The paper describes a novel use of planning in Reconfigurable Manufacturing. Authors considered the nodes of a manufacturing plant as individual AI-based agents able to reason on continuously updated representation of their domain model, plan their own actions, and execute them. The paper aims at clarifying the role of planning, its connection with both a goal selection mechanism, and the agent's knowledge. It describes in detail how a planning system has been customized for the task of planning and execution and shows results of a realistic simulation on a manufacturing plant.

Generalized planning is the task of generating a single solution that is valid for a set of planning problems. In this paper we show how to represent and compute generalized plans using procedural Domain Control Knowledge (DCK). We define a divide and conquer approach that first generates the procedural DCK solving a set of planning problems representative of certain subtasks and then compile it as callable procedures of the overall generalized planning problem. Our procedure calling mechanism allows nested and recursive procedure calls and is implemented in PDDL so that classical planners can compute and exploit procedural DCK. Experiments show that an off-the-shelf classical planner, using procedural DCK as callable procedures, can compute generalized plans in a wide range of domains including non-trivial ones, such as sorting variable-size lists or DFS traversal of binary trees with variable size.

We introduce a multi-agent route planning problem for col-lecting sensor data in hostile or dangerous environmentswhen communication is unavailable. Solutions must considerthe risk of losing robots as they travel through the environ-ment, maximizing the expected value of a plan. This requiresplans that balance the number of agents used with the riskof losing them and the data they have collected so far. Whilethere are existing approaches that mitigate risk during task as-signment, they do not explicitly account for the loss of robotsas part of the planning process. We analyze the unique prop-erties of the problem and provide a hierarchical agglomera-tive clustering algorithm that finds high value solutions withlow computational overhead. We show that our solution ishighly scalable, exhibiting performance gains on large problem instances with thousands of tasks.

Planning in hybrid systems is important for dealing with real-world applications. PDDL supports this representation of domains with mixed discrete and continuous dynamics, and supports events and processes modelling exogenous change. Motivated by numerous SAT-based planning approaches, we propose an approach to PDDL planning through SMT, describing an SMT encoding that captures all the features of the PDDL problem as published by Fox and Long. The encoding can be applied on domains with nonlinear continuous change. We apply this encoding in a simple planning algorithm, demonstrating excellent results on a set of benchmark problems.

Interaction with users is a key capability of planning systems that are applied in real-world settings. Such a system has to be able to react appropriately to requests issued by its users. Most of these systems are based on a generated plan that is continually criticised by him, resulting in a mixed-initiative planning system. We present several practically relevant requests to change a plan in the setting of hierarchical task network planning and investigate their computational complexity. On the one hand, these results provide guidelines when constructing algorithms to execute the respective requests, but also provide translations to other well-known planning queries like plan existence or verification. These can be employed to extend an existing planner such that it can form the foundation of a mixed-initiative planning system simply by adding a translation layer on top.

Recent work has begun exploring the value of domain abstractions in Monte-Carlo Tree Search (MCTS) algorithms for probabilistic planning.

Hierarchical Task Network (HTN) planning is a formalism that can express constraints which cannot easily be expressed by classical (non-hierarchical) planning approaches. It enables reasoning about procedural structures and domain-specific search control knowledge. Yet the cornucopia of modern heuristic search techniques remains largely unincorporated in current HTN planners, in part because it is not clear how to estimate the goal distance for a partially-ordered task network. When using SHOP2-style progression, a task network of yet unprocessed tasks is maintained during search. In the general case it can grow arbitrarily large.

In many robot motion planning problems such as manipulation planning for a personal robot in a kitchen or an industrial manipulator in a warehouse, all motion planning queries are in an environment that is largely static. Consequently, one should be able to improve the performance of a planning algorithm by training on this static environment ahead of operation time. In this work, we propose a method to improve the performance of heuristic search-based motion planners in such environments. The first, learning, phase of our proposed method analyzes search performance on multiple planning episodes to infer local minima zones, that is, regions where the existing heuristic(s) are weakly correlated with the true cost-to-go. Then, in the planning phase of the method, the learnt local minima are used to modify the original search graph in a way that improves search performance. We prove that our method preserves guarantees on completeness and bounded suboptimality with respect to the original search graph. Experimentally, we observe significant improvements in success rate and planning time for challenging 11 degree-of-freedom mobile manipulation problems.

Robot navigation through non-uniform environments requires reliable motion plan generation. The choice of planning model fidelity can significantly impact performance. Prior research has shown that reducing model fidelity saves planning time, but sacrifices execution reliability. While current adaptive hierarchical motion planning techniques are promising, we present a framework that leverages a richer set of robot motion models at plan-time. The framework chooses when to switch models and what model is most applicable within a single trajectory.

This paper presents a framework developed for an industrial robotics system that utilises two different planning components. At a high level, a multi-robot mission planner interfaces with a fleet and environment manager and uses multiagent planning techniques to build mission assignments to be distributed to a robot fleet. On each robot, a task planner automatically converts the robot's world model and skill definitions into a planning problem which is then solved to find a sequence of actions that the robot should perform to complete its mission. This framework is demonstrated on an industrial kitting task in a real-world factory environment.