This paper addresses the problem of learning abstractions that boost robot
planning performance while providing strong guarantees of reliability. Although
state-of-the-art hierarchical robot planning algorithms allow robots to
efficiently compute long-horizon motion plans for achieving user desired tasks,
these methods typically rely upon environment-dependent state and action
abstractions that need to be hand-designed by experts.
We present a new approach for bootstrapping the entire hierarchical planning
process. This allows us to compute abstract states and actions for new
environments automatically using the critical regions predicted by a deep
neural network with an auto-generated robot-specific architecture. We show that
the learned abstractions can be used with a novel multi-source bi-directional
hierarchical robot planning algorithm that is sound and probabilistically
complete. An extensive empirical evaluation on twenty different settings using
holonomic and non-holonomic robots shows that (a) our learned abstractions
provide the information necessary for efficient multi-source hierarchical
planning; and that (b) this approach of learning, abstractions, and planning
outperforms state-of-the-art baselines by nearly a factor of ten in terms of
planning time on test environments not seen during training.

本研究介绍了一种使用深度神经网络自动生成机器人特定体系结构进行环境预测和自动计算抽象状态和动作的方法，得到的结果可用于提高机器人的规划性能和可靠性。研究结果表明，所学习的抽象状态和动作可以与一种新型的多源双向分层机器人规划算法配合使用，在测试环境中的计划时间上的表现比现有技术的基准方法提高了近 10 倍。

使用深度学习为分层机器人规划引导抽象化

Using Deep Learning to Bootstrap Abstractions for Hierarchical Robot Planning

Mobile manipulation problems involving many objects are challenging to solve
due to the high dimensionality and multi-modality of their hybrid configuration
spaces. Planners that perform a purely geometric search are prohibitively slow
for solving these problems because they are unable to factor the configuration
space. Symbolic task planners can efficiently construct plans involving many
variables but cannot represent the geometric and kinematic constraints required
in manipulation. We present the FFRob algorithm for solving task and motion
planning problems. First, we introduce Extended Action Specification (EAS) as a
general purpose planning representation that supports arbitrary predicates as
conditions. We adapt existing heuristic search ideas for solving \proc{strips}
planning problems, particularly delete-relaxations, to solve EAS problem
instances. We then apply the EAS representation and planners to manipulation
problems resulting in FFRob. FFRob iteratively discretizes task and motion
planning problems using batch sampling of manipulation primitives and a
multi-query roadmap structure that can be conditionalized to evaluate
reachability under different placements of movable objects. This structure
enables the EAS planner to efficiently compute heuristics that incorporate
geometric and kinematic planning constraints to give a tight estimate of the
distance to the goal. Additionally, we show FFRob is probabilistically complete
and has finite expected runtime. Finally, we empirically demonstrate FFRob's
effectiveness on complex and diverse task and motion planning tasks including
rearrangement planning and navigation among movable objects.

介绍了 FFRob 算法，它使用 Extended Action Specification (EAS) 作为一般性的计划表示来支持任意谓词为条件。通过使用批量采样操纵基元和一个多查询路网结构来迭代离散化任务和运动规划问题，FFRob 可以有效地计算启发式，并结合几何和运动学规划约束，给出距离目标的紧密估计。同时，FFRob 也是概率上完备并且具有有限的期望运行时间。