Robot Action Selection Learning via Layered Dimension Informed Program Synthesis
Robot Action Selection Learning via Layered Dimension Informed Program Synthesis
复制标题
DOI：
--
复制
发表时间：
2020-08
期刊：
影响因子：
--
通讯作者：
Jarrett Holtz;Arjun Guha;Joydeep Biswas
中科院分区：
文献类型：
--
作者：
Jarrett Holtz;Arjun Guha;Joydeep Biswas
动作选择策略（ASP）用于将低级机器人技能组合成复杂的高级任务，在现有技术中通常表示为神经网络（NN）。这种范式虽然非常有效，但存在一些关键问题：1）NN对用户是不透明的，因此不适合验证，2）它们需要大量的训练数据，3）当域改变时，它们难以修复。我们提出了有关机器人ASP的两个关键见解。首先，ASP需要对从世界状态中导出的物理上有意义的量进行推理，其次，存在用于组成这些策略的分层结构。利用这些见解，我们引入分层的维度知情的程序合成（LDIPS）-通过推理的物理尺寸的状态变量，和维度约束的运营商，LDIPS直接合成ASP在一个人类可解释的领域特定的语言，是服从程序修复。我们提出的实证结果表明，LDIPS 1）可以合成有效的ASP的机器人足球和自动驾驶领域，2）需要两个数量级的训练样本比可比的NN表示，和3）可以修复合成的ASP时，只有少量的校正从模拟转移到真实的机器人。
Action selection policies (ASPs), used to compose low-level robot skills into complex high-level tasks are commonly represented as neural networks (NNs) in the state of the art. Such a paradigm, while very effective, suffers from a few key problems: 1) NNs are opaque to the user and hence not amenable to verification, 2) they require significant amounts of training data, and 3) they are hard to repair when the domain changes. We present two key insights about ASPs for robotics. First, ASPs need to reason about physically meaningful quantities derived from the state of the world, and second, there exists a layered structure for composing these policies. Leveraging these insights, we introduce layered dimension-informed program synthesis (LDIPS) - by reasoning about the physical dimensions of state variables, and dimensional constraints on operators, LDIPS directly synthesizes ASPs in a human-interpretable domain-specific language that is amenable to program repair. We present empirical results to demonstrate that LDIPS 1) can synthesize effective ASPs for robot soccer and autonomous driving domains, 2) requires two orders of magnitude fewer training examples than a comparable NN representation, and 3) can repair the synthesized ASPs with only a small number of corrections when transferring from simulation to real robots.