Autonomous agents embedded in a physical environment need the ability to recognize objects and their properties from sensory data. Such a perceptual ability is often implemented by supervised machine learning models, which are pre-trained using a set of labelled data. In real-world, open-ended deployments, however, it is unrealistic to assume to have a pre-trained model for all possible environments. Therefore, agents need to dynamically learn/adapt/extend their perceptual abilities online, in an autonomous way, by exploring and interacting with the environment where they operate. This paper describes a way to do so, by exploiting symbolic planning. Specifically, we formalize the problem of automatically training a neural network to recognize object properties as a symbolic planning problem (using PDDL). We use planning techniques to produce a strategy for automating the training dataset creation and the learning process. Finally, we provide an experimental evaluation in both a simulated and a real environment, which shows that the proposed approach is able to successfully learn how to recognize new object properties.

To effectively use an abstract (PDDL) planning domain to achieve goals in an unknown environment, an agent must instantiate such a domain with the objects of the environment and their properties. If the agent has an egocentric and partial view of the environment, it needs to act, sense, and abstract the perceived data in the planning domain. Furthermore, the agent needs to compile the plans computed by a symbolic planner into low level actions executable by its actuators. This paper proposes a framework that aims to accomplish the aforementioned perspective and allows an agent to perform different tasks. For this purpose, we integrate machine learning models to abstract the sensory data, symbolic planning for goal achievement and path planning for navigation. We evaluate the proposed method in accurate simulated environments, where the sensors are RGB-D on-board camera, GPS and compass.

This is coarse-grained in that, for each variable, it either remembers all past values (red), or remembers only the most recent one (black). We herein introduce limited-memory state variables, that remember a subset of their most recent values. It turns out that planning is still PSPACE-complete even when the memory is large enough to store all but a single value. Nevertheless, limited memory can be used to substantially broaden a known tractable fragment of red-black planning, yielding better heuristic functions in some domains.

We present an extension of the planning framework based on action graphs and local search to deal with PDDL2.1 temporal problems requiring concurrency, while previously the approach could only solve problems admitting a sequential solution. The paper introduces a revised plan representation supporting concurrency and some new search techniques using it, which are implemented in a new version of the LPG planner. An experimental analysis indicates that the proposed approach is suitable to temporal planning with requiring concurrency and is competitive with state-of-the-art planners.

The field of automated plan generation has recently significantly advanced. However, while several powerful domainindependent PbP has two variants: PbP.s focusing on speed, and planners have been developed, no one of these PbP.q focusing on plan quality. PbP.s entered the learning clearly outperforms all the others in every known benchmark track of the sixth international planning competition (IPC6), domain. It would then be useful to have a multi-planner system and was the overall winner of this competition track (Fern, that automatically selects and combines the most efficient Khardon and Tadepalli 2008). The paper includes some experimental planner(s) for each given domain.