robots operating in the real world encounter substantial uncertainty that cannot be modeled deterministically before the actual execution. This gives rise to the necessity of robust motion planning under uncertainty also known as belief space planning. Belief space planning can be formulated as Partially Observable Markov Decision Processes (POMDPs). However, computing optimal policies for non-trivial POMDPs is computationally intractable. Building upon recent progress from the search community, we propose a novel anytime POMDP solver, Partially Observable Multi-Heuristic Dynamic Programming (POMHDP), that leverages multiple heuristics to efficiently compute high-quality solutions while guaranteeing asymptotic convergence to an optimal policy. Through iterative forward search, POMHDP utilizes domain knowledge to solve POMDPs with specific goals and an infinite horizon. We demonstrate the efficacy of our proposed framework on a real-world, highly-complex, truck unloading application.