Human interaction relies on a wide range of signals, including non-verbal cues. In order to develop effective Explainable Planning (XAIP) agents it is important that we understand the range and utility of these communication channels. Our starting point is existing results from joint task interaction and their study in cognitive science. Our intention is that these lessons can inform the design of interaction agents -- including those using planning techniques -- whose behaviour is conditioned on the user's response, including affective measures of the user (i.e., explicitly incorporating the user's affective state within the planning model). We have identified several concepts at the intersection of plan-based agent behaviour and joint task interaction and have used these to design two agents: one reactive and the other partially predictive. We have designed an experiment in order to examine human behaviour and response as they interact with these agents. In this paper we present the designed study and the key questions that are being investigated. We also present the results from an empirical analysis where we examined the behaviour of the two agents for simulated users.

Autonomous agents such as self-driving cars or parcel robots need to recognize and avoid possible collisions with obstacles in order to move successfully in their environment. Humans, however, have learned to predict movements intuitively and to avoid obstacles in a forward-looking way. The task of collision avoidance can be divided into a global and a local level. Regarding the global level, we propose an approach called "Predictive Collision Management Path Planning" (PCMP). At the local level, solutions for collision avoidance are used that prevent an inevitable collision. Therefore, the aim of PCMP is to avoid unnecessary local collision scenarios using predictive collision management. PCMP is a graph-based algorithm with a focus on the time dimension consisting of three parts: (1) movement prediction, (2) integration of movement prediction into a time-dependent graph, and (3) time and risk-dependent path planning. The algorithm combines the search for a shortest path with the question: is the detour worth avoiding a possible collision scenario? We evaluate the evasion behavior in different simulation scenarios and the results show that a risk-sensitive agent can avoid 47.3% of the collision scenarios while making a detour of 1.3%. A risk-averse agent avoids up to 97.3% of the collision scenarios with a detour of 39.1%. Thus, an agent's evasive behavior can be controlled actively and risk-dependent using PCMP.

In this paper, we outline the implementation of the TFD (Totally Ordered Fast Downward) and the PFD (Partially ordered Fast Downward) hierarchical planners that participated in the first HTN IPC competition in 2020. These two planners are based on forward-chaining task decomposition coupled with a compact grounding of actions, methods, tasks and HTN problems.

This paper presents new approach based on grammar induction called AMLSI Action Model Learning with State machine Interactions. The AMLSI approach does not require a training dataset of plan traces to work. AMLSI proceeds by trial and error: it queries the system to learn with randomly generated action sequences, and it observes the state transitions of the system, then AMLSI returns a PDDL domain corresponding to the system. A key issue for domain learning is the ability to plan with the learned domains. It often happens that a small learning error leads to a domain that is unusable for planning. Unlike other algorithms, we show that AMLSI is able to lift this lock by learning domains from partial and noisy observations with sufficient accuracy to allow planners to solve new problems.

Qualitative numerical planning is classical planning extended with non-negative real variables that can be increased or decreased "qualitatively", i.e., by positive indeterminate amounts. While deterministic planning with numerical variables is undecidable in general, qualitative numerical planning is decidable and provides a convenient abstract model for generalized planning. The solutions to qualitative numerical problems (QNPs) were shown to correspond to the strong cyclic solutions of an associated fully observable non-deterministic (FOND) problem that terminate. This leads to a generate-and-test algorithm for solving QNPs where solutions to a FOND problem are generated one by one and tested for termination. The computational shortcomings of this approach for solving QNPs, however, are that it is not simple to amend FOND planners to generate all solutions, and that the number of solutions to check can be doubly exponential in the number of variables. In this work we address these limitations while providing additional insights on QNPs. More precisely, we introduce two polynomial-time reductions, one from QNPs to FOND problems and the other from FOND problems to QNPs both of which do not involve termination tests. A result of these reductions is that QNPs are shown to have the same expressive power and the same complexity as FOND problems.

Cable trees are widely used in industrial products to transmit energy and information between different product parts. For example, cable trees are needed in cars to automate many previously mechanical functions such as moving seats or opening windows and to add new functions such as a voice-controlled navigation or an onboard entertainment system. It is thus not surprising that for example a car like the VW Golf 7 contains 14 cable trees with a total of 1633 cables. The manufacturing of cable trees usually relies on cheap manual labour performed in low-cost countries where humans plug cables into harnesses following a wiring plan. Only few automated manufacturing solutions exist, which rely on complex robotic machines. These machines execute a sequence of wiring operations that highly qualified technicians develop by analyzing the wiring plan. With the continuing tendency towards customer-specific and resource-efficient justin-time manufacturing, smaller batch sizes of cable trees need to be manufactured requiring a frequent change of wiring plans, for which wiring sequences should be derived instantly. Scaling up human expertise to such frequent changes is simply impossible, which explains a growing interest in the intelligent automated manufacturing of cable trees. This interest is also nourished by a further miniaturization of cable harnesses, which will make their manual manufacturing impossible.

The future will be replete with scenarios where humans are robots will be working together in complex environments. Teammates interact, and the robot's interaction has to be about getting useful information about the human's (teammate's) model. There are many challenges before a robot can interact, such as incorporating the structural differences in the human's model, ensuring simpler responses, etc. In this paper, we investigate how a robot can interact to localize the human model from a set of models. We show how to generate questions to refine the robot's understanding of the teammate's model. We evaluate the method in various planning domains. The evaluation shows that these questions can be generated offline, and can help refine the model through simple answers.

The European research project START, coordinated by the Universidad Carlos III de Madrid (UC3M) and with the participation of important actors in the aeronautical scene, combines Big Data and Artificial Intelligence to develop algorithms that allow air traffic networks to be optimised during storms. This would improve the safety and timeliness of flights and reduce economic losses associated with delays and cancellations. Sometimes, during flights, aircrafts have to change their route (their flight plan) because of unforeseen events, such as storms. These meteorological phenomena, which may be accompanied by hail and lightning, are difficult to predict; they are known to appear in a wide area, but it is difficult to accurately predict when and where the storm focus will happen. START's objective is the development of research algorithms for optimising air transport networks in terms of their resilience (the system's recovery capacity) when facing this kind of disruptive phenomena.

Sometimes, during flights, aircrafts have to change their route (their flight plan) because of unforeseen events, such as storms. These meteorological phenomena, which may be accompanied by hail and lightning, are difficult to predict; they are known to appear in a wide area, but it is difficult to accurately predict when and where the storm focus will happen. START's objective is the development of research algorithms for optimising air transport networks in terms of their resilience (the system's recovery capacity) when facing this kind of disruptive phenomena. "The storms we are analysing in this project are convective, typically cumulonimbus (a type of cloud), which are very energetic and dangerous for an aircraft in flight, so pilots tend to systematically avoid them", explains the project's coordinator, Manuel Soler, from the UC3M's Department of Bioengineering and Aerospace Engineering. In addition to heavy rain, these storms often present hail, lightning, and thunder, and may eventually block airports or large airspace corridors.

A new design of an AI assistant that has become increasingly popular is that of an "aggregated assistant" - realized as an orchestrated composition of several individual skills or agents that can each perform atomic tasks. In this paper, we will talk about the role of planning in the automated composition of such assistants and explore how concepts in automated planning can help to establish transparency of the inner workings of the assistant to the end-user. Conversational assistants such as Siri, Google Assistant, Figure 1: Simplified architecture diagram of Verdi (Rizk et and Alexa have found increased user adoption over the last al.